4508 Final Quality Project Part 2 Clinical Quality Measur

4508 Final Quality Project
Part 2: Clinical Quality Measures for Hospitals
Overview
This activity focuses on Quality Measures for Hospitals. The act
ivity uses online resources from
the CMS website. The Clinical Quality Measures for Hospitals a
ctivity focuses on the Hospital
Value Based Purchasing (VBP) Program
Background
The National Quality Strategy (NQS) was first published in Mar
ch 2011 as the National Strategy
for Quality Improvement in Health Care, and is led by the Agen
cy for Healthcare Research and
Quality on behalf of the U.S. Department of Health and Human
Services (HHS). Today, the NQS
serves as a guide for identifying and prioritizing quality improv
ement efforts, sharing lessons
learned, and measuring the collective success of Federal, State,
and public‐ and private‐sector

healthcare stakeholders across the country.
The Aims of the NQS are threefold:
Better Care: Improve the overall quality by making health care
more patient‐centered,
reliable, accessible, and safe.
Healthy People/Healthy Communities: Improve the health of the
U.S. population by
supporting proven interventions to address behavioral, social, a
nd environmental
determinants of health in addition to delivering higher‐quality c
are.
Affordable Care: Reduce the cost of quality health care for indi
viduals, families,
employers, and government.
To align with this, CMS has set goals for their Quality Strategy.
These include:
•
Make care safer by reducing harm caused in the delivery of care
– Improve support for a culture of safety
– Reduce inappropriate and unnecessary care
– Prevent or minimize harm in all settings
•
Strengthen person and family engagement as partners in their ca
re

• Promote effective communication and coordination of care
• Promote effective prevention and treatment of chronic disease
•
Work with communities to promote best practices of healthy livi
ng
• Make care affordable
CMS’s vision states that if we can find better ways to pay provi
ders, deliver care, and distribute
information than patients can receive better care, health dollars
are spent more wisely, and
there are healthier communities, a healthier economy, and a heal
thier county. It is with this in
mind that they have created multiple quality payment programs.
In January 2015, the Department of Health and Human Services
made an announcement that
set in place measurable goals and a timeline to move the Medica
re program towards paying
providers based on the quality of care rather than the quantity.
This was the first time in the
history of the program that explicit goals were set. They invite
d private sector payers to match
or exceed these goals as well. These goals included:
1. Alternative Payment Models

a.
30% of Medicare payments tied to quality or value through Alte
rnative Payment
models by the end of 2016 and 50% by the end of 2018
2. Linking Fee‐For‐Service payments to Quality/Value
a.
85% of all Medicare fee‐for‐service payments tied to quality or
value by 2016;
90% by the end of 2018
The Affordable Care Act was passed in 2010 and authorized the
establishment of the Hospital
VBP Program, built on the quality reporting infrastructure of th
e Hospital Inpatient Quality
Reporting (Hospital IQR) Program. The programs intent was to
promote better clinical
outcomes for hospital patients, improve the patient experience o
f care during hospital stays,
and encourage hospitals to improve the quality and safety of car
e that all patients receive by:
or reducing the occurrence of adverse events,
Adopting evidence‐based care standards and protocols that resul
t in the best outcomes
for the most patients, and

Re‐engineering hospital processes that improve patients’ experi
ence of care.
There are several domains covered by the Hospital VBP progra
m. The first year began with 2
domains and increased over time to the current 4 domains. Thes
e domains and the weights
assigned to them vary over the years. Below is a table of these
domains and their weights by
year:
2013 2014 2015 2016
Clinical Process of Care 70% 45% 20% 10%
Patient Experience of Care 30% 30% 30% 25%
Outcome ‐ 25% 30% 40%
Efficiency ‐ ‐ 20% 25%
The following 2 years had changes to the language of the catego
ries
2017 2018
Clinical Care 5% 25%
Patient and Caregiver Experience of Care/Care Coordination
25% 25%
Outcome 25% ‐

Efficiency (and “cost reduction” in 2018) 25% 25%
Safety 20% 25%
The following 2 years (2019 and 2020) are subject to the propos
ed updates:
Care – 25%
and Community Engagement – 25%
– 25%
and Cost Reduction – 25%
The Hospital VBP program adjusts hospitals’ payments based o
n their performance on the
domains that reflect hospital quality. Each data set includes the
following:
achievement score –
scores awarded to hospitals that achieve certain levels of
performance compared to other hospitals; compare an individual
hospital’s rates with
all other participating hospital’s rates from a baseline period
improvement score –
scores award to hospitals that improved over its own baseline
period performance; compare an individual hospital’s rates with
all their own rates from
a baseline period
measure/dimension score –

represents higher of either the achievement or
improvement points
The total score for each hospital is out of 100. The program is b
udget neutral and uses the
funds saved by reducing payments for base operating diagnosis‐
related group (DRG) payments
to fund value‐based incentive payments to hospitals for discharg
es in that fiscal year based on
their performance under the program.
The applicable percent reduction to participating hospitals’ base
operating DRG payment
amounts increased by 0.25% each year, starting at a 1% reductio
n in the first year of the
Hospital VBP program until it reached 2%. The reductions by y
ear are:
1%
1.25%
2015: 1.5%
1.75%
2%
Incentive payments are applied to hospitals on a claim‐by‐claim
basis and each hospital’s value‐
based incentive payment percentage that the hospital earns for t

he year is determined based
on that hospital’s Total Performance Score (TPS) on the Hospita
l VBP measures. The hospital’s
TPS is converted to a value‐based incentive payment adjustment
factor, and that factor is then
multiplied by the base operating DRG payment amount for each
Medicare fee‐for‐service
discharge in a year to calculate the adjusted payment amount th
at applies to the discharge for
that year.
In 2018, there was a 2% reduction in base DRG payments for th
e year which made $1.9 billion
available for Value‐Based Incentive payments.
Domains
Clinical Care Domain
Assesses estimates of deaths in the 30 days after entering the ho
spital for a specific condition
(reported as the “survival” rate; therefore, higher percentage rat
es are favorable). Patients who
received high‐quality care during their hospitalizations and their
transition to the outpatient
setting will likely have improved outcomes, like survival rate. I

ncludes:
myocardial infarction (AMI) 30‐day mortality rate
failure (HF) 30‐day mortality rate
(PN) 30‐day mortality rate
Person and Community Engagement Domain
Based on the HCAHPS (Hospital Consumer Assessment of Healt
hcare Providers and Systems)
which is a national, standardized survey that asks adult patients
about their experiences during
a recent hospital stay. The domain score encompasses 8 importa
nt dimensions of hospital
quality:
with nurses
with doctors
of hospital staff
and quietness of hospital environment
about medicines

information
transition
rating of hospital
Safety Domain
Assesses a broad set of healthcare activities that affect patients’
well‐being. Patients who
received high‐quality care during their hospitalizations will like
ly have improved outcomes, like
reduced risk of in‐hospital falls with hip fracture, bed sores, and
other adverse events, reduced
risk of healthcare‐associated infections, and improved quality of
life. Includes:
(PSI‐90) patient safety for selected indicators
line‐associated bloodstream infection (CLABSI)
urinary tract infection (CAUTI)
site infection (SSI)
Staphylococcus Aureus (MRSA)
difficile Infection (CDI)
Care (PC)‐01
Efficiency and Cost Reduction Domain
Increases the transparency of care for consumers by recognizing
hospitals that provide high
quality care at lower costs to Medicare. Is determined by the M
edicare spending per

beneficiary (MSPB) measure.
Activity 1: Answer the following critical thinking questions:
1.
The patient experience/engagement category has remained stead
y over the years,
ranging from 25‐30% of the total score. Why is it important for
organizations to be
graded on this category? What affect does it have on the healthc
are provided?
2.
The category of efficiency/cost reduction was introduced in 201
5. What is the
importance of measuring efficiency/cost reduction on the health
care system as a
whole?
3.
Do you think a 2% reduction in payments is sufficient to encour
age behavioral changes
in the quality of care provided? Why or why not?
Activity 2:

You will review several facilities and their scores for the Hospit
al Value‐Based Purchasing
program. Scores are provided on the CMS website but have bee
n extracted and combined to a
single excel file located on the modules page under this assignm
ent. Each domain has a
separate tab in the excel file as well as a separate tab for Total
Performance Score.
the HVBP Scores file
Use the Hospital Measures Definitions file to identify the measu
res in the HVBP Scores
file.
Search the corresponding tabs for the 3 local hospitals and their
scores.
Hospital Provider Number
Orlando Health 100006
Florida Hospital 100007
Osceola Regional Medical Center 100110
4.
Under the Clinical Care domain, what was the benchmark for th
e “Acute Myocardial
Infarction (AMI) 30‐day mortality rate”?
a. 0.8732

b. 0.8506
c. 0.90
d. 10 out of 10 points
5.
Under the Clinical Care domain, which hospital had a performan
ce rate lower than the
benchmark for “Acute Myocardial Infarction (AMI) 30‐day mort
ality rate”?
a. Orlando Health
b. Florida Hospital
c. Osceola Regional Medical Center
6.
Under the Clinical Care domain, which hospital had a performan
ce rate lower than their
baseline for “Heart Failure (HF) 30‐day mortality rate”?
a. Orlando Health
b. Florida Hospital
7.
Under the Patient Experience of Care domain, what was the achi
evement threshold for
“Responsiveness of hospital staff”?
a. 0.90
b. 32.72

c. 65.16
d. 80.15
8.
Under the Patient Experience of Care domain, which hospital re
ceived improvement
points for “Communication with Doctors”?
a. Orlando Health
b. Florida Hospital
9.
Under the Patient Experience of Care domain, Florida Hospital r
eceived 5 points for
their “Care Transition” measure score. Were these points for ac
hievement or
improvement?
a. Achievement
b. Improvement
10.
Under the Safety domain, what was the benchmark for “Perinata
l Care (PC)‐01” (This is
identified as (PC‐01))?
a. 0
b. 0.0204
c. 10 out of 10 points

11.
Under the Efficiency domain, what was the achievement thresho
ld for “Medicare
spending per beneficiary (MSPB)”?
a. 0
b. 0.9869
c. 0.8396
d. 10 out of 10 points
12.
Under the Total Performance Score, which hospital had the high
est TPS?
a. Orlando Health
b. Florida Hospital
Data Science for Building Energy Management: a review
Miguel Molina-Solanaa,b, Maŕıa Rosa,∗, M. Dolores Ruiza,
Juan Gómez-Romeroa, M.J. Martin-Bautistaa
aDepartment of Computer Science and Artificial Intelligence,
Universidad de Granada
bData Science Institute, Imperial College London

Abstract
The energy consumption of residential and commercial
buildings has risen steadily in recent years, an
increase largely due to their HVAC systems. Expected energy
loads, transportation, and storage as well
as user behavior influence the quantity and quality of the energy
consumed daily in buildings. However,
technology is now available that can accurately monitor,
collect, and store the huge amount of data involved
in this process. Furthermore, this technology is capable of
analyzing and exploiting such data in meaningful
ways. Not surprisingly, the use of data science techniques to
increase energy efficiency is currently attracting
a great deal of attention and interest. This paper reviews how
Data Science has been applied to address the
most difficult problems faced by practitioners in the field of
Energy Management, especially in the building
sector. The work also discusses the challenges and opportunities
that will arise with the advent of fully
connected devices and new computational technologies.
1. Introduction
There is a general consensus in the world today that human
activities are having a negative impact
on the environment and have accelerated both global warming
and climate change. These environmental
threats have been intensified by the emissions produced by the
energy required for the lighting and HVAC
(heating, ventilation and air-conditioning) systems in building
constructions. According to the International
Energy Agency (IEA), residential and commercial buildings are
responsible for up to 32% of the total final
energy consumption. In fact, in most IEA countries, they

account for approximately 40% of the primary
energy consumption. Similar statistics are given by the World
Business Council for Sustainable Development
(WBCSD) within the framework of its Energy Efficiency in
Buildings (EEB) project1. Also provided is a
comprehensive review [1] of the state of the art in building
energy use (with a primary focus on energy
demand).
These data indicate that inefficient energy management in aging
buildings combined with rising construc-
tion activity in developed countries will cause energy
consumption to soar in the near future and heighten the
negative impacts associated with this consumption. Moreover,
variable energy costs call for the implemen-
tation of more intelligent strategies to adapt and reduce energy
consumption as well as to find alternative
and sustainable energy sources. The relevance of these issues is
clearly reflected in the research priorities of
the European Union, as stated in its Horizon2020 Societal
Challenge “Secure, Clean and Efficient Energy”.
This work program targets a significant reduction in energy
consumption by 2020 in the transportation and
building sectors, both of which have great potential for energy
savings.
Increasing energy efficiency is a two-fold process. Not only
does it involve the use of affordable energy
sources, but also the improvement of current energy
management procedures and infrastructures. The
∗ Corresponding author
Email addresses: [email protected] (Miguel Molina-Solana),
[email protected] (Maŕıa Ros),
[email protected] (M. Dolores Ruiz), [email protected] (Juan

Gómez-Romero), [email protected] (M.J.
Martin-Bautista)
1http://www.wbcsd.org/web/eeb.htm
Preprint submitted to Renewable & Sustainable Energy Reviews
June 25, 2017
http://www.wbcsd.org/web/eeb.htm
latter includes the optimization of energy generation and
transportation based on user demand [2], one of
the most important issues for energy companies. In this regard,
computer-aided approaches have recently
come into the spotlight. More specifically, increased data
awareness in companies has led to the development
of solutions based on Data Mining, a research area that studies
how to automatically discover non-trivial
knowledge from data, and Data Science, which encompasses a
wide range of techniques and more complex
datasets.
In the area of building energy management, Data Science is now
used to address problems such as the
following: (i)the prediction of energy demand in order to adapt
production and distribution; (ii) the analysis
of building operations as well as of equipment status and
failures to optimize operation and maintenance
costs; (iii) the detection of energy consumption patterns to
create customized commercial offers and to
detect fraud. This requires collecting data pertaining to building
operation and user behavior. These data
must also be interpreted to implement adapted energy
management policies. The information collected may
come from very heterogeneous sources ranging from in-site

sensors (located in the equipment and in the
immediate environment) to external parameters (e.g. weather,
energy costs, etc.). These advances have also
signified a shift in the perception of who owns these data and
who benefits from them [3]. Customers are
increasingly aware of the importance of their actions and the
value of the data that they generate. In this
sense, they have become actors with a key role in the energy
efficiency landscape.
This paper reviews different data science techniques and
explains how they have been employed to deal
with the difficult challenges faced by building energy
management. As reflected in recent literature on the
topic, classification and clustering methods are frequently used
for this purpose, but there is still room
for improvement in relatively underexplored areas, such as
frequent and temporal pattern discovery for
load prediction. Also discussed are future trends in Data
Science, which will lead to new methods and
tools capable of the more intelligent processing of large
amounts of data collected from multiple distributed
devices. Although there are other reviews on automatic
techniques for building efficiency assessment [4, 5],
and on classification methods for load and energy consumption
prediction [6], this work examines and
discusses a broader set of data science techniques, and their
applications to the different aspects of building
energy management.
The paper is structured as follows. After an introduction to data
science techniques (Section 2), Section
3 summarizes recent work in Energy Data Science and situates
it in the context of the current requirements
and needs of building energy managers. Section 4 discusses the
data science techniques employed in various

fields related to building energy management. Finally, Section 5
provides an overview of new approaches
that are expected to lead to research advances, and concludes
with recommendations and guidelines for the
future.
2. Data Science
Over the years, technological tools have benefited a wide range
of domains, and Energy Efficiency and
Management is no exception. Developments in various areas of
Information and Communications Technology
(ICT), such as Control and Automation, Smart Metering, Real-
time Monitoring, and Data Science, have
had a tremendous impact on this field. As is well known, Data
Science builds systems and algorithms to
discover knowledge, detect patterns, and generate useful
insights and predictions from large-scale data. It
encompasses the whole data analysis process, which begins with
data extraction and cleaning, and extends
to data analysis, description and summarization. The results is
the prediction of new values and their
visualization. Data Science thus involves mathematical and
statistical analysis, combined with information
technology tools.
However, deriving insights from data is not only achieved by
using such techniques. The expert must
also manage and interpret the data in order to obtain valuable
knowledge. As shown in Figure 1, the process
starts with the collection of raw data. After that, it is necessary
to clean the data, and select the subset that
has the relevant information. For that purpose, the expert
applies filters to the data or formulates queries
that will eliminate irrelevant information. At this step, it is also
when additional sources of information

might be integrated and fused with the original data to provide
further knowledge. Once the data are
prepared for use, an exploratory analysis (including
visualization tools) can help decide which methods or
2
Data Processing
Collection of
Raw Data
Data
Cleaning
Data Pre-Processing
Data
Filtering
Exploratory
Analysis &
Visualization
of Data
Models &
Algorithms
Data
Querying
Revision Reports
Decision

Making
Visualization
of Results
Results: Data description & prediction
Data Selection
Data
Aggregation
Figure 1: Data science process
algorithms are most effective to obtain the desired knowledge.
The final process will lead to a set of results
that guide the decision-making, which again, might rely on
visualisation.
Based on the preliminary outcomes, the whole process might
need to be tuned to obtain better results.
This could entail setting new parameter values or
adding/discarding new sets of data. Since such decisions
cannot be made automatically, the participation of the expert in
the analysis of the results is a crucial factor.
From a more technically perspective, Data Science comprises a
set of techniques and tools which pursue
different goals and depart from different situations. Some of the
most popular techniques are classification,
clustering, regression and association rule mining. Although
these techniques have been the most frequently
applied in Energy Efficiency and Management, others, which
are not so well known (e.g. sequence analysis
and anomaly detection), are also useful in providing solutions
for building energy problems.

Classification When classifying a set of objects, the objective is
to predict the class of each one on the
basis of their attributes. Decision trees (i.e. a kind of flowchart
for the classification of new data) are
a common way of performing and visualizing that classification
[7]. Decision trees can be generated by
many different algorithms, though the most well known are
CLS, ID3, C4.5, C5.0, and CART. Random
Forest is another classification technique that constructs a set of
decision trees and then predicts the
class by aggregating the values obtained with each tree (e.g. by
using the mode or mean). This method
corrects overfitting (when the models from the learning
algorithm perform very well on the training set,
at the cost of an increased error on the validation set), a
common practical difficulty in decision trees.
Support Vector Machine (SVM) [8] is a technique that is also
used for classification. SVMs perfom
classification tasks by constructing a hyperplane (or a set of
hyperplanes) in a multidimensional space
to separate the data (regarded as points in the space) into
classes. Once the hyperplanes is constructed,
it classifies the new examples according to the previously
specified decision boundaries.
Bayesian classification, genetic algorithms, and neural
Networks have been also employed in classifi-
cation tasks. There are various approximations that use
probabilistic classifiers based on the Bayes’
theorem, but as a consequence, there are strong independence
assumptions between the variables in-
3

volved [9]. Class prediction with genetic programming
algorithms [10] are based on chromosome-like
structures that can be combined and/or mutated with other
chromosomes to create new individuals.
Neural Networks (NNs) are able to predict new observations
from existing ones by means of intercon-
nected elements called neurons [11]. The main advantage of
NNs is that they are robust and tolerant
of errors. A self-organizing map (SOM) is a type of artificial
neural network that is trained by un-
supervised learning to produce low-dimensional views of high-
dimensional data. Another well-known
classification method is that of k -Nearest Neighbors, which
classifies and object by the majority vote
of its k neighbors. In other words, an object is assigned to a
category based on the category of its k
nearest neighbors [12].
Regression The main objective of regression analysis is to
numerically estimate the relationship between
variables. This involves ascertaining whether variables are
independent. When they are not, it is
then necessary to discover the type of dependence of their
relation [13]. Regression analysis is widely
used in prediction and forecasting as well as to understand how
the values of dependent variables
change while those of independent variables remain fixed.
Linear and non-linear (polynomial, logistic,
etc.) regression methods are mainly used for this purpose. In
linear regression, the model assumes
that variables are a linear combination of the parameters.
Examples of linear regression methods are
linear least squares, Bayesian linear regression, and generalized
linear models (GLM). Nevertheless,
linear models often do not provide a good fit to reality, and then

non-linear models are required. In
this case, classification-based techniques, such as support
vector regression or k -Nearest Neighbors,
can also be used for regression. In particular, ARMA
(Autoregressive Moving Average) or ARIMA
(Autoregressive Integrated Moving Average) are capable of
predicting the future values of time series,
based on past values. The relationship between variables can
also be statistically measured by means
of the standard deviation, Pearson correlation, and other
correlation coefficients.
Clustering Clustering is the separation of objects into groups
(clusters) based on their degree of similarity
[14]. It is unsupervised, because there is no previous knowledge
of the classes to which the objects can
be assigned. Depending on the criterion used to measure
similarity, there are different models of cluster
analysis: (i) connectivity models, based on distance
connectivity (e.g. hierarchical clustering); (ii)
centroid models, which are constructed by assigning objects to
the nearest cluster center (e.g. k -means
or k -medians); (iii) distribution models using statistical
distributions (e.g. expectation-maximization
algorithm); (iv) density models where clusters are defined based
on high-density areas in the data set;
(v) graph-based models in which the data are expressed as
graphs. A further distinction can be made
between hierarchical and non-hierarchical models. Hierarchical
models take the form of a hierarchy
of clusters (e.g. hierarchical tree or agglomerative hierarchical
clustering) whereas non-hierarchical
models are based on a plain cluster organization without any
relations between them but rather group
a set of units into a pre-determined number of groups, using an
iterative algorithm that optimizes a

chosen criterion.
Clustering techniques are often a first step in a classification
problem when there is no information
about the classes. In an initial phase, clustering is used to
identify groups of objects with similar
features. Classification techniques are then applied to assign
new objects to these groups. When there
is no previous information about the objects, clustering
techniques can also be used for classification
purposes.
Association rules (ARs) Association rules are a useful tool for
the representation of new information
extracted from raw data and comprehensively expressed for
decision-making in the form of implication
rules of the type A → B [15]. These rules depict the frequent
co-occurrence of attributes with a
high reliability in a database. For example “most transactions
containing beer also contain diapers”
is an association rule that could be found in a supermarket
database. The Apriori algorithm and its
adaptations (e.g. generalized rule induction algorithm) are the
most widely used, though there are
others, such as the FP-Growth and ECLAT algorithms, which
improve scalability in very large datasets
[16, 17]. Association rules now have more sophisticated
versions that not only capture correlations
but other kinds of association as well. Examples include the
following: (i) generalized ARs, which use
4
a concept hierarchy to obtain rules relating the different

granularities of items; (ii) quantitative ARs,
which deal with categorical and quantitative data; (iii) gradual
dependence rules, which capture data
tendencies by obtaining rules of the type “the more/less A →
the more/less B”; (iv) sequential rules,
which identify relationships between items while considering
some ordering criterion (e.g. time).
Sequence discovery Sequence discovery comprises techniques
that identify statistically relevant patterns
in data, whose values are distributed in order [18]. Frequent
problems in sequence analysis include
the following: (i) the extraction of sequence information using
techniques such as Motif Mining (MM);
(ii) the detection of frequently occurring patterns; (iii) the
search for similar sequences with a time
lag by means of autocorrelation methods such as the ACF
(Autocorrelation Function) and PACF
(Partial Autocorrelation Function); (iv) the recovery of missing
sequence members. Many of the other
previously explained techniques are also capable of dealing
with this kind of data.
Anomaly or outlier detection The objective of detecting
anomalies is to identify items, events, or ob-
servations that deviate from expected patterns or from the usual
behavior of other data items [19].
The discovery of anomalous items is crucial in the resolution of
bank fraud, medical diagnoses, errors
in data transmission, noise, etc. Since the previously described
techniques are based on the identifica-
tion/classification of similar items, most frequent patterns, etc.,
variations of these methods can also
be employed for anomaly discovery. Methods used for this
purpose are the following: density-based
techniques, correlation, clustering, searching deviations from

association rules, and combinations of
diverse techniques using, for example, feature bagging or score
normalization.
Time series analysis Time series analysis is performed on time-
series data (i.e. data points that are
recorded over time) in order to model data and then use the
model to predict or monitor future
values of the time series [20]. The most frequently used
methods include the following: (i) methods for
exploratory analysis (e.g. autocorrelation, trend analysis,
wavelets, etc.); (ii) prediction and forecasting
techniques (e.g. regression methods, signal estimation, etc.);
(iii) classification methods which assign
a category to patterns in the series; (iv) segmentation which
aims to identify a sequence of points
sharing specific properties (e.g. ARMA or ARIMA).
Most of the previously mentioned techniques have a fuzzy
extension that allows them to process with
imprecise and uncertain data in various domains [21]. Fuzzy
logic allows a non-strict representation of
object membership to a set, thus avoiding the problem of hard
boundaries that are often present in basic
techniques, such as clustering and classification methods. For
example, fuzzy k -means is a clustering method
that has proved effective in many scenarios since it permits the
assignment of data elements to one or more
clusters [22]. Fuzzy approaches also allow a more human-
friendly representation of the extracted knowledge;
since fuzzy association rules are easier to interpret than purely
numerical rules [23].
3. Applications of Data Science for Building Energy
Management

Data science techniques have been frequently used to support
and improve basic aspects of Energy
Efficiency and Management. Accordingly, this section focuses
on applications of Data Science that are
capable of doing the following: (1) predicting the energy
demand required for the efficient operation of a
building; (2) optimizing building operation; (3) enabling
building retroffiting; (3) verifying the operational
status and failures of building equipment and networks; (4)
analyzing the economic and commercial impact
of user energy consumption; (5) detecting and preventing
energy fraud.
3.1. Prediction of building energy load
Energy demand, or energy load, refers to the amount of energy
required at a certain time instant or
interval. In particular, HVAC systems focus on thermal loads,
which refer to the quantity of heating and
cooling energy that must be added or removed from the building
to keep its occupants comfortable. Thermal
loads can be classified as internal loads, when heat
transfer/influence is produced by elements (e.g. lightning,
5
equipment, or people) within the building during its operation
or as external loads when the source of the
influence is due to external (generally environmental) factors,
such as, sun, air and moisture.
The detection of common patterns of building loads can be
extremely complex because of the number
of interrelated terms that must be dealt with. For example,

Kusiak et al. [24] created a model to select the
parameters required for a non-linear mapping of climate
measurements. Neural networks were then used to
predict the thermal loads (for heating and cooling) of a
building.
Electricity loads have also been modelled with clustering
methods. In line with this, Prahastono et
al. [25] presented an overview of common clustering methods
(e.g. hierarchical, k -means, fuzzy k -means,
follow the leader and fuzzy relation) and compared their
effectiveness in the classification of customers and
the generation of electricity load profiles (in terms of average
retail price and net generation). In contrast,
Yu et al. [26] proposed the use of decision trees to develop
predictive models for building energy demand
since they are more easily interpreted than other classification
techniques.
Peak demand is the term used in energy demand management
for a time period in which electrical power
is expected to be provided at a significantly higher supply level
than average. When the generation and
supply levels are not able to meet the demand, this can result in
power outages and load shedding, which
are evident sources of customer dissatisfaction. It is thus
extremely important to develop procedures that
can anticipate the peak demand for any given day and model
both the short-term and medium-term energy
load. Traditionally, conventional analytical methods (such as
regression) have been most frequently used
for this purpose. However, in the last few years, other data
science techniques have been applied to build
predictive models from historical data. These models are
extremely valuable because they are able to learn
the temporal trends and extrapolate them to new scenarios.

For example, Li [27] developed a decision tree to analyze the
impact of external factors on energy peaks.
The objective of this research was to learn different models for
building energy loads in different climates
by means of two regression algorithms, and use the information
from the decision trees to predict the
maximum expected load for the next day. In contrast, Yang et
al. [28] used C4.5 classification methodology
to analyze a combination of internal and external ambient
conditions, and to determine the influence of
external conditions on a building’s internal user comfort.
Load prediction may also help when predicting energy peaks.
Fan et al. [29] proposed using a combination
of models for predicting next-day energy consumption and peak
power demand. They structured their
proposal in three stages. The first stage involved extracting
abnormal building energy consumption profiles
using feature selection and clustering analysis. In the second
stage, optimal inputs for eight predictive
algorithms were selected by means of recursive feature
elimination. Finally, in the third stage, an ensemble
model was developed, whose weights were optimized by means
of a genetic algorithm.
User behavior is an important factor that alters energy demand,
and which has a significant impact on
energy load. Various studies have used data science techniques
to show that energy needs vary, depending
on the activities of the building occupants [2, 3]. Consequently,
a more cost-effective management of the
energy load based on user behavior could result in a high
percentage of savings [30].
3.2. Building operation

In the world today, building management systems generate a
considerable quantity of data. These data
contain information concerning temperature, humidity, flow
rate, pressure, power, control signals, equipment
status, etc. As such, they can be analyzed and exploited to
extract operational rules to support building
operation. In most cases, these rules are easily interpretable IF-
THEN rules, which can help to generate
recommendations for control strategies such as feedback
mechanisms, and modifications of control processes
[28]. For example, May-Ostendorp et al. [31] applied different
classification techniques to extract rules from
offline model predictive control results. The authors used those
rules to achieve near-optimal supervisory
control strategies for a mixed-mode building during the cooling
season. Although a variety of techniques can
be applied to extract IF-THEN rules, most authors use
classification techniques [32, 33], especially decision
tree algorithms [31, 28]. In addition, classification models are
effective tools that can be used to predict
building user comfort under different environmental conditions
[28].
Although association rules (ARs) are less widespread in the
field of Energy Efficiency and Management,
they can also help to identify meaningful rules for building
operation. This technique can process building-
6
related data and extract hidden correlations that are not so
evident for experienced energy management.
Yu et al. [34] used ARs to determine associations and

correlations in building operation data. Other authors
combine ARs with other techniques to derive interesting rules.
For example, in Xiao et al. [35] ARs were
used to specify the relations among the power consumptions of
major components in each cluster.
Other studies focused on the improvement of specific parts or
variables of the building. For instance,
Kusiak et al. [33] investigated the relationships between the
control settings of the air handling unit and
energy usage of the HVAC system. In this case, an algorithm
based on the combination of NNs was used
to model the non-linear relationship between energy
consumption, control settings (supply air temperature
and supply air static pressure), and a set of uncontrollable
parameters.
Clustering techniques have also been applied to analyze the data
sets generated by building automation
systems. Xaio and Fan [35] used cluster analysis to identify
daily power consumption patterns, whereas
Morbitzer et al. [36] applied clustering to analyze simulation
results for performance predictions in order to
extract predicted operation rules.
3.3. Analysis of infrastructures and retrofitting
In the last few years, new regulations have fomented the study
and analysis of aspects related to energy
efficiency and sustainable development. Both are now a clear
priority for building designers and owners,
regardless of whether the building is newly constructed or in
renovation. This signifies examining the
relations between energy loads, real consumption, and different
building components (e.g. walls, windows,
doors, lighting, heating, cooling, and ventilation). When

equipment status must be verified and potential
problems detected, data science techniques are a powerful tool
for the extraction of meaningful patterns and
correlations between those elements.
Clustering techniques are extremely effective in the analysis of
correlations between building infras-
tructure and performance. For this purpose, Morbitzer et al. [36]
applied clustering algorithms to process
building monitoring data and discover non-obvious factors of
energy loss in building infrastructures. How-
ever, clustering is not the only technique that has been
employed. Ahmed et al. [37] used classification
models to estimate indicators of building behavior, such as
comfort and room usage. They concluded that
their approach produced better results than traditional analytical
tools. The same authors also applied clas-
sification and regression techniques couple with building indoor
daylight methods to assist decision-making
and optimize building design [38].
Sequence analysis techniques, such as motif mining, were used
by Patnaik et al. [39] to enhance the
performance of cooling infrastructure. In this same line, Shao et
al. [40] extracted temporal episodic re-
lationships to better compare systematic consumption trends in
residential and commercial buildings with
different electrical infrastructure.
Furthermore, Data Science can also assist building designers in
the decision-making process by identi-
fying interrelations or patterns to support the design of low-
emission buildings. A case in point is Kim et
al. [41], whose research focused on finding basic building
elements (windows, walls, floors, etc.) that could
significantly improve the energy efficiency. For this purpose,

they used feature selection extraction combined
with C4.5 decision tree classification.
3.4. Fault detection and prevention
Certainly related with the previous issue, Data Science can also
help in verifying the operational status
and detecting faults of the building infrastructures. By
continuously monitoring the building, it is possible
to detect when a fault has happened (typically an anomalous
event) and how it affects to other equipment
(by means of correlation analysis). From the managers
perspective, it is even more interesting to anticipate
such faults by characterizing the …
Consents Apr 13,2016
MED-SURG
===============================================
===========================
*** WORK COPY ONLY *** Printed: Jul 25,
2017 06:35
LOCAL TITLE: CONSENTS
DATE OF NOTE: APR 13, [email protected]:00 ENTRY
DATE: APR 13, [email protected]:00
AUTHOR: DOCTOR,EIGHT EXP COSIGNER:
URGENCY: STATUS: COMPLETED
Patient Consent Form for Operation or Special Procedure
1. Permission: I hereby authorize the doctor (and other such
physician (s) at

the Hospital as he/she may designate) to perform upon the
following operation(s):
Total Thyroidectomy
2. Unforeseen Conditions: If any unforeseen condition arises in
the course of
the operation or procedure for which other procedures, in
addition to or
different from those above contemplated, are necessary or
appropriate in the
judgment of the said physician or his designee(s), I further
request and
authorize the carrying out of such operation or procedures.
3. Anesthesia: I consent to the administration of anesthesia
under the direction
of the Department of Anesthesiology. I understand that certain
risks and
complications (including damaged teeth) may result from the
administration of
anesthesia.
4. Specimens: Any organs or tissue surgically removed may be
examined and
retained by the Hospital for medical, scientific or educational
purposes and
such tissues or parts may be disposed of in accordance with
accustomed practice
and applicable State laws and regulations.
5. Photographing, Videotaping, etc: I consent to the
photographing, videotaping,
televising or other observation of the operation or procedures to
be performed
including appropriate portions of my body, for medical,
scientific or
educational purposes, provided my identity is not revealed by
the pictures or
descriptive texts accompanying them.

6. Explanation of Procedure, Risks, Benefits and Alternatives:
The nature and
purpose of the operation/procedure, possible alternative
methods of treatment,
the expected benefits and complications, attendant discomforts
and the risks
involved have been fully explained to me. I have been given an
opportunity to
ask questions and all my questions have been answered fully
and satisfactorily.
7. I further consent to the administration of blood or blood
products as may be
considered necessary. I recognize that there are always risks to
health
associated to the administration of blood or blood products and
such risks have
been fully explained to me.
8. No Guarantees: I acknowledge that no guarantee or assurance
has been made to
me as to the results that may be obtained.
I CERTIFY THAT I HAVE READ AND FULLY
UNDERSTAND THE ABOVE CONSENT TO OPERATION
THAT THE EXPLANATIONS THEREIN REFERRED TO
WERE MADE AND THAT ALL THE BLANK
SPACES ABOVE HAVE BEEN COMPLETED PRIOR TO MY
SIGNING.
Patient/Relative/Guardian:
Electronic Signature
Relationship, if other than patient signed: Mother
--------------------------------------------------------------------------

DOE, JON 555-55-5505 Apr 01, 1999 (17)
Jon Doe
Jon Doe
Jane Doe
MED-SURG
===============================================
===========================
2017 06:35
/es/ EIGHT DOCTOR
FACULTY
Signed: 04/13/2016 06:00
--------------------------------------------------------------------------
End of report
INPATIENT UNIT
===============================================
===========================

2017 06:37
AUTHOR: NURSE,FOUR EXP COSIGNER:
physician (s) at
following operation(s):
Left Radical Mastectomy
the course of
addition to or
appropriate in the
request and
under the direction
risks and
administration of
anesthesia.
examined and

purposes and
accustomed practice
be performed
scientific or
the pictures or
The nature and
and the risks
opportunity to
and satisfactorily.
products as may be
health
such risks have
has been made to

SIGNING.
Relationship, if other than patient signed:
/es/ FOUR NURSE
FACULTY
--------------------------------------------------------------------------
End of report
THOMAS, JANE 555-55-5504 Mar 01, 1972 (45)
Jane Thomas
Jane Thomas
INPATIENT UNIT
===============================================
===========================
2017 06:36

AUTHOR: DOCTOR,EIGHT EXP COSIGNER:
physician (s) at
following
operation(s):
L4-L5 Laminectomy
the course of
addition to or
appropriate in the
request and
under the direction
risks and
administration of
anesthesia.
examined and
purposes and

accustomed practice
be performed
scientific or
the pictures or
The nature and
and the risks
opportunity to
and satisfactorily.
products as may be
health
such risks have
has been made to

SIGNING.
Relationship, if other than patient signed:
Physician: Dr. Eight
Witness: Nurse, Five
--------------------------------------------------------------------------
Page 1
THOMAS, JON 555-55-5503 Feb 01, 1972 (45)
Jon Thomas
Jon Thomas
INPATIENT UNIT
===============================================
===========================
2017 06:36
/es/ EIGHT DOCTOR
FACULTY

Signed: 04/24/2016 07:00
--------------------------------------------------------------------------
End of report
ORTHOPAEDIC
===============================================
===========================
2017 06:34
AUTHOR: CLERK,NINE EXP COSIGNER:
Consent for:
anesthesia and right total knee arthroplasty
Consent reviewed by patient: YES
Consent signed by patient: YES
Consent reviewed by physician: YES
Consent signed by physician: YES
Procedure(s) discussed with patient: YES
Physician(s) who spoke with patient:
surgeon and anesthesiologist

Consent with patient chart: YES
/es/ NINE CLERK
FACULTY
Signed: 04/06/2016 08:45
--------------------------------------------------------------------------
End of report
SMITH, JANE 555-55-5502 Jan 01, 1972 (45)
INPATIENT UNIT
===============================================
===========================
2017 06:35
AUTHOR: CLERK,EIGHT EXP COSIGNER:
Consent for:
Consious sedation for colonoscopy,
Esophagogastroduodenoscopy and
any possible biopsies.
Consent reviewed by patient:

Consent signed by patient: YES
Consent reviewed by physician: YES
Consent signed by physician: YES
Procedure(s) discussed with patient: YES
Physician(s) who spoke with patient:
Doctor One
Consent with patient chart: YES
/es/ EIGHT CLERK
FACULTY
Signed: 04/06/2016 09:15
--------------------------------------------------------------------------
End of report
SMITH, JON 555-55-5501 Dec 1, 1974 (42)
1
A. Reviewed/Revised:
December 1, 2019
B. Purpose:
_(15)
_____________________________________________________

___
_____________________________________________________
________
_____________________________________________________
________
C. Policy:
It is the policy of Hospital XYZ to maintain an auditing and
monitoring program,
which will evaluate adherence to corporate compliance policies,
meets one of
the seven elements as stated in the Office of the Inspector
General (OIG)
Guidance on Compliance Programs for Hospitals, and the State
Office of the
Medicaid Inspector General Compliance program requirements,
Federal and
State regulations and other regulations as may be required.
D. Scope:
__(16)_________________ is responsible for documenting
clinical information
in the medical record.
__(17) ________________ is responsible for auditing the
medical record to
ensure documentation is complete.
E. Definitions:
(18) ______
__________

__________
__________
Hospital XYZ
Health Information Management Department
_(14)_____________ Policy and Procedure
2
F. Procedures:
Techniques for the auditing and monitoring process may
include:
• On-site reviews
• Unannounced mock surveys, audits and investigations
• Interviews with staff.
• Check of personnel records to determine whether any
individuals who
have been reprimanded for compliance issues in the past are
among
those currently engaged in improper conduct.
• Interviews with personnel involved in management,
operations, and
other related activities.
• Questionnaires developed to solicit impressions of a broad

cross section
of the organization's Representatives.
• Reviews of written materials and documentation prepared by
various
Representatives .
• Trend analyses or longitudinal studies that seek deviations,
positive or
negative in specific areas over a given period of time.
• Review of electronic records to determine appropriate or
inappropriate
accesses.
• Review of departmental policies and procedures.
Audit File: All documentation regarding the audit will be
maintained in the
appropriate audit file. Any corrective action required will be
tracked and
confirmed.
Audit File Retention: A copy of the documentation supporting
the findings will be
maintained in the designated audit file. This file will be
maintained indefinitely.
Training Requirements: Individuals designated by the Health
Information
Management Director to conduct audits shall participate in any
training provided
by the Corporate Compliance Office. Auditors shall:
• Possess the qualifications and experience necessary to
adequately

identify potential issues with the subject matter to be reviewed.
• Be objective and independent of line management.
• Have access to existing audit and health care resources,
relevant
personnel, and all relevant areas of operation.
• Report any and all review results and deviations from "norms"
to the
Director.
• Have the authority to request and review any related
information.
3
Self-Assessment and Annual Compliance Work Plan
An annual risk assessment will be performed to evaluate the
effectiveness of and
opportunities for improvement in the Compliance Program. Risk
areas can
include any of the following:
• Regulatory/legal issues
• Funds Flow Process
• Environmental/health/safety issues
• HR issues
• IT/systems issues
• Reimbursement

The Compliance Staff will assist the Health Information
Management Director in
determining the elements of the annual work plan, taking into
consideration the
State Office of the Medicaid Inspector General (OMIG)
compliance guidance,
yearly audit and monitoring results, risks identified through the
annual risk
assessment and recommendations from the Compliance
Committee. The HIM
Director will submit the written compliance work plan for
approval by the
Executive Committee.
Reporting
Reviews should be reported to the Director.
The Director will maintain audit documentation and report
findings on a regular
basis to the Compliance Committee and the Executive
Committee.
_____________________________
Health Info Mgmt Director
_____________________________
Compliance Director
_____________________________
Chief Executive Officer, XYZ Hospital

4508 Final Quality Project
Part 1: Quality Improvement and the EHR
Overview
This activity focuses on Quality Improvement using EHRs. The
activity uses online resources as well as
copies of actual medical records. For this assignment, you will
perform an audit of the
documentation of consents in the chart for accuracy and quality.
Afterwards, you will make
recommendations about the consent and audit process. This
encompasses quality management,
performance improvement and initiatives within a healthcare
system.
Quality Improvement (QI): Systematic and continuous actions
that lead to measurable improvement
in health care services and the health status of targeted patient
groups. (www.hrsa.gov)
Continuous Quality Improvement (CQI): Is a quality
management process that encourages all health
care team members to continuously ask the questions, “How are
we doing?” and “Can we do it
better?” (Edwards, 2008). To address these questions, a practice
needs structured clinical and
administrative data. (www.healthit.gov)
Rapid-Cycle Quality Improvement: A QI methodology that was
developed out of the need to see

improvement quicker. It reduces wasted activity and efforts for
a quick turnaround on QI projects.
PDSA/PDCA: Plan, Do, Study/Check, Act. A commonly used QI
strategy that is a four step rapid-cycle
quality improvement strategy.
• Plan: Identify an opportunity to improve and plan a change
• Do: Carry out the plan on a sample number of patients.
• Study/Check: Examine the results. Were your goals achieved?
• Act: Use your results to make a definitive decision.
Incorporate the changes into your
workflow.
SMART Goals:
• Specific (simple, sensible, significant).
• Measurable (meaningful, motivating).
• Achievable (agreed, attainable).
• Relevant (reasonable, realistic and resourced, results-based).
• Time bound (time-based, time limited, time/cost limited,
timely, time-sensitive).
http://www.hrsa.gov/
http://www.healthit.gov/
Activity 1
Watch video: Implementing EHRs to Improve Healthcare
Quality: https://youtu.be/okO8Z7ZPPuw

Watch video: The Path to Interoperability:
https://youtu.be/PaWcU7rqqyA
Answer questions 1-3.
1. Most physicians feel as if EHRs do not save them time. What
is your response to this?
a. Were EHRs designed to “save time” in the healthcare
documentation process?
b. If not, what was the EHR designed to do? Be thorough in
your response.
2. When implementing organization wide QI initiatives, many
employees and physicians take the
attitude of “that won’t work here.”
a. How should the organization respond?
b. What would be different ways of implementing an initiative
that could combat this
response?
3. Do you feel quality improvement is an easier process now
that many healthcare organizations
are utilizing an EHR? Why?
Activity 2
Use the chart forms linked in the assignment description on
Canvas to complete this activity:
You are completing an internship in the Quality Department at

General Hospital. As part of your
internship, the director of the department has asked you to
complete a small quality improvement
project utilizing their EHR. The director would like you to
determine if randomly selected five charts
meet the following criteria:
• The consent is detailed and addresses the following 8 items:
o Permission
o Unforseen Conditions
o Anesthesia
o Specimens
o Photographing, Videotaping, etc.
o Explanation of Procedure, Risks, Benefits, and Alternatives
o Blood Transfusion
o No Guarantees
• All signatures required are present
o Patient/Relative/Guardian
o Physician
o Witness
https://youtu.be/okO8Z7ZPPuw
https://youtu.be/PaWcU7rqqyA
4-8. Record chart findings: (questions will be individual
on quiz). All valid electronic signatures
are denoted by an /es/ with the name of the individual signing
and the date/time of the
signature.
Question # Chart # Yes No

4. 1
5. 2
6. 3
7. 4
8. 5
9. Based on your findings from the 5 charts, what would be a
goal for improvement (use the
SMART goal format)?
Analyze the process and come up with your QI process (keep it
simple)
10. Plan:
11. Do:
12. Check/Study:
13. Act:
Activity 3
You are the director of the Health Information Management
Department of Hospital XYZ. The
hospital has been using an EHR for 6 years and has been part of
the Meaningful Use Incentive
Program for 3 years.
Part of your success has been the routine audits of medical
records. The clinical staff is short-handed
and has admitted to not being able to document as they used to
as evidenced by the results of
Activity 2. Your current staff of two are not able to meet the
demands of auditing the charts and you

will be hiring a third person to work with you. Among your
many duties as manager is keeping
policies and procedures up-to-date.
Your team has composed the step by step process for a policy
about auditing but after you review it
you notice there are key elements missing that you as director
must complete. The policy with the
highlighted areas needed is located on the Modules page under
this assignment (Critical thinking is
required)
14. Title of policy
15. Purpose of auditing
16. Individuals responsible for documenting clinical
information in the medical record
17. Individuals responsible for auditing the medical record to
ensure documentation is complete
18. Definitions – do not define, just list the words from the
policy that should be defined

4508 Final Quality Project Part 2 Clinical Quality Measur

Recommended

Recommended

More Related Content

Similar to 4508 Final Quality Project Part 2 Clinical Quality Measur

Similar to 4508 Final Quality Project Part 2 Clinical Quality Measur (20)

More from romeliadoan

More from romeliadoan (20)

Recently uploaded

Recently uploaded (20)

4508 Final Quality Project Part 2 Clinical Quality Measur