This document discusses predicting medication adherence through predictive modeling. It begins by outlining the problem of medication non-adherence and its impacts. It then describes the methodology used, which involved blending data from Medicare, drug information databases, and census data to derive predictors and classify patients based on adherence. Regression and decision tree models with 45 predictors were able to predict medication adherence days and classify patients as adherent or non-adherent. The inferences from the models supported the hypothesis that public health, personal, and medication factors influence non-adherence. The document concludes by discussing interventions like behavioral, financial, and clinical approaches that can be tailored to individuals to improve adherence.
Dr. Mollyann Brodie: "What Soaring Drug Prices Mean for Patients," 9.3.15reportingonhealth
Dr. Mollyann Brodie's presentation from "What Soaring Drug Prices Mean for Patients," 9.3.15
http://www.reportingonhealth.org/content/what-soaring-drug-prices-mean-patients
Team Lift: Predicting Medication AdherenceNeil Ryan
Medication adherence is a growing public health concern in the US. It is the extent to which patients are taking medications as prescribed by their healthcare providers. Simply put, are patients eating their pills on time?
We looked at patient data from Medicare part D program released by Centers for Medicare & Medicaid services. We built a prediction model to ascertain whether a patient would be adherent based on a variety of social, economic and behavioral aspects.
Kristin Gourlay: "What Soaring Drug Prices Mean for Patients," 9.3.15reportingonhealth
Kristin Gourlay's presentation from "What Soaring Drug Prices Mean for Patients," 9.3.15
http://www.reportingonhealth.org/content/what-soaring-drug-prices-mean-patients
Dr. Mollyann Brodie: "What Soaring Drug Prices Mean for Patients," 9.3.15reportingonhealth
Dr. Mollyann Brodie's presentation from "What Soaring Drug Prices Mean for Patients," 9.3.15
http://www.reportingonhealth.org/content/what-soaring-drug-prices-mean-patients
Team Lift: Predicting Medication AdherenceNeil Ryan
Medication adherence is a growing public health concern in the US. It is the extent to which patients are taking medications as prescribed by their healthcare providers. Simply put, are patients eating their pills on time?
We looked at patient data from Medicare part D program released by Centers for Medicare & Medicaid services. We built a prediction model to ascertain whether a patient would be adherent based on a variety of social, economic and behavioral aspects.
Kristin Gourlay: "What Soaring Drug Prices Mean for Patients," 9.3.15reportingonhealth
Kristin Gourlay's presentation from "What Soaring Drug Prices Mean for Patients," 9.3.15
http://www.reportingonhealth.org/content/what-soaring-drug-prices-mean-patients
Presentation by Avella Specialty Pharmacy & mScripts at Armada 2015 on improving medication adherence through mobile app technology. Learn about how Avella meets the challenges of medication non-adherence: http://www.avella.com/medication-adherence
Case Study: Advanced Analytics to Help Youth At Risk Population Avoid Out of ...ODH, Inc.
Case Study: Incorporate Advanced Analytics to Help Youth at Risk Avoid Out of Home Placement. Data is critical to care management. Aggregate data from multiple sources. Apply to segment of at-risk population. Analyze and extract insight to identify interventions. NJ takes Electronic Health Records (EHR) and pairs with health IT to improve out of home placement decisions. Presented at the Payer's Behavioral Health Management Track on Tues, Oct. 16, 2018 by Michael Golinkoff, PhD, MBA, Sr. Vice President, AmeriHealth Caritas, Innovation Advisor, and Daniel Carpenter, PhD, Sr. Director, Delivery & Account Management, ODH, Inc.
Population Health Management PHM MLCSU huddleMatthew Grek
Andi Orlowski (Director of The Health Economics Unit) give an overview of Population Health Management (PHM) to the Midlands and Lancashire Commissioning Support Unit Huddle, on 25 March 2021
Pittsburgh Nonprofit Summit - Health Care & Health Care Reform - Implications...GPNP
The health care act is difficult to navigate and nonprofits were written into the act under the auspices of small businesses, making it even more confusing to understand. Gain insights from experts about the intent of the act and the act in its current draft, how it will impact nonprofits as small businesses, the impact on staff, those we serve, and on society at large. Additionally, portions of the act are still being debated and amended; learn of the potential changes and points where the nonprofit sector can influence the outcome.
Presentation by Avella Specialty Pharmacy & mScripts at Armada 2015 on improving medication adherence through mobile app technology. Learn about how Avella meets the challenges of medication non-adherence: http://www.avella.com/medication-adherence
Case Study: Advanced Analytics to Help Youth At Risk Population Avoid Out of ...ODH, Inc.
Case Study: Incorporate Advanced Analytics to Help Youth at Risk Avoid Out of Home Placement. Data is critical to care management. Aggregate data from multiple sources. Apply to segment of at-risk population. Analyze and extract insight to identify interventions. NJ takes Electronic Health Records (EHR) and pairs with health IT to improve out of home placement decisions. Presented at the Payer's Behavioral Health Management Track on Tues, Oct. 16, 2018 by Michael Golinkoff, PhD, MBA, Sr. Vice President, AmeriHealth Caritas, Innovation Advisor, and Daniel Carpenter, PhD, Sr. Director, Delivery & Account Management, ODH, Inc.
Population Health Management PHM MLCSU huddleMatthew Grek
Andi Orlowski (Director of The Health Economics Unit) give an overview of Population Health Management (PHM) to the Midlands and Lancashire Commissioning Support Unit Huddle, on 25 March 2021
Pittsburgh Nonprofit Summit - Health Care & Health Care Reform - Implications...GPNP
The health care act is difficult to navigate and nonprofits were written into the act under the auspices of small businesses, making it even more confusing to understand. Gain insights from experts about the intent of the act and the act in its current draft, how it will impact nonprofits as small businesses, the impact on staff, those we serve, and on society at large. Additionally, portions of the act are still being debated and amended; learn of the potential changes and points where the nonprofit sector can influence the outcome.
Biopharmaceutics Classification System (BCS) & Waiver of BioequivalenceAjaz Hussain
Graduate Lecture at the University of Maryland (August 2012). Learning Objective: Identify and explain how future regulatory applications of BCS may be realized in the context of ‘Quality by Design’.
Updated July 2013.
I wish to thank all the viewers of my Slideshare presentation of the development and application of the US FDA’s BCS Guidance 2000. Over 11K views have been recorded making this the 2nd highest viewed presentation. FDA is expected to issue a revised BCS draft guidance in the next few weeks. Expected changes include the following:
1. Addition of ‘very rapid’ dissolution criteria (>85% in 15 minutes)
2. Change permeability boundary from 90% to 85%
3. Change the pH solubility range from 1 – 7.5 to 1 – 6.8
4. Possibility of changing paddle speed from 50 to 75 rpm.
5. Additional topics / clarification on FDCs (Fixed Dose Combinations), ODTs (Orally Disintegrating Tablets), MR (Modified Release) products.
6. Update the list of model drugs.
7. Strengthen GI stability requirement.
Bioavailability and Bioequivalence Studies (BABE) & Concept of BiowaiversJaspreet Guraya
The presentation gives an insight on BABE studies, mathematical and statistical procedures involved in designing these studies, the official guidelines regarding study design. In the later part it also discusses about biowaivers and their role.
BRP Pharmaceuticals is a leader in physician dispensing services that provides instant medication to patients located in Burbank, CA. Visit: http://www.brppharma.com/
Preventing Medication Errors: A $21 Billion OpportunityHealth Catalyst
With a potential industry-wide savings of almost $21 billion and an impact on more than seven million patient lives, preventing harmful medication error is a significant improvement opportunity for health systems. Also known as adverse drugs events (ADEs), harmful medication errors comprise about 37 percent of all medical harm. Approximately 50 percent of ADEs are preventable, making their reduction a highly impactable area of patient safety.
Current data and analytics workflow tools are making ADE surveillance, monitoring, and prevention increasingly more effective with four key capabilities:
Perspective surveillance for ADEs and identification of previously undescribed ADEs.
Identification of the root cause of many ADEs by drug class.
Prescription at appropriate doses for patients with compromised kidney or liver functions.
Identification of different types of harm to find causes.
March 02, 2018
Value-based health care is one of the most pressing topics in health care finance and policy today. Value-based payment structures are widely touted as critical to controlling runaway health care costs, but are often difficult for health care entities to incorporate into their existing infrastructures. Because value-based health care initiatives have bipartisan support, it is likely that these programs will continue to play a major role in both the public and private health insurance systems. As such, there is a pressing need to evaluate the implementation of these initiatives thus far and to discuss the direction that American health care financing will take in the coming years.
To explore this important issue, the Petrie-Flom Center for Health Law Policy, Biotechnology, and Bioethics at Harvard Law School collaborated with Ropes & Gray LLP to host a one-day conference on value-based health care. This event brought together scholars, health law practitioners, and health care entities to evaluate the impact of value-based health care on the American health care system.
For more information, visit our website at: http://petrieflom.law.harvard.edu/events/details/will-value-based-care-save-the-health-care-system
Although symptoms can vary widely, the first problem many people notice is forgetfulness severe enough to affect their ability to function at home or at work or to enjoy lifelong hobbies.
Becoming Better Advocates for Your HealthBest Doctors
A leader and innovator in research on patient-centered care, Dr. Leana Wen will share her perspectives on what patients and providers can do to work more effectively together to achieve their shared goal – better health and outcomes. She will be joined by Sonia Millsom, VP of Best Doctors, who will discuss how optimizing care and controlling costs are within reach for today’s patient. The presenters will finish with live questions from the audience.
Provider Based Patient Engagement - An Essential Strategy for Population HealthPhytel
As the healthcare industry starts to re-engineer care delivery to accommodate new reimbursement models, providers on the front lines of change recognize the need for population health management and for increasing patients’ engagement in their own care. These two approaches are inextricably bound together, because it is impossible to manage the health of a population without getting patients more involved in self-management and the modification of their own risk factors. This paper discusses the fundamentals of patient engagement and shows how automation tools and web-based care management can facilitate this key process.
Lean Healthcare: 6 Methodologies for Improvement from Dr. Brent JamesHealth Catalyst
The survival of healthcare organizations depends on applying lean principles. Organizations that adopt lean principles can reduce waste while improving the quality of care. By applying stringent clinical data measurement approaches to routine care delivery, healthcare systems identify best practice protocols and incorporate those into the clinical workflow. Data from these best practices are applied through continuous-learning loop that enables teams across the organization to update and improve protocols–ultimately reducing waste, lowering costs, and improving access to care.
This executive report based on a presentation by Dr. Brent James at a regional medical center, covers the following:
1. How lean healthcare principles can help improve the quality of care.
2. The steps healthcare organizations need to take to create a continuous-learning loop.
3. How a lean approach creates financial leverage by eliminating waste and improving net operating margins and ROI.
2. Our Team
Data by itself isn’t worth anything unless there’s a problem
to solve and a community to solve it.
- Beth Noveck, Founder, GovLab
Suresh Prasanth Bala Sakthi
3. Medication non-adherence is a major and growing public health concern, as
20% to 30% of medication prescriptions are never filled consistently.
Heart Disease and Strokes
• Cause 1 of every 3 deaths
• Over 2 million heart attacks and strokes
each year
– 800,000 deaths
– Leading cause of preventable death in
people <65
– $444 B in health care costs and lost
productivity
– Treatment costs are ~$1 for every $6
spent
• Greatest contributor to racial disparities in
life expectancy
The less good news is that we are not
reaching 50% medical adherence.
100%
88%
76%
47%
Rx Prescribed
Rx Filled
Rx Taken
Rx Continued
The good news is that we know what
works, and the medications, when
required, are low cost.
Medication Adherence
Source: American Heart Association: Statistics you need to know.
http://www.americanheart.org/presenter.jhtml?identifier=107
Accessed November 21, 2007.
Source: Roger VL, et al. Circulation 2012;125:e2-e220
Heidenriech PA, et al. Circulation 2011;123:933–4
4. Investment in medication adherence can lead to dramatic reductions in
overall cost of care
Why adherence matters?
• Results of failure to adhere to prescribed
medications:
– Increased hospitalization
– Poor health outcomes
– Increased costs
– Decreased quality of life
– Patient death
Diabetes Medication level of Adherence
$8,812
$6,959
$6,237 $5,887
$3,808
$55
$165
$285
$404
$763
1-19% 20-39% 40-59% 60-79% 80-100%
Rx $
Medical $
About 30% to 50% of treatment failures
are due to medication non-adherence.
These treatment failures are estimated
to cause 125,000 deaths annually.
Healthcare expenditure ($/year)
Outcome is significantly higher than outcome for 80-
100% adherence group (P<0.05). Differences were
tested for medical cost and hospitalization risk.
Source: Sokol M et al. Impact of Medication Adherence on Hospitalization
Risk and Healthcare Cost. Medical Care.
Volume 43, Number 6, June 2005
Source: Benner JS, Glynn RJ, Mogun H, Neumann PJ, Weinstein MC, Avorn J.
Long-term persistence in use of statin therapy in elderly patients. JAMA
2002;288:455-461
5. Medical adherence needs to be addressed in Primary Care
Top reasons for nonadherence
• Cost of medications
• Side effects/fear of side effects
• Forget/can’t keep track of
medications/complexity
• Don’t think it works/don’t need it
Most nonadherence is not caused by side effects or drug costs. Rather the
problem is behavioral, simple procrastination and forgetfulness.
Complex human behavior
Source: Sokol M et al. Impact of Medication Adherence on Hospitalization
Risk and Healthcare Cost. Medical Care.
Volume 43, Number 6, June 2005
Source: Nasseh K, et al. Cost of medication nonadherence associated with
diabetes, hypertension, and dyslipidemia.
Am J Pharm. 2012;4.2:e41–e47.
• Socioeconomic factors (age, race,
gender, ecomonic status)
• Patient-related factors (knowledge,
attitudes, beliefs, and skills)
• Condition/treatment related factors
(disease severity, co-morbidity, regimen
complexity, side effects)
• Provider factors (skill, training, resources)
• Setting/policies (access to care, Rx
coverage)
6. Effective interventions - Automated call helped increase the number of
prescriptions that were filled, indicating improved adherence.
Source: Derose SF, Green K, Marrett E. Automated outreach to increase
primary adherence to cholesterol-lowering medications
[published online November 26, 2012]. Arch Intern Med. 2013.
Automated call system in patients
with primary non-adherence to
statin medication
7. Blending data from different sources was key to derive predictors &
classifying patients based on adherence
Source: www.cms.gov
www.nlm.nih.gov/research/umls/rxnorm/docs/rxnormfiles.html
www.census.gov
Medicare - Primary Data Source
Drug Information
Disease Information
rxNorm Data
Economic Information
Social Information
Household Information
Census Data
Patient Information
Medicare Part D Information
8. When we looked at this data, we kept asking this question often “What
diseases that this pill treat?”
• Five websites with 3 different datasets to
find this information
• Often information coding conventions are
not common or consistent
• We used Alteryx to help solve this problem
Simple question, but complex data
We were using this so often that we built
an Analytic App!
Published this on http://gallery.alteryx.com as well
9. Prediction Methodology - What factors influence nonadherence?
• Decision tree model to predict ‘Yes’/’No’
• Regression to fit adherence days. Can we
predict for how many days does this
patient take his medication
• Models with 45 predictors
Modeling medication nonadherence
Socioeconomic Factors
Changing the Context
To make individuals’ behavior
Long-lasting
Protective Interventions
Clinical
Interventions
Counseling
& Education
Largest
Impact
Smallest
Impact
Poverty, education, housing, inequality
Brief intervention for alcohol,
cessation treatment
0g trans fat, salt, smoke-free
laws, tobacco tax
Rx for high blood pressure, high
cholesterol
Eat healthy, be physically active
Examples for
cardiovascular health
Our Hypothesis
10. Inferences from our predictive models are largely inline with our hypothesis
• Public Health factors – State, County, Area
• Personal factors – Age, Income, Race,
Sex, Education, Insurance
• Medication factors – Number of pills,
Patient payments, Cost of drugs, Other
chronic diseases
Factors that influence nonadherence
for cardio vascular diseases
Model Summary
Variables actually used in tree construction:
[1] Area.name Avg_Annual.Average.Pay BENE_BIRTH_DT
[4] BENE_RACE_CD BENE_SEX_IDENT_CD BENRES_CAR
[7] BENRES_OP MEDREIMB_CAR MEDREIMB_OP
[10] Num_Pills PPPYMT_CAR PTNT_Pays
[13] RX_Cost SomeColPct SP_ALZHDMTA
[16] State
Root node error: 1821/10308 = 0.17666
n= 10308
We can add more personal and
behavioral factors to improve the
accuracy of our model further
11. Each intervention must be tailored to individual patients. Incentives of all
stakeholders needs to be aligned to improve medication adherence.
Source: Derose SF, Green K, Marrett E. Automated outreach to increase
primary adherence to cholesterol-lowering medications
[published online November 26, 2012]. Arch Intern Med. 2013.
Improve medication adherence
• Behavioral – audible reminders, smart pill
boxes and auto-refills counteract
procrastination and forgetfulness.
• Financial – Lower cost pharmacies,
generics, and payment assistance make
medication more affordable.
• Clinical – Pharmacist consultations and
therapeutic resources help address
medical concerns.
Improve Medicare systems
• Medication Adherence rates are far from
optimal but CAN be improved through
collaboration and alignment of incentives
for plans, physicians and pharmacists
• Ongoing, consistent, measurement of
medication adherence rates is important to
gauge improvement and to identify “best
practices” across plans, physicians and
pharmacists
• What gets measured…. Gets improved!
Source: Nau D The importance of measuring adherence Pharmacy Quality
Alliance [published online November 7, 2011].
12. Notes on models & data
• Lift_ISCHM_NDC_workflow p1 – this
workflow does the lookup of all drugs to
diseases lookup and builds relations
database for stage 2
• Lift_ISCHM_NDC_workflow p2 – this
worlfow does the panel data construction
with merging census datat, medicare data
and prescriptions data
• Lift_NDC_Disease_App – This is our
Analytical App for ‘What diseases does this
pill treat’
• Lift_Predictive_Model – Data
preprocessing and predictive models
(decision tree/regression) for medication
adherence
Workflows in our submission