Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Electronic health records and machine learning
1. Electronic Health Records
and Machine Learning
Eman Abdelrazik
Bioinformatics Research Assistant, Center of Informatics Science, Nile University
H3ABioNet Teaching Assistant
4. Real World Data (RWD)
● RWD are information reported and collected from real-world
medical settings that may show the effectiveness and safety
of a medicine for an approved indication in patients.
● These data may be collected in one country or collected from
all over the world (heterogeneous patient population in real-
world settings).
7. HOW ARE RWD USED?
● RWD analyses generate insights about the effectiveness and safety
profile of a medicine.
● RWD studies can help explore additional research questions,
complement clinical trial findings, and fill gaps related to how a
medicine is used in real-world medical settings.
● RWD may also be used to inform future investigational plans to
increase efficiency and reduce cost.
8. Real world evidence (RWE)
● Obtained from real world data (RWD), which are observational data
obtained outside the context of randomized controlled trials (RCTs) and
generated during routine clinical practice.
○ In order to assess patient outcomes and to ensure that patients get
treatment that is right for them, real world data needs to be utilized.
● RWE is generated by analyzing data which is stored in electronic health
records (EHR), medical claims or billing activities databases, registries,
patient-generated data, mobile devices, etc.
○ It may be derived from retrospective or prospective observational studies and
observational registries
11. Electronic Health Record (EHR)
● EHRs are systematic collections of longitudinal health information of patient
and population electronically-stored health information in a digital format.
● These records can be shared across different health care settings.
● Records are shared through network-connected, enterprise-wide information
systems or other information networks and exchanges.
13. EHR
There are two types of data contained in
patient EHRs:
1) Structured Data
● fields that contain data using existing
lexicons, such as demographics,
diagnosis, laboratory tests,
medications, and procedures.
2) Unstructured Data
● free text documents such as clinical
notes from physicians and nurses.
EHR Components
14. EHR is the GPS of Health Care!
EHR & Pathology Reports!
16. Diagnosis : why it is hard to?
● Phenotype is a spectrum
○ Physical characteristics (signs; tumor markers, grade,
tumor mass)
○ Diseases (stroke, lung cancer, Rheumatoid Arthritis “RA” )
● A correct diagnosis refers to the presence, absence and
severity grade of pathology and determines decision making in
prognosis, risk assessment and treatment.
● Deciding cut points for who has or does not have disease.
17. Misdiagnosis!!
● Misdiagnosis in clinic
○ Major implications for patient
● Misclassification in research
○ Reduces ability to identify relationships at population level
■ Effectiveness of new therapies
● Side effects
■ Risk factors
Algorithms are only as good as training set and reviewers!
18. Artificial Intelligence (AI): Machine Learning
● Artificial Intelligence
○ Intelligence demonstrated by machines.
■ Contrast to human intelligence.
● Machine Learning (ML)
○ Require data to train
■ Develops mathematical models to predict the data of
interest
■ ML abstracts rules from the data, similar to what a
physician might experience during his residency
19. Machine Learning Models
● Choice of a distinct model for a given problem is determined by:
1) Features of the data
● Fewer unique data points indicate that classical techniques:
○ linear regression, or decision-tree methods
● which segment data sets into regions according to fixed rules
2) Data types
● a collection of images (histopathology data, radiography)
● a time-series signal (longitudinal studies)
● general descriptive data (demographics & narrative data)
27. Machine learning for medical ultrasound
Suffers from inter-
and intra-observer
variability + image
quality
❏ Region of Interest (ROI);
liver fibrosis staging
Credit: Brattain, L.J., Telfer, B.A., Dhyani, M. et al. Abdom Radiol (2018) 43: 786.
28. Machine learning for medical ultrasound
Credit: Brattain, L.J., Telfer, B.A., Dhyani, M. et al. Abdom Radiol (2018) 43: 786.
35. Future challenges
● Selecting training data set
● Setting gold standard
● Adapting new diagnosis and new treatments
● Responsible party for the final decision for diagnosis and
treatment
37. References
1. Kourou, Konstantina, et al. “Machine Learning Applications in Cancer
Prognosis and Prediction.” Computational and Structural Biotechnology
Journal, Elsevier. 2014; 13: 8-17.
2. L.J., Telfer, B.A., Dhyani, M. et al. Abdom Radiol. 2018; 43: 786.
3. Nichols JA, Herbert Chan HW, Baker MAB. Machine learning: applications of
artificial intelligence to imaging and diagnosis. Biophys Rev. Biophysical
Reviews. 2019;11:111–8.
4. Wang F, Preininger A. AI in Health: State of the Art, Challenges, and Future
Directions. Yearb Med Inform. 2019;28:16–26.
The journey from data to evidence. Real-world data (RWD) are data that are routinely collected in the form of electronic health records (EHRs), patient disease registries, wearables, genomic datasets, medical claims registries, and others. These data can be aggregated, linked, and processed to produce key conclusions in the form of real-world evidence (RWE). The proposed checklist can be used to assess if the quality of the RWD is regulatorygrade.
https://www.semanticscholar.org/paper/Harnessing-the-Power-of-Real%E2%80%90World-Evidence-(RWE)%3A-Miksad-Abernethy/db481a65cbb491fcd5d4b838d13fe9338bebd711
RWE can be valuable across the lifecycle of drug development. In a drug’s predevelopment stages, RWE helps inform clinical development strategies and study planning. During clinical development stages, RWE may inform trial design and feasibility (e.g., patient enrollment, inclusion and exclusion criteria), and serve as a synthetic control arm. Following drug approval, RWE may help fulfill postmarketing commitments and potentially support label expansions. Finally, in clinical practice, RWE may assist personalization of treatment by offering clinicians and patients a deeper understanding of the nuances of drug performance in the real world.
https://www.semanticscholar.org/paper/Harnessing-the-Power-of-Real%E2%80%90World-Evidence-(RWE)%3A-Miksad-Abernethy/db481a65cbb491fcd5d4b838d13fe9338bebd711
digital form of the paper charts that healthcare facilities previously used to keep track of treatments, medications, changes in condition,
Like an EMR, an electronic health record (EHR) provides a digital record of health information. However, the EHR includes more data than the EMR. It contains input from all the practitioners that are involved in the client’s care. Thus, the EHR offers a more comprehensive view of the client’s health and treatment history. This information is entered into a common database that can be shared among authorized users across multiple healthcare organizations.
https://www.psytechsolutions.net/emr-vs-ehr-vs-phr
What Are the Benefits of EHR Technology?
The use of EHR systems is now standard operating procedure in healthcare organizations of all types and sizes. Aided by the installation of EHR software, these systems offer many key benefits for practitioners, staff members and clients:
• Providing access to comprehensive, current, accurate client information at the point of care
• Enhancing client safety by improving diagnostic accuracy and reducing errors
• Allowing for faster, more accurate and convenient prescribing of medication
• Enabling the secure sharing of client medical information among multiple providers
• Facilitating communication between the practitioner and client
• Increasing administrative efficiency in areas such as scheduling, billing and collections, resulting in lower business-related costs for the organization
Demographics: The common variables that are gathered in demographic research include age, sex, income level, race, employment, location, homeownership, and level of education.
http://blog.75health.com/what-components-constitute-an-electronic-health-record/
A correct diagnosis refers to the presence, absence and severity grade of pathology and determines decision making in prognosis, risk assessment and treatment
A correct diagnosis refers to the presence, absence and severity grade of pathology and determines decision making in prognosis, risk assessment and treatment
Artificial Intelligence (AI) refers to a set of technologies that allow machines and computers to simulate human intelligence. AI technologies have been developed to analyze a diverse array of health data, including patient data from multi-omic approaches, as well as clinical, behavioral, environmental, and drug data, and data encompassed in the biomedical literature.
AI technologies can simulate human intelligence at a variety of levels. Both machine learning (ML) and deep learning (DL) are subsets of AI.
ML allows systems to learn from data at the most basic level. DL is a type of ML which uses more complex structures to build models.
ML abstracts rules from the data, similar to what a physician might experience during his residency
ML algorithms, which we typically refer as a model
A primary consideration is the number of unique data points. Large data sets, of the order of 106 unique data points, mean more exotic deep learning algorithms may be suitable.
Another choice is between supervised learning and unsupervised learning. Supervised learning, as the name suggests, involves teaching the model with a collection of input data that has the correct output already associated with it.
Supervised learning is more broadly used in image classification tasks.
Unsupervised learning is where a model trains itself on data, in a sense. Typically, this may involve tasks like cluster detection or various forms of pattern recognition
http://dspace.bracu.ac.bd/xmlui/bitstream/handle/10361/11431/14101060%2C14101143%2C14101146_CSE.pdf?sequence=1&isAllowed=y
Overview of the two main types of EMR data, structured and unstructured, and how these data can be integrated for research studies. In this instance, the figure illustrates the development of a phenotype algorithm for rheumatoid arthritis. *Including ICD-9 (international classification of diseases, 9th revision) codes and CPT (current procedural terminology) codes
https://www.bmj.com/content/350/bmj.h1885
Overview of methods used to develop EMR phenotype algorithms
https://www.bmj.com/content/350/bmj.h1885
Ultra sound: cross sectional images with low reselotion, Challenges include high inter- and intra-operator variability and limited image quality control.
suffers from inter- and intra-observer variability
aggregated machine intelligence will have the ability to observe data, orient the end user, assess new information, and assist with decision making.