Categories
Machine Learning

Machine Learning in population health: Creating conditions that ensure good health.

Machine Learning (ML) in healthcare has an affinity for patient-centred care and individual-level predictions. Population health deals with health outcomes in a group of individuals and the outcome distribution in the group. Both individual health and population health are not divergent, but at the same time, both are not the same and may require different approaches. ML in public health applications receives far less attention.

The skills available to public health organizations to transition towards an integrated data analytics is limited. Hence the latest advances in ML and artificial intelligence (AI) have made very little impact on public health analytics and decision making. The biggest barrier is the lack of expertise in conceiving and implementing data warehouse systems for public health that can integrate health information systems currently in use. 

The data in public health organizations are generally scattered in disparate information systems within the region or even within the same organization. Efficient and effective health data warehousing requires a common data model for integrated data analytics. The OHDSI – OMOP Common Data Model allows for the systematic analysis of disparate observational databases and EMRs. However, the emphasis is on patient-level prediction. Research on how patient-centred data models to observation-centred population health data models are the need of the hour.

We are making a difficult yet important transition towards integrated health by providing new ways of delivering services in local communities by local health teams. The emphasis is clearly on digital health. We need efficient and effective digital tools and techniques. Motivated by the Ontario Health Teams’ digital strategy, I have been working on tools to support this transition.

Hephestus is a software tool for ETL (Extract-Transform-Load) for open-source EMR systems such as OSCAR EMR and national datasets such as Discharge Abstract Database (DAD). It is organized into modules to allow code reuse. Hephestus uses SqlAlchemy for database connection and auto-mapping tables to classes and bonobo for managing ETL. Hephaestus aims to support common machine learning workflows such as model building with Apache spark and model deployment using serverless architecture. I am also working on FHIR based standards for ML model deployments.

Hephaestus is a work in progress and any help will be highly appreciated. Hephaestus is an open-source project on GitHub. If you are looking for an open-source project to contribute to Hacktoberfest, consider Hephaestus! 

Categories
mHealth

HL10: A proposal for an mHealth framework

HL10 Framework
Image credit: beapen

Behaviour Intervention Technologies (BITs) are a subset of eHealth and mHealth interventions that support users in changing behaviour and cognitions related to health. Several psychological models guide the implementation of BITs. However, these psychological models such as social cognitive theory and theory of planned behaviour have a clinical focus and are incapable of guiding the design and coding.

Mohr et.al proposed the BIT model [ [ref] Mohr DC, Schueller SM, Montague E, Burns MN, Rashidi P. The Behavioral Intervention Technology Model: An Integrated Conceptual and Technological Framework for eHealth and mHealth Interventions. J Med Internet Res 2014;16(6):e146 [/ref] ] to address these limitations by systematizing why, how (conceptual and technical), what and when of BIT. ‘Why’ translates to clinical aims such as sun protection and weight reduction. Examples of conceptual ‘how’ are education, goal setting, monitoring and feedback. Technical ‘how’ indicates the medium of delivery and the complexity of delivery. ‘What’ corresponds to alerts, logs, messaging and data collection. ‘When’ indicates the workflow that can be user defined or based on time/event rules. The model proposes a sense-plan-act paradigm based on robotics with sense-act coupling in reactive models.

HL10 (Hamilton) is an attempt to take the BIT model and the sense-plan-act paradigm to the next level of a software framework. HL10 is a proposal for an mHealth specific mobile application frameworks that can be easily extended to create any type of app. The framework should take care of overarching concerns such as privacy and security of patient data, communication with electronic health record (EHR) systems and population health.

Ultimately HL10 framework would be available as an mHealth boilerplate or a Yeoman generator that can be easily modified to create any mHealth BIT. HL10 would try to segregate the sense-plan-act layers and would propose fundamental rules of communication between these layers though standardizing is not its primary intent. Privacy would be built into the framework by design. External communication with EMR and other HIS would be negotiated through fire! (FHIR)

HL10 is still a concept and would greatly benefit from ideas and contributions from domain experts. Though I am ‘opinionated’ to a certain extent, this preliminary post is intentionally left ‘non-opinionated’ to encourage the flow of ideas. Do give me a shout if you find this interesting. I have created a group on GitHub for this: https://github.com/E-Health

Some of the ideas are influenced by AppsForHealth at Mohawk, especially the keynote lecture by Dr. Ann Cavoukian on privacy by design, and the introductory lecture on FHIR followed by the connectathon demos.

Please site this page as below if you expand on this concept.

Eapen BR. HL10 (Hamilton) – An mHealth behaviour intervention technology framework. NuChange Informatics Blog (2015). Available from: http://nuchange.ca/2015/07/hl10-from-model-to-framework.html

CAS-002  
350-018  
9A0-385  
CISSP  
000-104  
300-208  
M70-101  
200-310  
642-999  
CISM  
1Z0-144  
9A0-385  
70-177  
70-486  
OG0-091  
300-206  
70-243  
300-206  
350-001  
210-260  
300-320  
200-355  
MB2-704  
300-135  
LX0-104  
74-678  
220-901  
70-246  
70-488  
210-260  
1z0-434  
300-320  
1z0-434  
2V0-620  
1Z0-061  
2V0-621D  
70-480  
N10-006  
210-260  
300-101  
700-501  
PR000041  
N10-006  
1Z0-061  
JN0-360  
100-101  
200-101  
500-260  
CAS-002  
EX300  
000-106  
70-417  
101  
200-125  ,
74-678  
2V0-621D  
1Y0-201  
9L0-012  

JK0-022  ”
MB2-707  ”
70-177  ”
70-462  ”
MB5-705  ”
CRISC  ”
70-417  
350-018  ”
350-060  
1z0-434  ”
70-410  
SSCP  
70-411  ”
70-483  ”
70-480  ”
NS0-157  ”
1Y0-201  ”
000-106  ”
JK0-022  ”
70-178  
HP0-S42  ”
CISSP  
70-534  ”
OG0-093  ”
100-105  ,”
JK0-022  ”
70-417  ”
70-532  ”
CRISC  ”
c2010-657  ”
200-120  ”
SY0-401  ”
3002  ”
100-105  ,”
OG0-091  ”
OG0-093  ”
000-104  ”
350-050  ”
400-201  ”
OG0-093  ”
9L0-066  
ADM-201  ”
EX300  ”
LX0-103  ”
000-104  ”
000-105  ”
70-246  ”
070-461  ”
MB6-703  ”
70-347  ”
CISM  ”
1Z0-051  
ADM-201  ”
70-462  ”
1V0-601  ”
000-017  
220-901  ”
9A0-385  ”
ITILFND  ”