Public Health Intelligence Platform for Social Health Records (SHR)* - PDF document

11/3/2017 Public Health Intelligence Platform for Social Health Records (SHR)* City University of New York Soon Ae Chun In collaboration with Xiang Ji (NJIT PhD graduate, Bloomberg Inc.) James Geller (NJIT) Introduction & Overview • Online health-related social networks generate a big amount of health data, e.g. – Twitter, PatientsLikeMe, Medhelp, etc. • SHR (Social Health Records) – Social Media-based Health-related Data – How can we leverage these for gaining health Intelligence & better healthcare? • We present an integration and analytics framework of social health records (SHR) to address three problems: – Health Data Integration Problem – Population Analytics Problem – Predictive Analytics Problem 2 1

11/3/2017 Statistics: Social Media Use in Healthcare 2/2015 Becker’s ASC Review >40% 41% Youths 19% 90% Youths consumers say that of smartphone owners of people said social 18 to 24 year olds are information found via have at least one media would affect more than twice as social media affects the from 18 to 24 years of health app on their their choice of a likely as 45 to 54 year way they deal with age said they would phone . Exercise, diet, specific physician, olds to use social their health (chronic trust medical and weight apps are hospital or medical media for health- information shared by disease, diet & the most popular facility. related discussions. exercise) others on their social types. media networks. 31% 54% 31% 26% 31% of adults are likely to share information about their of healthcare healthcare patients are very health on social media sites of all hospitals in the comfortable with their professionals use organizations have with other patients , United States social media for specific social providers seeking participate in social 47 percent with physicians, advice from online professional media guidelines in 43 percent with hospitals, media. networking. writing. communities to better 38 percent with a health treat their conditions. insurance company and 32 percent with a drug company. Most popular online resources for Health Information • The most accessed online resources for health related information are: • 56% searched WebMD, • 31% on Wikipedia, • 29% on health magazine websites, • 17% used Facebook, • 15% used YouTube, • 13% used a blog or multiple blogs, • 12% used patient communities • 6% used Twitter and • 27% used none of the above (source: Mashable, 2012, referralmd.com) 2

11/3/2017 Social Media Health Data • Twitter – 230 million tweets posted per day in 2011 -> 317 million (2016) (statistica.com) • PatientsLikeMe – 17,835 patients – share profiles with public; 307,033 members – share only with members – 500+ health conditions (as of 2015) • Medhelp – 20 million monthly visitors – Track pain, weight, chronic diseases • CureTogether – anonymously track and compare health data • DailyStrength – emotional support groups • Inspire – different communities to offer support and educate • FacetoFaceHealth – algorithm to match people with similar diagnoses • Meddik – empower patients to search health info and learn from experiences from others • Doximity – medical doctors and students network to extend and build prof relationships 5 Challenges Social Media for Health Care • People do seek for Health Information from the social media to make personal health care decisions • However, the challenge is that they need to – visit many different information sources. – synthesize, – reason, – compare – to make a reasonable decision on their health. • In other words, social health data – Vast amount of health data, Distributed (scattered) heterogeneous data, streaming data – DRIP syndrome: Data rich and Info Poor  core problems DS addresses – Data Science methodologies can provide necessary analytics to generate more “useful” knowledge for health care. – SOCIAL HEALTH Analytics Framework 3

11/3/2017 Social Health Records (SHR) Patient’s Health Reports on Social Media SHR (Social Health Records) EHR (Electronic Health Records) • Generated by patients • Entered by clinical professionals – Health status reports – Clinical data • Headaches, experienced symptoms • medications, allergies, problems, procedures, chart notes, clinical alert notes, lab results, and • Diagnosis reports images – Healthcare practice data – Patient history • Actual medications, treatments – Orders • Side effects from treatments – Medications/Allergies – Health-related behaviors/habits – Demographic data • Drinking, smoking, etc. – Lab data • Exercises, fitbits • Nutritional EHR SHR • Structured/unstructured • Mostly unstructured data • Uses Medical expert language • Informal everyday language – Myocardial infarction – Hearattack • Comparatively precise • Ambiguous, vague – Diabetes (type 1 or 2), hepatitis (A or – ICD9 code for a disease C?) • Not easily accessible due to • Publicly available or more HIPAA privacy law readily available • Localized/silo • Can be access around the – Hospital, provider/group world – Application specific (lack of – Web browser accessible interoperability) • Emotional • Factual statement • Reviews, empatic statements, Annotations 4

11/3/2017 Social Health Records (SHR) • Seems to exhibit potentials to investigate – Major concerns or topics in health – Health risks, attitudes towards health – Identify trends – Personal feelings/views on treatments or conditions – What is desired outcomes – Track adverse drug events • Can it serve as a knowledge source for clinical, policy related decision making as well ? • the social health data as complimentary data source for research and clinical decisions, • knowledge source for Health Intelligence to understand health behaviors or practices for population? SHR Integration and Analytics Framework • A social health Integration and analytics framework uses Social Health Records as the first class data to gain useful insights – Health Data Integration • Scattered data sources – Predictive Analytics Problem • From similar individuals to predict a future disease of a person? • Comorbidity trajectory model – Public Health Analytics • Public health issues e.g. epidemic outbreak detection, public sentiments • Drug abuse detection 5

11/3/2017 Query: What are other patients’ symptoms and drug reviews for treating the top-10 conditions? • Users have to integrate health information from all these sources into one coherent mental model. Research Issues & Approaches • Research Issues • How can we model and integrate the extracted data to satisfy the information needs? • How can we best present social health analytics and inference results to users? • Approach- • Health data integration for Analytics – Designed semantic model & RDF storage to perform integration of data that can satisfy the information needs. – Developed context-aware social analytics and inferences. – Social InfoButton (knowledge from social data about population health behaviors, practices..) 6

11/3/2017 RDF-Based Storage • Triple: <subject, predicate, object>. • A patient “John” has a profile page as well as a health condition “ Psoriasis ”. http://www.patientlikeme.com/patient#1050 ( URI1 ) hasCondition hasProfile hasName http://www.patientlikeme.com/condition http://www.patientlikeme.com/ #154 ( URI3 ) Members/232328/about_me ( URI2 ) “John” hasConditionName “Psoriasis” 7

11/3/2017 Information Needs User Information Need Examples What are the symptoms for diabetes? What are the treatment Pre-diagnosis options for high blood sugar? What are the new research findings about breast cancer? Are Patient Post-diagnosis my symptoms indeed caused by the diagnosed condition? What patients or expert communities can provide support for a Community Support specific condition? What are the drug options used by other patients to treat a Drug Choice specific condition? How many pills a day and how many times a day should the Clinician Drug Dosage patients take a specific drug? What are the possible adverse effects of a specific drug, and Side Effect how severe are they? Where are the current disease outbreaks? What is the trend of a Organization Disease Surveillance specific condition? SHR Analytics What are the online profile, # of posts, and # of replies for a specific condition? 8

11/3/2017 Open Health Data Sources Data Source Patients Clinicians Government Support Pre- Healthcare Post- Drug Adverse Disease Drug Dosage Community diagnosis Providers diagnosis Choice Effect Surveillance P P P P PatientsLikeMe P Twitter P P P MedHelp P P P WebMD P P Mayo Clinic P P CDC P PubMed State Data Source Patient Condition Treatment Symptom Review Community Post Prevalence PatientsLikeMe 17,407 1,228 5,608 2,176 n/a n/a n/a n/a MedHelp n/a n/a n/a n/a n/a 365 69,243 n/a WebMD n/a 647 180 n/a 86,715 n/a n/a n/a Mayo Clinic n/a 1,116 2,496 5,426 n/a n/a n/a n/a CDC n/a n/a n/a n/a n/a n/a n/a 52 Social InfoButtons • Use case: A doctor is devising the best practice for a PTSD (Post Traumatic Stress Disorder) patient. Statistical Analytic 9

11/3/2017 Social InfoButtons (Cont.) Geospatial Analytic Twitter Tag Cloud Individual Tweets Social InfoButtons (Cont.) 10