ADS Capstone Chronicles Revised

‭1‬

‭Adverse Drug Reaction Surveillance:‬ ‭A Precision Public Health Model‬

‭Halee Staggs‬ ‭Applied Data Science‬ ‭Master’s Program‬ ‭Shiley Marcos School of‬ ‭Engineering/University of‬ ‭San Diego‬ ‭hstaggs@sandiego.edu‬

‭Vicky van der Wagt‬ ‭Applied Data Science‬ ‭Master’s Program‬

‭Shiley Marcos School of‬ ‭Engineering/University of‬ ‭San Diego‬ ‭vvanderwagt@sandiego.edu‬

‭ABSTRACT‬ ‭Almost‬ ‭half‬ ‭of‬ ‭Americans‬ ‭take‬ ‭prescription‬ ‭pharmaceutical‬ ‭drugs‬ ‭every‬ ‭month.‬ ‭Side‬ ‭effect‬ ‭profiles‬ ‭and‬ ‭warnings‬ ‭issued‬ ‭by‬‭drug‬ ‭manufacturers‬ ‭are‬ ‭limited‬ ‭by‬ ‭clinical‬ ‭trial‬ ‭data,‬ ‭and‬ ‭therefore‬ ‭lack‬ ‭variance‬ ‭for‬ ‭individual‬ ‭differences.‬ ‭To‬ ‭track‬ ‭the‬ ‭epidemiological‬ ‭impacts‬ ‭of‬ ‭drugs,‬ ‭the‬‭Food‬ ‭and‬ ‭Drug‬‭Administration‬‭(FDA)‬‭created‬‭the‬ ‭Adverse‬ ‭Event‬ ‭Reporting‬ ‭System‬ ‭(FAERS)‬ ‭which‬‭receives‬‭millions‬‭of‬‭reports‬‭each‬‭year‬ ‭of‬ ‭adverse‬ ‭reactions‬ ‭to‬ ‭pharmaceutical‬ ‭drugs,‬ ‭underscoring‬ ‭the‬ ‭size‬ ‭of‬ ‭the‬ ‭public‬ ‭health‬ ‭burden.‬ ‭Many‬ ‭systems‬ ‭have‬ ‭been‬ ‭developed‬‭to‬‭model‬‭side‬‭effects‬‭and‬‭adverse‬ ‭drug‬ ‭reactions‬ ‭based‬ ‭on‬ ‭FAERS‬ ‭data,‬ ‭but‬ ‭they‬ ‭lack‬ ‭interpretability‬ ‭of‬ ‭individual‬ ‭differences‬ ‭and‬ ‭economic‬ ‭impacts.‬ ‭In‬ ‭this‬ ‭project,‬‭an‬‭extract-transform-load‬‭pipeline‬‭is‬ ‭implemented‬ ‭that‬ ‭synthesizes‬ ‭multiple‬ ‭sources‬ ‭of‬‭public‬‭data‬‭about‬‭pharmaceutical‬ ‭drugs‬ ‭into‬ ‭a‬ ‭publicly‬ ‭accessible‬ ‭SQL‬ ‭database‬ ‭(FAERS,‬ ‭Medicaid‬ ‭drug‬ ‭prices,‬ ‭RxNorm).‬‭Data‬‭is‬‭queried‬‭from‬‭the‬‭database‬ ‭to‬ ‭train,‬ ‭tune,‬ ‭and‬ ‭test‬ ‭machine‬ ‭learning‬ ‭models‬‭to‬‭classify‬‭outcomes‬‭of‬‭adverse‬‭drug‬ ‭reactions‬ ‭(ADRs).‬ ‭The‬ ‭optimal‬ ‭pre-trained‬ ‭model‬ ‭(random‬ ‭forest)‬ ‭is‬ ‭stored‬ ‭in‬ ‭GitHub‬ ‭and‬ ‭deployed‬ ‭in‬ ‭a‬ ‭user-friendly‬ ‭Streamlit‬ ‭application.‬ ‭The‬ ‭data‬ ‭is‬ ‭also‬ ‭loaded‬ ‭into‬ ‭PowerBI‬ ‭as‬ ‭an‬ ‭interactive‬ ‭dashboard.‬ ‭The‬ ‭model‬ ‭reveals‬ ‭novel‬ ‭insights‬ ‭that‬ ‭are‬ ‭clinically‬‭relevant‬‭and‬‭add‬‭a‬‭precision‬‭public‬

‭health‬ ‭approach‬ ‭to‬ ‭adverse‬ ‭drug‬ ‭event‬ ‭outcomes.‬ ‭Individual‬ ‭differences‬ ‭like‬ ‭age,‬ ‭weight,‬ ‭and‬ ‭sex,‬ ‭and‬ ‭economic‬ ‭factors‬ ‭like‬ ‭drug‬ ‭prices,‬ ‭are‬ ‭the‬ ‭primary,‬ ‭significant‬ ‭features‬ ‭for‬ ‭classifying‬ ‭adverse‬ ‭outcomes,‬ ‭with‬ ‭pharmaceutical‬ ‭drugs‬ ‭adding‬ ‭less‬ ‭contribution‬‭to‬‭the‬‭model.‬‭More‬‭specifically,‬ ‭younger,‬ ‭overweight‬ ‭females‬ ‭are‬ ‭at‬ ‭highest‬ ‭risk‬ ‭for‬ ‭death,‬ ‭compared‬ ‭to‬ ‭older,‬ ‭lower‬ ‭weight‬ ‭males,‬ ‭implying‬ ‭that‬ ‭differences‬ ‭in‬ ‭pharmacokinetics‬ ‭are‬ ‭related‬ ‭to‬ ‭outcome‬ ‭seriousness.‬ ‭These‬ ‭results‬ ‭show‬ ‭that‬ ‭individual‬ ‭difference‬ ‭input‬ ‭features‬ ‭can‬ ‭inform‬‭patient-focused‬‭decisions,‬‭rather‬‭than‬ ‭modeling‬ ‭side‬ ‭effects‬ ‭and‬ ‭drug‬ ‭compounds‬ ‭only‬ ‭which‬‭lack‬‭context.‬‭It‬‭is‬‭recommended‬ ‭that‬ ‭the‬ ‭FAERS‬ ‭should‬ ‭require‬ ‭more‬ ‭biopsychosocial‬ ‭variables‬ ‭for‬ ‭reporting‬ ‭so‬ ‭that‬ ‭other‬ ‭factors‬ ‭can‬ ‭be‬ ‭assessed‬ ‭in‬ ‭ADR‬ ‭outcomes‬ ‭like‬ ‭socioeconomic‬ ‭status,‬ ‭underlying‬ ‭health‬ ‭conditions,‬ ‭stress,‬ ‭and‬ ‭substance‬ ‭use.‬ ‭Other‬ ‭recommendations‬ ‭for‬ ‭improvement‬ ‭in‬ ‭the‬ ‭FAERS‬ ‭system‬ ‭and‬ ‭tracking‬ ‭true‬ ‭population‬ ‭rates‬ ‭of‬‭ADRs‬ ‭are‬ ‭discussed.‬ ‭KEYWORDS‬ ‭adverse‬ ‭drug‬ ‭reactions,‬ ‭pharmaceutical‬ ‭drugs,‬ ‭machine‬ ‭learning,‬ ‭data‬ ‭mining,‬ ‭data‬ ‭engineering,‬ ‭precision‬ ‭public‬ ‭health,‬ ‭side‬ ‭effects, drug prices‬

151

Made with FlippingBook - Online Brochure Maker