BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250327T203344Z LOCATION:Frontenac Foyer DTSTART;TZID=America/New_York:20250401T164500 DTEND;TZID=America/New_York:20250401T181500 UID:HFESHCS_2025 International Symposium on Human Factors and Ergonomics i n Health Care_sess148_POST261@linklings.com SUMMARY:DH3 - AI-Driven Solution for Reducing Polypharmacy Risks Following Hospital Discharge: A Predictive Model for Patient Medication Review DESCRIPTION:Poster Presentation\n\nGabriel Gazetta, Kenneth Joseph, Steven Feuerstein, Jennifer Stoll, Robert Wahler, Ann Bisantz, Sharon Hewner, Hu ei-Yen Winnie Chen, Ranjit Singh, and David Jacobs (University at Buffalo) \n\nPolypharmacy has become increasingly prevalent, especially among aging populations with multiple chronic conditions. While medications are cruci al for managing complex diseases, the use of multiple medications can incr ease the risk of adverse drug effects, and drug-drug interactions, comprom ising patient safety. Additionally, the use of medications can present sid e effects which in turn are treated by other medications, situation known as prescribing cascade. Patients susceptible to polypharmacy are likely to experience consequences of multi-drug administration, exacerbating health risks, which can lead to hospital readmissions, prolonged hospital stays, or even mortality. These outcomes are especially prevalent during the tra nsition of care from hospital to home environments, when medication schedu les are often complex and less closely monitored. Considering the risks, e ffective intervention requires timely identification of patients at high r isk of medication-related complications, however, it is common that clinic ians face overwhelming workloads and cognitive overload, hindering their a bility to perform thorough medication reviews. Moreover, deprescribing med ications remains uncommon because medications are often prescribed by mult iple specialists, each focusing on a specific aspect of the patient’s care . This can create reluctance among physicians to modify or discontinue pre scriptions initiated by their peers, out of concern for overstepping profe ssional boundaries or lacking full insight into the rationale behind anoth er specialist’s treatment decisions.\nWith that, clinical decision support tools that streamline the identification of at-risk patients could signif icantly enhance both workflow efficiency and patient safety. This study p resents the development of a predictive model aimed at flagging patients w ho would benefit from a comprehensive medication review, specifically targ eting individuals in the post-hospital discharge period, aimed to bring at tention to clinicians, and consequently reduce the risks associated with p olypharmacy and medication related. In the development, the algorithm will also be useful to generate insights about the variables and relationships within the dataset, enhancing the clinical understanding of polypharmacy risks.\nThe primary goal of this work is to build an AI model that identif ies patients during post-discharge phase that could benefit from a medicat ion review due to medication-related risks while reducing clinical cogniti ve workload and enhancing decision-making within a fast-paced clinical env ironment. To ensure its usefulness and to ease adoption, a user-centered d esign approach will support the development of an explainable AI (XAI) mod el that provides clinicians access to more detailed information on the rea soning behind the model predictions. This deeper level of transparency is expected to support clinical decision-making and facilitate the investigat ion of the drivers for polypharmacy risk. Ultimately, it is expected that such systems would increase the frequency and quality of medication review s, targeted to patients who are most vulnerable to adverse drug effects.\n The AI model is built using a comprehensive longitudinal dataset with info rmation from over 400,000 patients, tracked across multiple years. The dat aset includes a wide range of variables, such as demographics (age, sex, r ace), social determinants of health (income level, education, housing stab ility), hospital admissions, primary and secondary diagnoses, and detailed medication histories. Advanced machine learning techniques are employed t o identify patients at elevated risk of medication-related complications. The explainable AI model helps go beyond the prediction of high risk from polypharmacy complications, by clarifying why the predictions were made, e ither by identifying patterns of medication use or associated clinical fac tors such as recent diagnoses and hospitalizations, for example. Furthermo re, early findings from the model’s predictions and XAI explanations will be shared with clinicians, allowing for the refinement of both the model a nd its explanations based on real-world feedback and clinical relevance. \ nA medication review predictive model has the potential to enhance how med ication-related risks are identified post-hospital discharge and managed a cross healthcare settings. By flagging patients who would benefit from med ication reviews in care transition, the model will not only enhance medica tion safety but also support clinicians in making more informed decisions under time constraints. One key benefit from a user-centered approach is t hat it can guide the design of the model's outputs, ensuring that they are not only accurate but also resonate with the practical experiences of hea lthcare professionals, facilitating their integration into clinical workfl ows. Another key benefit of the model is its ability to prioritize high-ri sk patients. Clinicians often struggle to deal with the high volume of pat ients and the complexity of their cases, by identifying patients who are a t risk of the effects of medication-related problems and likely need a rev iew of their prescribed medication, such systems can help by streamlining the identification of at-risk individuals and consequently reducing mental workload in clinicians. END:VEVENT END:VCALENDAR