Exploring polypharmacy with artificial intelligence: data analysis protocol

Background Polypharmacy is common among older adults and it represents a public health concern, due to the negative health impacts potentially associated with the use of several medications. However, the large number of medication combinations and sequences of use makes it complicated for traditional statistical methods to predict which therapy is genuinely associated with health outcomes. The project aims to use artificial intelligence (AI) to determine the quality of polypharmacy among older adults with chronic diseases in the province of Québec, Canada. Methods We will use data from the Quebec Integrated Chronic Disease Surveillance System (QICDSS). QICDSS contains information about prescribed medications in older adults in Quebec collected over 20 years. It also includes diagnostic codes and procedures, and sociodemographic data linked through a unique identification number for each individual. Our research will be structured around three interconnected research axes: AI, Health, and Law&Ethics. The AI research axis will develop algorithms for finding frequent patterns of medication use that correlate with health events, considering data locality and temporality (explainable AI or XAI). The Health research axis will translate these patterns into polypharmacy indicators relevant to public health surveillance and clinicians. The Law&Ethics axis will assess the social acceptability of the algorithms developed using AI tools and the indicators developed by the Heath axis and will ensure that the developed indicators neither discriminate against any population group nor increase the disparities already present in the use of medications. Discussion The multi-disciplinary research team consists of specialists in AI, health data, statistics, pharmacy, public health, law, and ethics, which will allow investigation of polypharmacy from different points of view and will contribute to a deeper understanding of the clinical, social, and ethical issues surrounding polypharmacy and its surveillance, as well as the use of AI for health record data. The project results will be disseminated to the scientific community, healthcare professionals, and public health decision-makers in peer-reviewed publications, scientific meetings, and reports. The diffusion of the results will ensure the confidentiality of individual data.

[1]  J. Benichou,et al.  Choice of time‐scale in Cox's model analysis of epidemiologic cohort data: a simulation study , 2004, Statistics in medicine.

[2]  James E. Helmreich.  Regression Modeling Strategies with Applications to Linear Models, Logistic and Ordinal Regression and Survival Analysis (2nd Edition) , 2016 .

[3]  J. Kortbeek,et al.  Derivation and Validation of a Quality Indicator to Benchmark In-Hospital Complications Among Injury Admissions. , 2016, JAMA surgery.

[4]  S. Mohile,et al.  Associations of Polypharmacy and Inappropriate Medications with Adverse Outcomes in Older Adults with Cancer: A Systematic Review and Meta-Analysis. , 2019, The oncologist.

[5]  M. Laroche,et al.  Mixed Bag “Polypharmacy”: Methodological Pitfalls and Challenges of This Exposure Definition , 2019, Current Epidemiology Reports.

[6]  Christian Borgelt,et al.  An implementation of the FP-growth algorithm , 2005 .

[7]  A. Frini,et al.  The delicate choice of optimal basic therapy for multimorbid older adults: A cross-sectional survey. , 2019, Research in social & administrative pharmacy : RSAP.

[8]  R. Agarwal.  Fast Algorithms for Mining Association Rules , 1994, VLDB 1994.

[9]  Benjamin Schrauwen,et al.  Training and Analysing Deep Recurrent Neural Networks , 2013, NIPS.

[10]  Sylvia Thun,et al.  The Use of FHIR in Digital Health - A Review of the Scientific Literature , 2019, GMDS.

[11]  Tommi S. Jaakkola,et al.  Towards Robust Interpretability with Self-Explaining Neural Networks , 2018, NeurIPS.

[12]  Alexander D'Amour,et al.  On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives , 2019, ArXiv.

[13]  Wouter M. Koolen,et al.  Monte-Carlo Tree Search by Best Arm Identification , 2017, NIPS.

[14]  J. Hoffman,et al.  National trends in prescription drug expenditures and projections for 2019. , 2019, American journal of health-system pharmacy : AJHP : official journal of the American Society of Health-System Pharmacists.

[15]  L. Lee,et al.  Updated guidelines for evaluating public health surveillance systems: recommendations from the Guidelines Working Group. , 2001, MMWR. Recommendations and reports : Morbidity and mortality weekly report. Recommendations and reports.

[16]  R. G. Parrish,et al.  Measuring Population Health Outcomes , 2010, Preventing chronic disease.

[17]  Emanuel Falkenauer,et al.  Genetic Algorithms and Grouping Problems , 1998 .

[18]  Lyse Langlois,et al.  La sensibilité éthique : Une fenêtre pour combattre les inégalités de pouvoir entre les groupes , 2015 .

[19]  A. Kesselheim,et al.  The High Cost of Prescription Drugs in the United States: Origins and Prospects for Reform. , 2016, JAMA.

[20]  S. Morgan,et al.  Chronic catastrophes: exploring the concentration and sustained nature of ambulatory prescription drug expenditures in the population of British Columbia, Canada. , 2009, Social science & medicine.

[21]  A. Murray,et al.  An overview of prevalence, determinants and health outcomes of polypharmacy , 2020, Therapeutic advances in drug safety.

[22]  Philip S. Yu,et al.  Mining Colossal Frequent Patterns by Core Pattern Fusion , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[23]  Daniel J. Vreeman,et al.  Recent Developments in Clinical Terminologies — SNOMED CT, LOINC, and RxNorm , 2018, Yearbook of Medical Informatics.

[24]  B. Hanratty,et al.  Adverse Outcomes of Polypharmacy in Older People: Systematic Review of Reviews. , 2020, Journal of the American Medical Directors Association.

[25]  Tyler J. VanderWeele,et al.  Sensitivity Analysis in Observational Research: Introducing the E-Value , 2017, Annals of Internal Medicine.

[26]  L. Guénette,et al.  Polypharmacy Definitions for Multimorbid Older Adults Need Stronger Foundations to Guide Research, Clinical Practice and Public Health , 2019, Pharmacy.

[27]  D. L. Le Couteur,et al.  Assessing the harms of polypharmacy requires careful interpretation and consistent definitions. , 2014, British journal of clinical pharmacology.

[28]  Wei Chen,et al.  Combinatorial Pure Exploration of Multi-Armed Bandits , 2014, NIPS.

[29]  Soojin Lee,et al.  Factors Contributing to Increases in Prescription Drug Expenditures Borne by National Health Insurance in South Korea , 2016, Yonsei medical journal.

[30]  M. Simard,et al.  Validation of the Combined Comorbidity Index of Charlson and Elixhauser to Predict 30-Day Mortality Across ICD-9 and ICD-10 , 2018, Medical care.

[31]  E L Korn,et al.  Time-to-event analysis of longitudinal follow-up of a survey: choice of the time-scale. , 1997, American journal of epidemiology.

[32]  N. Kerse,et al.  Interventions to improve the appropriate use of polypharmacy for older people. , 2018, The Cochrane database of systematic reviews.

[33]  Li Li,et al.  Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records , 2016, Scientific Reports.

[34]  B. Stiegler,et al.  Réflexion interdisciplinaire et interculturelle sur l’éthique du soin. L’expérience d’échanges France-Québec (2009–2015) , 2017 .

[35]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[36]  Walter F. Stewart,et al.  Doctor AI: Predicting Clinical Events via Recurrent Neural Networks , 2015, MLHC.

[37]  Björn Wettermark,et al.  Forecasting drug utilization and expenditure: ten years of experience in Stockholm , 2020, BMC Health Services Research.

[38]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[39]  Michal Abrahamowicz,et al.  The International Journal of Biostatistics CAUSAL INFERENCE Accuracy of Conventional and Marginal Structural Cox Model Estimators : A Simulation Study , 2011 .

[40]  C. Nélaton.  La philosophie dans l’éthique narrative. Narration, prise de décision et souffrance morale , 2015 .

[41]  C. Hughes,et al.  Appropriate Polypharmacy and Medicine Safety: When Many is not Too Many , 2015, Drug Safety.

[42]  Erik Schultes,et al.  The FAIR Guiding Principles for scientific data management and stewardship , 2016, Scientific Data.

[43]  R. Brook,et al.  Consensus methods: characteristics and guidelines for use. , 1984, American journal of public health.

[44]  S. Vansteelandt,et al.  Doubly robust estimation of attributable fractions in survival analysis , 2017, Statistical methods in medical research.

[45]  G. Petersson,et al.  The impact of increasing polypharmacy on prescribed drug expenditure-a register-based study in Sweden 2005-2009. , 2013, Health policy.

[46]  D St-Laurent,et al.  Quebec Integrated Chronic Disease Surveillance System (QICDSS), an innovative approach. , 2014, Chronic diseases and injuries in Canada.

[47]  Gillian E. Caughey,et al.  What is polypharmacy? A systematic review of definitions , 2017, BMC Geriatrics.

[48]  Tyler J. VanderWeele,et al.  Using the E-Value to Assess the Potential Effect of Unmeasured Confounding in Observational Studies , 2019, JAMA.

[49]  R. Pampalon,et al.  A deprivation index for health planning in Canada. , 2009, Chronic diseases in Canada.

[50]  Eric J Topol,et al.  High-performance medicine: the convergence of human and artificial intelligence , 2019, Nature Medicine.

[51]  J. Verho,et al.  Register‐based indicators for potentially inappropriate medication in high‐cost patients with excessive polypharmacy , 2015, Pharmacoepidemiology and drug safety.

[52]  G. Collins,et al.  Handling time varying confounding in observational research , 2017, British Medical Journal.

[53]  J. Hunt,et al.  Prescribed Drug Spending in Canada, 2019: A Focus on Public Drug Programs. , 2020, Healthcare quarterly.

[54]  W. Nicholson Price,et al.  Black-Box Medicine , 2014 .

[55]  Nathan Kallus,et al.  Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning , 2020, NeurIPS.

[56]  B. Burnand,et al.  The RAND/UCLA Appropriateness Method User's Manual , 2001 .

[57]  E. Steyerberg,et al.  [Regression modeling strategies]. , 2011, Revista espanola de cardiologia.