{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T02:06:53Z","timestamp":1793066813010,"version":"4.5.0"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T00:00:00Z","timestamp":1675814400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["NIHR130581"],"award-info":[{"award-number":["NIHR130581"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["NIHR203986"],"award-info":[{"award-number":["NIHR203986"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Health Data Research UK","id":[{"id":"https:\/\/ror.org\/04rtjaj74","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["PSTRC-2016-003"],"award-info":[{"award-number":["PSTRC-2016-003"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIHR NW Coast Applied Research Collaboration"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Polypharmacy can be a consequence of overprescribing that is prevalent in older adults with multimorbidity. Polypharmacy can cause adverse reactions and result in hospital admission. This study predicted risks of adverse drug reaction (ADR)-related and emergency hospital admissions by medicine classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used electronic health record data from general practices of Clinical Practice Research Datalink (CPRD GOLD) and Aurum. Older patients who received at least five medicines were included. Medicines were classified using the British National Formulary sections. Hospital admission cases were propensity-matched to controls by age, sex, and propensity for specific diseases. The matched data were used to develop and validate random forest (RF) models to predict the risk of ADR-related and emergency hospital admissions. Shapley Additive eXplanation (SHAP) values were calculated to explain the predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In total, 89,235 cases with polypharmacy and hospitalised with an ADR-related admission were matched to 443,497 controls. There were over 112,000 different combinations of the 50 medicine classes most implicated in ADR-related hospital admission in the RF models, with the most important medicine classes being loop diuretics, domperidone and\/or metoclopramide, medicines for iron-deficiency anaemias and for hypoplastic\/haemolytic\/renal anaemias, and sulfonamides and\/or trimethoprim. The RF models strongly predicted risks of ADR-related and emergency hospital admission. The observed Odds Ratio in the highest RF decile was 7.16 (95% CI 6.65\u20137.72) in the validation dataset. The C-statistics for ADR-related hospital admissions were 0.58 for age and sex and 0.66 for RF probabilities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Polypharmacy involves a very large number of different combinations of medicines, with substantial differences in risks of ADR-related and emergency hospital admissions. Although the medicines may not be causally related to increased risks, RF model predictions may be useful in prioritising medication reviews. Simple tools based on few medicine classes may not be effective in identifying high risk patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0281466","type":"journal-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:31:43Z","timestamp":1675863103000},"page":"e0281466","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":25,"title":["Combinations of medicines in patients with polypharmacy aged 65\u2013100 in primary care: Large variability in risks of adverse drug related and emergency hospital admissions"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1661-4475","authenticated-orcid":true,"given":"Ali","family":"Fahmi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8117-9193","authenticated-orcid":true,"given":"David","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren","family":"Walker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iain","family":"Buchan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Munir","family":"Pirmohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anita","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harriet","family":"Cant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2958-915X","authenticated-orcid":true,"given":"Darren M.","family":"Ashcroft","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9363-742X","authenticated-orcid":true,"given":"Tjeerd Pieter","family":"van Staa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,2,8]]},"reference":[{"key":"pone.0281466.ref001","year":"2021","journal-title":"Good for you, good for us, good for everybody"},{"key":"pone.0281466.ref002","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12916-015-0322-7","article-title":"The rising tide of polypharmacy and drug-drug interactions: Population database analysis 1995\u20132010.","volume":"13","author":"B Guthrie","year":"2015","journal-title":"BMC Med"},{"key":"pone.0281466.ref003","first-page":"21","article-title":"Exclusion rates in randomized controlled trials of treatments for physical conditions: a systematic review.","author":"J He","year":"2020","journal-title":"Trials"},{"key":"pone.0281466.ref004","unstructured":"Duerden M, Avery T, Payne R. Polypharmacy and medicines optimisation: Making it safe and sound."},{"key":"pone.0281466.ref005","author":"World Health Organization","year":"2017","journal-title":"Medication Without Harm"},{"key":"pone.0281466.ref006","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1111\/bcp.14368","article-title":"Evidence for the impact of interventions and medicines reconciliation on problematic polypharmacy in the UK: A rapid review of systematic reviews","volume":"87","author":"M Martyn-St James","year":"2021","journal-title":"Br J Clin Pharmacol"},{"key":"pone.0281466.ref007","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1093\/ageing\/afu145","article-title":"STOPP\/START criteria for potentially inappropriate prescribing inolder people: version 2","volume":"44","author":"O O\u2019mahony D","year":"2015","journal-title":"Age Ageing"},{"key":"pone.0281466.ref008","doi-asserted-by":"crossref","first-page":"n1585","DOI":"10.1136\/bmj.n1585","article-title":"Optimizing Therapy to Prevent Avoidable Hospital Admissions in Multimorbid Older Adults (OPERAM): cluster randomised controlled trial.","volume":"374","author":"MR Blum","year":"2021","journal-title":"BMJ"},{"key":"pone.0281466.ref009","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1093\/ije\/dyv098","article-title":"Data Resource Profile: Clinical Practice Research Datalink (CPRD).","volume":"44","author":"E Herrett","year":"2015","journal-title":"Int J Epidemiol."},{"key":"pone.0281466.ref010","doi-asserted-by":"crossref","first-page":"1740","DOI":"10.1093\/ije\/dyz034","article-title":"Data resource profile: Clinical Practice Research Datalink (CPRD) Aurum.","volume":"48","author":"A Wolf","year":"2019","journal-title":"Int J Epidemiol."},{"key":"pone.0281466.ref011","doi-asserted-by":"crossref","first-page":"e020738","DOI":"10.1136\/bmjopen-2017-020738","article-title":"Spatial distribution of clinical computer systems in primary care in England in 2016 and implications for primary care electronic medical record databases: a cross-sectional population study.","volume":"8","author":"E Kontopantelis","year":"2018","journal-title":"BMJ Open."},{"key":"pone.0281466.ref012","author":"GOV.UK","year":"2019","journal-title":"English indices of deprivation"},{"key":"pone.0281466.ref013","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0021-9681(87)90171-8","article-title":"A New Method of Classifying Prognostic in Longitudinal Studies: Development and Validation.","volume":"40","author":"ME Charlson","year":"1987","journal-title":"J Chronic Dis"},{"key":"pone.0281466.ref014","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1136\/amiajnl-2013-002116","article-title":"ICD-10 codes used to identify adverse drug events in administrative data: A systematic review","author":"CM Hohl","year":"2014","journal-title":"Journal of the American Medical Informatics Association. BMJ Publishing Group"},{"key":"pone.0281466.ref015","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1056\/NEJMsa1103053","article-title":"Emergency hospitalizations for adverse drug events in older Americans","volume":"365","author":"DS Budnitz","year":"2011","journal-title":"N Engl J Med"},{"key":"pone.0281466.ref016","doi-asserted-by":"crossref","first-page":"e003482","DOI":"10.1136\/bmjopen-2013-003482","article-title":"Predicting risk of emergency admission to hospital using primary care data: derivation and validation of QAdmissions score","volume":"3","author":"J Hippisley-Cox","year":"2013","journal-title":"BMJ Open"},{"key":"pone.0281466.ref017","first-page":"18","article-title":"Characteristics, service use and mortality of clusters of multimorbid patients in England: A population-based study.","author":"Y Zhu","year":"2020","journal-title":"BMC Med."},{"key":"pone.0281466.ref018","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1002\/pst.433","article-title":"Optimal caliper widths for propensity-score matching when estimating differences in means and differences in proportions in observational studies.","volume":"10","author":"PC Austin","year":"2011","journal-title":"Pharm Stat"},{"key":"pone.0281466.ref019","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L. Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"pone.0281466.ref020","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.cmpb.2016.03.020","article-title":"Congestive heart failure detection using random forest classifier","volume":"130","author":"Z Masetic","year":"2016","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0281466.ref021","doi-asserted-by":"crossref","first-page":"7028","DOI":"10.1109\/TIM.2020.2973843","article-title":"Deep Multimodel Cascade Method Based on CNN and Random Forest for Pharmaceutical Particle Detection","volume":"69","author":"H Zhang","year":"2020","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0281466.ref022","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1016\/j.jclinepi.2012.11.008","article-title":"Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes","volume":"66","author":"PC Austin","year":"2013","journal-title":"J Clin Epidemiol"},{"key":"pone.0281466.ref023","unstructured":"Breiman L, Cutler A. Random forests. [cited 26 Jul 2022]. Available: https:\/\/www.stat.berkeley.edu\/~breiman\/RandomForests\/cc_home.htm"},{"key":"pone.0281466.ref024","first-page":"30","article-title":"A Unified Approach to Interpreting Model Predictions.","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst."},{"key":"pone.0281466.ref025","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"SM Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"pone.0281466.ref026","first-page":"3","article-title":"Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare.","author":"SD Mohanty","year":"2022","journal-title":"Patterns"},{"key":"pone.0281466.ref027","author":"SM Lundberg","year":"2018","journal-title":"Welcome to the shap documentation"},{"key":"pone.0281466.ref028","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1097\/j.pain.0000000000001390","article-title":"The IASP classification of chronic pain for ICD-11: Chronic primary pain","volume":"160","author":"M Nicholas","year":"2019","journal-title":"Pain"},{"key":"pone.0281466.ref029","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.mayocp.2020.06.012","article-title":"Polypharmacy Management in Older Patients","volume":"96","author":"RW Hoel","year":"2021","journal-title":"Mayo Clin Proc"},{"key":"pone.0281466.ref030","first-page":"32","article-title":"Polypharmacy: Evaluating risks and deprescribing.","volume":"100","author":"AD Halli-Tierney","year":"2019","journal-title":"Am Fam Physician"},{"key":"pone.0281466.ref031","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.archger.2017.05.017","article-title":"A systematic review of trends in the selective exclusion of older participant from randomised clinical trials.","volume":"72","author":"M Thake","year":"2017","journal-title":"Arch Gerontol Geriatr"},{"key":"pone.0281466.ref032","doi-asserted-by":"crossref","unstructured":"Muth C, Blom JW, Smith SM, Johnell K, Gonzalez-Gonzalez AI, Nguyen TS, et al. Evidence supporting the best clinical management of patients with multimorbidity and polypharmacy: a systematic guideline review and expert consensus. doi: 10.1111\/joim.12842","DOI":"10.1111\/joim.12842"},{"key":"pone.0281466.ref033","article-title":"National overprescribing review report\u2014GOV.UK","author":"K. Ridge","year":"2021"},{"key":"pone.0281466.ref034","year":"2015","journal-title":"Medicines optimisation: the safe and effective use of medicines to enable the best possible outcomes NICE guideline"},{"key":"pone.0281466.ref035","unstructured":"Polypharmacy Guidance. 2018. Available: https:\/\/www.therapeutics.scot.nhs.uk\/wp-content\/uploads\/2018\/09\/Polypharmacy-Guidance-2018.pdf"},{"key":"pone.0281466.ref036","unstructured":"Juliette Ferry-Danini, What Is the Problem with the Opacity of Artificial Intelligence in Medicine? (Ethics@Noon-ish) | Centre for Ethics, University of Toronto."},{"key":"pone.0281466.ref037","doi-asserted-by":"crossref","first-page":"505","DOI":"10.2105\/AJPH.2005.066043","article-title":"Learning from evidence in a complex world.","volume":"96","author":"JD Sterman","year":"2006","journal-title":"Am J Public Health"},{"key":"pone.0281466.ref038","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.jclinepi.2021.11.001","article-title":"Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based.","volume":"142","author":"LG McCoy","year":"2022","journal-title":"J Clin Epidemiol"},{"key":"pone.0281466.ref039","doi-asserted-by":"crossref","unstructured":"Hern\u00e1n MA, Hsu J, Healy B. A Second Chance to Get Causal Inference Right: A Classification of Data Science Tasks. https:\/\/doi.org\/101080\/0933248020191579578. 2019;32: 42\u201349.","DOI":"10.1080\/09332480.2019.1579578"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:32:15Z","timestamp":1675863135000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281466"}},"subtitle":[],"editor":[{"given":"Giuseppe","family":"Di Martino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,2,8]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0281466","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,8]]}}}