{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:05:38Z","timestamp":1785413138438,"version":"3.56.0"},"posted":{"date-parts":[[2026,5,5]]},"group-title":"Dermatology","reference-count":67,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,27]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:sec>\n                  <jats:title>Importance<\/jats:title>\n                  <jats:p>Hidradenitis suppurativa (HS) has been reported with several medications, but the spectrum of implicated drug classes and patient-level risk factors remains poorly characterized.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To characterize drug-associated HS pharmacovigilance signals across drug classes, distinguish new-onset from worsened disease, and evaluate whether machine learning (ML) approaches identify reproducible patient-level predictors.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Design<\/jats:title>\n                  <jats:p>Disproportionality and ML of spontaneous adverse event reports submitted from 2004 through 2023.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Setting<\/jats:title>\n                  <jats:p>The US Food and Drug Administration Adverse Event Reporting System.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Participants<\/jats:title>\n                  <jats:p>Reports containing a preferred term for hidradenitis, stratified by whether HS was a listed indication (worsened) or an adverse event only (new-onset). A parallel cohort comprised all tumor necrosis factor inhibitor (TNFi)-exposed reports.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Exposures<\/jats:title>\n                  <jats:p>Primary suspect and concomitant medications.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Main Outcomes and Measures<\/jats:title>\n                  <jats:p>Disproportionate reporting quantified by the reporting odds ratio; agent- and indication-specific hidradenitis suppurativa reporting rates; and discrimination, calibration, feature concordance, and risk enrichment of supervised machine-learning models estimating the probability of HS.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Among 5529 HS reports (3725 with and 1804 without an indication), patients were predominantly female (3511 [63.5%]), with a mean (SD) age of 41 (14) years. Among reports without a hidradenitis suppurativa indication, significant signals included adalimumab (reporting odds ratio, 12.6; 95% CI, 11.3-14.0), infliximab (8.2; 6.7-9.9), secukinumab (6.6; 5.2-8.2), and isotretinoin (6.2; 4.2-8.9). Among TNFi exposed reports, reporting rates were highest for adalimumab (1.08 per 1000; OR, 2.75; 95% CI, 2.41-3.14) and lowest for etanercept (0.11 per 1000; OR, 0.12; 95% CI, 0.09-0.15), and the association was strongest in inflammatory bowel disease (OR 3.06; 2.20-4.25); all reported associations were significant at P &lt; .001. Supervised ML models demonstrated similar discrimination while identifying consistent patient-level predictors of HS. Tree-based models showed greater enrichment of high-risk reports than penalized regression.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions and Relevance<\/jats:title>\n                  <jats:p>HS reporting signals spanned biologic, hormonal, retinoid, and immunomodulatory drug classes. Multiple supervised ML approaches consistently identified TNFi agent (adalimumab), age, and a history of arthropathy as associated with paradoxical HS, suggesting that pharmacovigilance data contain reproducible information on heterogeneity of HS reporting. These findings support indication-aware monitoring when initiating these therapies, while recognizing that spontaneous reports reflect disproportionate reporting rather than incidence or causality.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>KEY POINTS<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Question<\/jats:title>\n                    <jats:p>Which medications are associated with disproportionate reporting of hidradenitis suppurativa (HS), and can routinely collected pharmacovigilance data identify patient- and treatment-level characteristics associated with paradoxical HS?<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>In this disproportionality and machine-learning analysis of 5529 HS reports, significant reporting signals spanned tumor necrosis factor inhibitors, interleukin-17 inhibitors, retinoids, hormonal agents, and antineoplastics and were strongest for adalimumab and in inflammatory bowel disease. Calibrated risk models were concordant, and the best-performing model (gradient-boosted trees) enriched the highest-risk 1% approximately 16-fold for cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Meaning<\/jats:title>\n                    <jats:p>Findings support indication-aware dermatologic monitoring when initiating implicated therapies, but reflect disproportionate reporting rather than incidence or causality.<\/jats:p>\n                  <\/jats:sec>\n                <\/jats:sec>","DOI":"10.64898\/2026.05.04.26352179","type":"posted-content","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T22:15:18Z","timestamp":1778019318000},"source":"Crossref","is-referenced-by-count":0,"title":["Patient-Level Risk Characterization of Drug-Associated Hidradenitis Suppurativa Using Machine Learning"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7610-4869","authenticated-orcid":false,"given":"Kyle","family":"Maas","sequence":"first","affiliation":[{"name":"Vanderbilt University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire","family":"Brewer","sequence":"additional","affiliation":[{"name":"Vanderbilt University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Chai","sequence":"additional","affiliation":[{"name":"Vanderbilt University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dodie","family":"Park","sequence":"additional","affiliation":[{"name":"Center for Drug Safety and Immunology, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Martin-Pozo","sequence":"additional","affiliation":[{"name":"Center for Drug Safety and Immunology, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth","family":"Phillips","sequence":"additional","affiliation":[{"name":"Center for Drug Safety and Immunology, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8715-1378","authenticated-orcid":false,"given":"Eric","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Center for Drug Safety and Immunology, Vanderbilt University Medical Center"},{"name":"Department of Dermatology, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026073004200531000_2026.05.04.26352179v2.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(24)02475-9"},{"key":"2026073004200531000_2026.05.04.26352179v2.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2017.08.046"},{"key":"2026073004200531000_2026.05.04.26352179v2.3","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.49637"},{"key":"2026073004200531000_2026.05.04.26352179v2.4","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.72049"},{"key":"2026073004200531000_2026.05.04.26352179v2.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jid.2017.09.051"},{"key":"2026073004200531000_2026.05.04.26352179v2.6","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3549491"},{"key":"2026073004200531000_2026.05.04.26352179v2.7","doi-asserted-by":"publisher","DOI":"10.1111\/dth.13150"},{"key":"2026073004200531000_2026.05.04.26352179v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdcr.2024.12.022"},{"key":"2026073004200531000_2026.05.04.26352179v2.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2025.08.002"},{"key":"2026073004200531000_2026.05.04.26352179v2.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2023.06.025"},{"key":"2026073004200531000_2026.05.04.26352179v2.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2020.12.010"},{"key":"2026073004200531000_2026.05.04.26352179v2.12","doi-asserted-by":"publisher","DOI":"10.1111\/srt.13718"},{"key":"2026073004200531000_2026.05.04.26352179v2.13","doi-asserted-by":"publisher","DOI":"10.1159\/000506074"},{"key":"2026073004200531000_2026.05.04.26352179v2.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2023.103332"},{"key":"2026073004200531000_2026.05.04.26352179v2.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2016.01.018"},{"key":"2026073004200531000_2026.05.04.26352179v2.16","doi-asserted-by":"publisher","DOI":"10.1097\/MEG.0000000000002170"},{"key":"2026073004200531000_2026.05.04.26352179v2.17","doi-asserted-by":"publisher","DOI":"10.1080\/14740338.2022.2131770"},{"key":"2026073004200531000_2026.05.04.26352179v2.18","doi-asserted-by":"publisher","DOI":"10.1038\/clpt.2012.50"},{"key":"2026073004200531000_2026.05.04.26352179v2.19","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3701"},{"key":"2026073004200531000_2026.05.04.26352179v2.20","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1742"},{"key":"2026073004200531000_2026.05.04.26352179v2.21","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.602365"},{"key":"2026073004200531000_2026.05.04.26352179v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-18522-z"},{"key":"2026073004200531000_2026.05.04.26352179v2.23","doi-asserted-by":"publisher","DOI":"10.1002\/bcp.70377"},{"key":"2026073004200531000_2026.05.04.26352179v2.24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026073004200531000_2026.05.04.26352179v2.25","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"2026073004200531000_2026.05.04.26352179v2.26","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.960296"},{"key":"2026073004200531000_2026.05.04.26352179v2.27","doi-asserted-by":"publisher","DOI":"10.1101\/2025.03.05.25323441"},{"key":"2026073004200531000_2026.05.04.26352179v2.28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"2026073004200531000_2026.05.04.26352179v2.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2026.110381"},{"key":"2026073004200531000_2026.05.04.26352179v2.30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"2026073004200531000_2026.05.04.26352179v2.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.02.010"},{"key":"2026073004200531000_2026.05.04.26352179v2.32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"2026073004200531000_2026.05.04.26352179v2.33","unstructured":"Lundberg SM , Lee SI. A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS\u201917. Curran Associates Inc.; 2017:4768\u20134777. Accessed July 20, 2026. https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295230"},{"key":"2026073004200531000_2026.05.04.26352179v2.34","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487579"},{"key":"2026073004200531000_2026.05.04.26352179v2.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106415"},{"key":"2026073004200531000_2026.05.04.26352179v2.36","doi-asserted-by":"publisher","DOI":"10.1002\/bcp.70655"},{"key":"2026073004200531000_2026.05.04.26352179v2.37","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwg113"},{"key":"2026073004200531000_2026.05.04.26352179v2.38","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyu029"},{"key":"2026073004200531000_2026.05.04.26352179v2.39","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"2026073004200531000_2026.05.04.26352179v2.40","doi-asserted-by":"publisher","DOI":"10.1007\/s40257-024-00844-5"},{"key":"2026073004200531000_2026.05.04.26352179v2.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2021.01.059"},{"key":"2026073004200531000_2026.05.04.26352179v2.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.det.2023.12.004"},{"key":"2026073004200531000_2026.05.04.26352179v2.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.clindermatol.2020.10.016"},{"key":"2026073004200531000_2026.05.04.26352179v2.44","doi-asserted-by":"publisher","DOI":"10.1097\/PG9.0000000000000081"},{"key":"2026073004200531000_2026.05.04.26352179v2.45","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-022-01176-1"},{"key":"2026073004200531000_2026.05.04.26352179v2.46","doi-asserted-by":"publisher","DOI":"10.1002\/pds.5407"},{"key":"2026073004200531000_2026.05.04.26352179v2.47","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.4006"},{"key":"2026073004200531000_2026.05.04.26352179v2.48","doi-asserted-by":"publisher","DOI":"10.1111\/cei.13449"},{"key":"2026073004200531000_2026.05.04.26352179v2.49","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.16561"},{"key":"2026073004200531000_2026.05.04.26352179v2.50","doi-asserted-by":"publisher","DOI":"10.1007\/s40265-020-01460-3"},{"key":"2026073004200531000_2026.05.04.26352179v2.51","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0047578"},{"key":"2026073004200531000_2026.05.04.26352179v2.52","doi-asserted-by":"publisher","DOI":"10.1212\/NXI.0000000000000210"},{"key":"2026073004200531000_2026.05.04.26352179v2.53","doi-asserted-by":"publisher","DOI":"10.1159\/000530664"},{"key":"2026073004200531000_2026.05.04.26352179v2.54","doi-asserted-by":"publisher","DOI":"10.1159\/000315508"},{"key":"2026073004200531000_2026.05.04.26352179v2.55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdcr.2025.11.010"},{"key":"2026073004200531000_2026.05.04.26352179v2.56","doi-asserted-by":"publisher","DOI":"10.3390\/ijms21155342"},{"key":"2026073004200531000_2026.05.04.26352179v2.57","doi-asserted-by":"publisher","DOI":"10.3390\/ijms232315250"},{"key":"2026073004200531000_2026.05.04.26352179v2.58","doi-asserted-by":"publisher","DOI":"10.1097\/00000372-199702000-00013"},{"key":"2026073004200531000_2026.05.04.26352179v2.59","doi-asserted-by":"publisher","DOI":"10.1016\/S0190-9622(84)70210-6"},{"key":"2026073004200531000_2026.05.04.26352179v2.60","doi-asserted-by":"publisher","DOI":"10.3109\/10428194.2014.889826"},{"key":"2026073004200531000_2026.05.04.26352179v2.61","doi-asserted-by":"publisher","DOI":"10.1080\/14740338.2017.1323867"},{"key":"2026073004200531000_2026.05.04.26352179v2.62","doi-asserted-by":"publisher","DOI":"10.1007\/S40264-023-01302-7"},{"key":"2026073004200531000_2026.05.04.26352179v2.63","doi-asserted-by":"publisher","DOI":"10.2165\/00002018-200730100-00007"},{"key":"2026073004200531000_2026.05.04.26352179v2.64","doi-asserted-by":"publisher","DOI":"10.1002\/pds.3622"},{"key":"2026073004200531000_2026.05.04.26352179v2.65","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-014-0225-0"},{"key":"2026073004200531000_2026.05.04.26352179v2.66","doi-asserted-by":"publisher","DOI":"10.1002\/pds.4672"},{"key":"2026073004200531000_2026.05.04.26352179v2.67","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2022-071752"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.05.04.26352179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:20:16Z","timestamp":1785410416000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.05.04.26352179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":67,"URL":"https:\/\/doi.org\/10.64898\/2026.05.04.26352179","relation":{},"subject":[],"published":{"date-parts":[[2026,5,5]]},"subtype":"preprint"}}