{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:03:31Z","timestamp":1789581811842,"version":"build-2803163510"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Purpose<\/jats:title>\n High complexity of modern processes renders manual process optimization impossible. The main goal of our work was to formalize and to demonstrate the practical efficiency of explainable rule-learning AI in complex process optimization.<\/jats:p>\n <\/jats:sec>\n \n Materials and methods<\/jats:title>\n Process optimization methodology was based on globally-optimal Boolean rule-learning AI models, capable of identifying multiple inefficiency patterns, and supporting process-oriented optimization metrics. To illustrate this approach in real-word environment, the study used 3994 liver and prostate Magnetic Resonance Imaging (MRI) exams performed on five 3T scanners at three outpatient facilities from January 2019 to January 2024. Imaging exams longer than 25 minutes were labeled as requiring optimization, which applied to 35.4% of liver and 52.6% of prostate cases. Rule-learning AI was applied to the MRI scanner log data to discover short and interpretable process optimization rules. The selected Boolean rules were used to implement improved exam protocols, and a permutation test was used to measure the statistical significance of the resulting change in average exam duration.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n N=1000 top rules, identifying the most significant processing delay patterns, were discovered by rule-learning AI from the scanner log data based on F1 score. A smaller set of 20 top rules was selected using the secondary operational impact metric, an estimate of each rule\u2019s impact on average scan duration. A change in liver MRI protocols based on findings from the top rule resulted in a 10.9% reduction of median scan time. The proportion of long liver exams was reduced from 35.4% to 23.9% (p < 0.001). Similar optimizations in prostate protocols were used to add a new scanning sequence, improving exam quality.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Globally optimal, multi-model rule-learning AI can transform feature-rich device logs into concise, interpretable, and operationally meaningful rules. When combined with domain expertise, this approach can support measurable and sustainable improvements in complex clinical workflows.<\/jats:p>\n <\/jats:sec>","DOI":"10.1371\/journal.pone.0358070","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:30:57Z","timestamp":1789579857000},"page":"e0358070","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Process optimization with rule-learning explainable AI, and its application to MRI scanning"],"prefix":"10.1371","volume":"21","author":[{"given":"Sean","family":"Hartmann","sequence":"first","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Sharp","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heather","family":"Johnston","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael S.","family":"Gee","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susie Y.","family":"Huang","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mukesh G.","family":"Harisinghani","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"G\u00fchring","sequence":"additional","affiliation":[{"name":"Siemens Healthineers","place":["Malvern, Pennsylvania, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ching","family":"Lo","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vibhas","family":"Deshpande","sequence":"additional","affiliation":[{"name":"Siemens Healthineers","place":["Malvern, Pennsylvania, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9107-5432","authenticated-orcid":true,"given":"Oleg S.","family":"Pianykh","sequence":"additional","affiliation":[{"name":"Mass General Brigham Hospital, Harvard Medical School","place":["Boston, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"issue":"5","key":"pone.0358070.ref001","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1007\/s10278-018-0170-z","article-title":"Developing deeper radiology exam insight to optimize MRI workflow and patient experience","volume":"32","author":"IA Talati","year":"2019","journal-title":"J Digit Imaging"},{"key":"pone.0358070.ref002","article-title":"Predicting slot lengths of MRI exams to decrease observed discrepancies between planning and execution","author":"X Wang","year":"2024","journal-title":"Curr Prob Diag Radiol"},{"key":"pone.0358070.ref003","unstructured":"Cohen WW, Singer Y. A simple, fast, and effective rule learner. In: AAAI\/IAAI, 1999."},{"issue":"3","key":"pone.0358070.ref004","doi-asserted-by":"crossref","DOI":"10.1214\/07-AOAS148","article-title":"Predictive learning via rule ensembles","volume":"2","author":"JH Friedman","year":"2008","journal-title":"Ann Appl Stat"},{"key":"pone.0358070.ref005","doi-asserted-by":"crossref","unstructured":"Wenmin Li, Jiawei Han, Jian Pei. CMAR: accurate and efficient classification based on multiple class-association rules. In: Proceedings 2001 IEEE International Conference on Data Mining. 369\u201376. https:\/\/doi.org\/10.1109\/icdm.2001.989541","DOI":"10.1109\/ICDM.2001.989541"},{"key":"pone.0358070.ref006","doi-asserted-by":"crossref","unstructured":"Yang H, Rudin C, Seltzer M. Scalable bayesian rule lists. In: Proceedings of the 34th International Conference on Machine Learning. 2017.","DOI":"10.32614\/CRAN.package.sbrl"},{"issue":"234","key":"pone.0358070.ref007","first-page":"1","article-title":"Learning certifiably optimal rule lists for categorical data","volume":"18","author":"E Angelino","year":"2018","journal-title":"J Mach Learn Res"},{"key":"pone.0358070.ref008","unstructured":"Dash S, Gunluk O, Wei D. Boolean decision rules via column generation. In: Advances in neural information processing systems, 2018."},{"issue":"2","key":"pone.0358070.ref009","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.ejor.2023.09.026","article-title":"Explainable AI for operational research: a defining framework, methods, applications, and a research agenda","volume":"317","author":"KW De Bock","year":"2024","journal-title":"Euro J Operat Res"},{"issue":"1","key":"pone.0358070.ref010","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s10845-021-01903-y","article-title":"Data-driven dynamic causality analysis of industrial systems using interpretable machine learning and process mining","volume":"34","author":"K Nadim","year":"2022","journal-title":"J Intell Manuf"},{"key":"pone.0358070.ref011","doi-asserted-by":"crossref","first-page":"100169","DOI":"10.1016\/j.egyai.2022.100169","article-title":"Explainable Artificial Intelligence (XAI) techniques for energy and power systems: review, challenges and opportunities","volume":"9","author":"R Machlev","year":"2022","journal-title":"Energy and AI"},{"issue":"1","key":"pone.0358070.ref012","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.eswa.2012.07.033","article-title":"Mining transportation logs for understanding the after-assembly block manufacturing process in the shipbuilding industry","volume":"40","author":"SK Lee","year":"2013","journal-title":"Expert Syst Appl"},{"key":"pone.0358070.ref013","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-19345-3","volume-title":"Process mining: discovery, conformance and enhancement of business processes","author":"W Van der Aalst","year":"2011"},{"key":"pone.0358070.ref014","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1067\/j.cpradiol.2022.01.001","article-title":"Correlating the radiological assessment of patient motion with the incidence of repeat sequences documented by log files","author":"JB Andre","year":"2022","journal-title":"Curr Prob Diag Radiol"},{"issue":"6","key":"pone.0358070.ref015","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.jacr.2016.11.021","article-title":"Improving MRI scanner utilization using modality log files","volume":"14","author":"ML Gunn","year":"2017","journal-title":"J Am Coll Radiol"},{"issue":"7","key":"pone.0358070.ref016","article-title":"Factors predicting the time-length variability of identically protocoled MRI exams","volume":"49","author":"GD Avey","year":"2019","journal-title":"J Magn Reson Imaging"},{"key":"pone.0358070.ref017","first-page":"919","article-title":"Automatic, log file-based process analysis of a clinical 1.5T MR scanner: a proof-of-concept study","author":"A Frydrychowicz","year":"2021","journal-title":"Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebende Verfahren"},{"issue":"4","key":"pone.0358070.ref018","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1055\/a-1659-8821","article-title":"Software-based evaluation of optimization potential for clinical MRI scanners in radiology","volume":"194","author":"TP Meyl","year":"2022","journal-title":"R\u00f6Fo - Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren"},{"issue":"1","key":"pone.0358070.ref019","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s10278-019-00252-w","article-title":"Large-scale assessment of scan-time variability and multiple-procedure efficiency for cross-sectional neuroradiological exams in clinical practice","volume":"33","author":"R Zhang","year":"2020","journal-title":"J Digit Imaging"},{"issue":"10","key":"pone.0358070.ref020","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0275814","article-title":"Human knowledge models: learning applied knowledge from the data","volume":"17","author":"E Dudyrev","year":"2022","journal-title":"PLoS One"},{"issue":"1","key":"pone.0358070.ref021","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1017\/S0140525X01003922","article-title":"The magical number 4 in short-term memory: a reconsideration of mental storage capacity","volume":"24","author":"N Cowan","year":"2001","journal-title":"The Behav Brain Sci"},{"issue":"1","key":"pone.0358070.ref022","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1111\/j.0956-7976.2005.00782.x","article-title":"How many variables can humans process?","author":"GS Halford","year":"2005","journal-title":"Psychol Sci"},{"issue":"27","key":"pone.0358070.ref023","doi-asserted-by":"crossref","first-page":"11252","DOI":"10.1073\/pnas.1104666108","article-title":"Neural substrates of cognitive capacity limitations","volume":"108","author":"TJ Buschman","year":"2011","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"2","key":"pone.0358070.ref024","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1038\/s41567-023-02303-0","article-title":"The low-rank hypothesis of complex systems","volume":"20","author":"V Thibeault","year":"2024","journal-title":"Nat Phys"},{"key":"pone.0358070.ref025","doi-asserted-by":"crossref","first-page":"54776","DOI":"10.1109\/ACCESS.2020.2980942","article-title":"Analysis of dimensionality reduction techniques on big data","volume":"8","author":"GT Reddy","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0358070.ref026","article-title":"Causal discovery in observational medical research: scoping review","volume":"14","author":"Z Liu","year":"2026","journal-title":"JMIR Med Inform"},{"issue":"1","key":"pone.0358070.ref027","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1080\/09332480.2019.1579578","article-title":"A second chance to get causal inference right: a classification of data science tasks","volume":"32","author":"MA Hern\u00e1n","year":"2019","journal-title":"Chance"},{"issue":"21","key":"pone.0358070.ref028","doi-asserted-by":"crossref","DOI":"10.1088\/0031-9155\/60\/21\/R297","article-title":"Reducing acquisition time in clinical MRI by data undersampling and compressed sensing reconstruction","volume":"60","author":"KG Hollingsworth","year":"2015","journal-title":"Phys Med Biol"},{"issue":"3","key":"pone.0358070.ref029","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1007\/s00330-022-09151-1","article-title":"Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time","volume":"33","author":"M Kaniewska","year":"2023","journal-title":"Eur Radiol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:31:03Z","timestamp":1789579863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358070"}},"subtitle":[],"editor":[{"given":"Arvind","family":"Mahindru","sequence":"first","affiliation":[{"name":"DAV University","place":["INDIA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":29,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358070","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]}}}