{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:54:46Z","timestamp":1753890886497,"version":"3.41.2"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Genet."],"abstract":"<jats:p>Patients with the target gene mutation frequently derive significant clinical benefits from target therapy. However, differences in the abundance level of mutations among patients resulted in varying survival benefits, even among patients with the same target gene mutations. Currently, there is a lack of rational and interpretable models to assess the risk of treatment failure<jats:bold>.<\/jats:bold> In this study, we investigated the underlying coupled factors contributing to variations in medication sensitivity and established a statistically interpretable framework, named SAFE-MIL, for risk estimation. We first constructed an effectiveness label for each patient from the perspective of exploring the optimal grouping of patients\u2019 positive judgment values and sampled patients into 600 and 1,000 groups, respectively, based on multi-instance learning (MIL). A novel and interpretable loss function was further designed based on the Hosmer-Lemeshow test for this framework. By integrating multi-instance learning with the Hosmer-Lemeshow test, SAFE-MIL is capable of accurately estimating the risk of drug treatment failure across diverse patient cohorts and providing the optimal threshold for assessing the risk stratification simultaneously. We conducted a comprehensive case study involving 457 non-small cell lung cancer patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors. Results demonstrate that SAFE-MIL outperforms traditional regression methods with higher accuracy and can accurately assess patients\u2019 risk stratification. This underscores its ability to accurately capture inter-patient variability in risk while providing statistical interpretability. SAFE-MIL is able to effectively guide clinical decision-making regarding the use of drugs in targeted therapy and provides an interpretable computational framework for other patient stratification problems. The SAFE-MIL framework has proven its effectiveness in capturing inter-patient variability in risk and providing statistical interpretability. It outperforms traditional regression methods and can effectively guide clinical decision-making in the use of drugs for targeted therapy. SAFE-MIL offers a valuable interpretable computational framework that can be applied to other patient stratification problems, enhancing the precision of risk assessment in personalized medicine. The source code for SAFE-MIL is available for further exploration and application at <jats:ext-link>https:\/\/github.com\/Nevermore233\/SAFE-MIL<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/fgene.2024.1381851","type":"journal-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T04:35:23Z","timestamp":1723696523000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SAFE-MIL: a statistically interpretable framework for screening potential targeted therapy patients based on risk estimation"],"prefix":"10.3389","volume":"15","author":[{"given":"Yanfang","family":"Guan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengfa","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghao","family":"Ai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.5555\/944919.944949","article-title":"Multiple-instance learning of real-valued data","volume":"28","author":"Amar","year":"2001","journal-title":"InICML"},{"key":"B2","doi-asserted-by":"publisher","first-page":"592303","DOI":"10.3389\/fimmu.2021.592303","article-title":"Machine learning identifies complicated sepsis course and subsequent mortality based on 20 genes in peripheral blood immune cells at 24 H post-ICU admission","volume":"12","author":"Banerjee","year":"2021","journal-title":"Front. Immunol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1693","DOI":"10.1038\/ng.3990","article-title":"Evolution and clinical impact of co-occurring genetic alterations in advanced-stage EGFR-mutant lung cancers","volume":"49","author":"Blakely","year":"2017","journal-title":"Nat. Genet."},{"key":"B4","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1093\/annonc\/mdz060","article-title":"Analysis of time-to-treatment discontinuation of targeted therapy, immunotherapy, and chemotherapy in clinical trials of patients with non-small-cell lung cancer","volume":"30","author":"Blumenthal","year":"2019","journal-title":"Ann. Oncol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"5055","DOI":"10.1109\/JBHI.2021.3133455","article-title":"AI-driven synthetic biology for non-small cell lung cancer drug effectiveness-cost analysis in intelligent assisted medical systems","volume":"26","author":"Chang","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B6","doi-asserted-by":"publisher","first-page":"e1279","DOI":"10.1002\/iid3.1279","article-title":"Machine learning reveals ferroptosis features and a novel ferroptosis classifier in patients with sepsis","volume":"12","author":"Chen","year":"2024","journal-title":"Immun. Inflamm. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.lungcan.2020.04.004","article-title":"Comprehensive characterization and clinical impact of concomitant genomic alterations in EGFR-mutant NSCLCs treated with EGFR kinase inhibitors","volume":"145","author":"Cheng","year":"2020","journal-title":"Lung Cancer"},{"key":"B8","doi-asserted-by":"publisher","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J. R. Soc. Interface"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3154","DOI":"10.1109\/JBHI.2020.3004663","article-title":"Q-rank: reinforcement learning for recommending algorithms to predict drug sensitivity to cancer therapy","volume":"24","author":"Daoud","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1001\/jamacardio.2022.1781","article-title":"A simple score to identify increased risk of transthyretin amyloid cardiomyopathy in heart failure with preserved ejection fraction","volume":"7","author":"Davies","year":"2022","journal-title":"JAMA Cardiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1286203","DOI":"10.3389\/fimmu.2023.1286203","article-title":"A simplified machine learning model utilizing platelet-related genes for predicting poor prognosis in sepsis","volume":"14","author":"Diao","year":"2023","journal-title":"Front. Immunol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"507","DOI":"10.2307\/2331838","article-title":"Frequency distribution of the values of the correlation coefficient in samples from an indefinitely large population","volume":"10","author":"Fisher","year":"1915","journal-title":"Biometrika"},{"key":"B13","first-page":"3","article-title":"On the 'probable error' of a coefficient of correlation deduced from a small sample","author":"Fisher","year":"1921","journal-title":"Contributions Math. Statistics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1186\/1471-2105-13-S15-S3","article-title":"Implementation of multiple-instance learning in drug activity prediction","volume":"13","author":"Fu","year":"2012","journal-title":"BMC Bioinforma."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e53885","DOI":"10.3791\/53885","article-title":"A combined 3D tissue engineered in vitro\/in silico lung tumor model for predicting drug effectiveness in specific mutational backgrounds","volume":"110","author":"G\u00f6ttlich","year":"2016","journal-title":"J. Vis. Exp."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1080\/03610928008827941","article-title":"Goodness of fit tests for the multiple logistic regression model","volume":"9","author":"Hosmer","year":"1980","journal-title":"Commun. Statistics - Theory Methods"},{"key":"B17","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-1-4612-4380-9_35","article-title":"Robust estimation of a location parameter","author":"Huber","year":"1992","journal-title":"Break. statistics Methodol. distribution"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2052","DOI":"10.1097\/01.CCM.0000275267.64078.B0","article-title":"Assessing the calibration of mortality benchmarks in critical care: the Hosmer-Lemeshow test revisited","volume":"35","author":"Kramer","year":"2007","journal-title":"Crit. Care Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1016\/j.ccell.2020.09.014","article-title":"Predicting drug response and synergy using a deep learning model of human cancer cells","volume":"38","author":"Kuenzi","year":"2020","journal-title":"Cancer Cell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2254","DOI":"10.21037\/jtd-22-755","article-title":"EGFR mutation types and abundance were associated with the overall survival of advanced lung adenocarcinoma patients receiving first-line tyrosine kinase inhibitors","volume":"14","author":"Liu","year":"2022","journal-title":"J. Thorac. Dis."},{"key":"B21","doi-asserted-by":"publisher","first-page":"8283","DOI":"10.1038\/s41598-022-12271-9","article-title":"Long-term drug effectiveness and survival for reference rituximab in rheumatoid arthritis patients in an ordinary outpatient clinic","volume":"12","author":"\u0141osi\u0144ska","year":"2022","journal-title":"Sci. Rep."},{"key":"B22","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","article-title":"An interpretable machine learning model for accurate prediction of sepsis in the ICU","volume":"46","author":"Nemati","year":"2018","journal-title":"Crit. care Med."},{"key":"B23","doi-asserted-by":"publisher","first-page":"3114","DOI":"10.1038\/s41467-018-05327-w","article-title":"Circulating tumor DNA analysis depicts subclonal architecture and genomic evolution of small cell lung cancer [published correction appears in Nat Commun 2019 Jan 29;10(1):552]","volume":"9","author":"Nong","year":"2018","journal-title":"Nat. Commun."},{"key":"B24","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1056\/NEJMoa1810865","article-title":"Pembrolizumab plus chemotherapy for squamous non-small-cell lung cancer","volume":"379","author":"Paz-Ares","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1109\/JBHI.2021.3102186","article-title":"Predicting drug response based on multi-omics fusion and graph convolution","volume":"26","author":"Peng","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B26","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1038\/s41586-021-03898-1","article-title":"Structure-based classification predicts drug response in EGFR-mutant NSCLC","volume":"597","author":"Robichaux","year":"2021","journal-title":"Nature"},{"key":"B27","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/nrclinonc.2012.22","article-title":"Drug development and clinical trials--the path to an approved cancer drug","volume":"9","author":"Rubin","year":"2012","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"3128","DOI":"10.1109\/TMI.2022.3178523","article-title":"DEEMD: drug efficacy estimation against SARS-CoV-2 based on cell morphology with deep multiple instance learning","volume":"41","author":"Saberian","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B29","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1038\/s41588-018-0312-8","article-title":"Tumor mutational load predicts survival after immunotherapy across multiple cancer types","volume":"51","author":"Samstein","year":"2019","journal-title":"Nat. Genet."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.1200\/JCO.2015.61.6706","article-title":"American society of clinical oncology statement: a conceptual framework to assess the value of cancer treatment options","volume":"33","author":"Schnipper","year":"2015","journal-title":"J. Clin. Oncol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"3926","DOI":"10.1109\/TNNLS.2017.2750679","article-title":"Continuous dropout","volume":"29","author":"Shen","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn Syst."},{"key":"B32","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1109\/TCBB.2021.3084562","article-title":"Machine learning for pharmacogenomics and personalized medicine: a ranking model for drug sensitivity prediction","volume":"19","author":"Sotudian","year":"2022","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B33","doi-asserted-by":"publisher","first-page":"13274","DOI":"10.1021\/acs.analchem.1c02877","article-title":"Self-internal-reference probe system for control-free quantification of mutation abundance","volume":"93","author":"Tang","year":"2021","journal-title":"Anal. Chem."},{"key":"B34","doi-asserted-by":"publisher","first-page":"11136","DOI":"10.3390\/ijms231911136","article-title":"Modeling DTA by combining multiple-instance learning with a private-public mechanism","volume":"23","author":"Wang","year":"2022","journal-title":"Int. J. Mol. Sci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"635","DOI":"10.21037\/atm-20-7155","article-title":"Plasma EGFR mutation abundance affects clinical response to first-line EGFR-TKIs in patients with advanced non-small cell lung cancer","volume":"9","author":"Wang","year":"2021","journal-title":"Ann. Transl. Med."},{"key":"B36","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.lungcan.2018.12.007","article-title":"Efficacy of first-line treatment with epidermal growth factor receptor-tyrosine kinase inhibitor (EGFR-TKI) alone or in combination with chemotherapy for advanced non-small cell lung cancer (NSCLC) with low-abundance mutation","volume":"128","author":"Yan","year":"2019","journal-title":"Lung Cancer"},{"key":"B37","doi-asserted-by":"publisher","first-page":"bbac518.","DOI":"10.1093\/bib\/bbac518","article-title":"DRONet: effectiveness-driven drug repositioning framework using network embedding and ranking learning","volume":"24","author":"Yang","year":"2023","journal-title":"Brief. Bioinform"},{"key":"B38","doi-asserted-by":"publisher","first-page":"671184","DOI":"10.3389\/fmed.2021.671184","article-title":"Construction and evaluation of a sepsis risk prediction model for urinary tract infection","volume":"8","author":"Zhang","year":"","journal-title":"Front. Med. (Lausanne)"},{"key":"B39","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s40425-019-0581-5","article-title":"The correlations of tumor mutational burden among single-region tissue, multi-region tissues and blood in non-small cell lung cancer","volume":"7","author":"Zhang","year":"2019","journal-title":"J. Immunother. Cancer"},{"key":"B40","doi-asserted-by":"publisher","first-page":"265","DOI":"10.4103\/wjtcm.wjtcm_28_21","article-title":"International clinical practice guideline of Chinese medicine Alzheimer","volume":"7","author":"Zhang","year":"","journal-title":"World J. Trad. Chin. Med."},{"key":"B41","doi-asserted-by":"publisher","first-page":"216","DOI":"10.21037\/atm.2018.05.32","article-title":"Opening the black box of neural networks: methods for interpreting neural network models in clinical applications","volume":"6","author":"Zhang","year":"2018","journal-title":"Ann. Transl. Med."},{"key":"B42","doi-asserted-by":"publisher","first-page":"103081","DOI":"10.1016\/j.ebiom.2020.103081","article-title":"Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values","volume":"62","author":"Zhang","year":"2020","journal-title":"EBioMedicine"},{"key":"B43","doi-asserted-by":"publisher","first-page":"S16","DOI":"10.1186\/1471-2105-14-S14-S16","article-title":"Drug activity prediction using multiple-instance learning via joint instance and feature selection","volume":"14","author":"Zhao","year":"2013","journal-title":"BMC Bioinforma."},{"key":"B44","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1200\/JCO.2010.33.3757","article-title":"Relative abundance of EGFR mutations predicts benefit from gefitinib treatment for advanced non-small-cell lung cancer","volume":"29","author":"Zhou","year":"2011","journal-title":"J. Clin. Oncol."}],"container-title":["Frontiers in Genetics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2024.1381851\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T04:35:27Z","timestamp":1723696527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2024.1381851\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,15]]},"references-count":44,"alternative-id":["10.3389\/fgene.2024.1381851"],"URL":"https:\/\/doi.org\/10.3389\/fgene.2024.1381851","relation":{},"ISSN":["1664-8021"],"issn-type":[{"type":"electronic","value":"1664-8021"}],"subject":[],"published":{"date-parts":[[2024,8,15]]},"article-number":"1381851"}}