{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:59:58Z","timestamp":1773964798851,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Laby Foundation"},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"crossref","award":["1054618"],"award-info":[{"award-number":["1054618"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-025-00489-y","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T11:42:06Z","timestamp":1761738126000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Using artificial intelligence (AI) to model clinical variant reporting for next generation sequencing (NGS) oncology assays"],"prefix":"10.1186","volume":"18","author":[{"given":"Kenneth D.","family":"Doig","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rashindrie","family":"Perera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yamuna","family":"Kankanige","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Fellowes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Lupat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ella R.","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piers","family":"Blombery","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen B.","family":"Fox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"489_CR1","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1016\/S1470-2045(15)00195-3","volume":"16","author":"K Doig","year":"2015","unstructured":"Doig K, Papenfuss AT, Fox S. Clinical cancer genomic analysis: data engineering required. Lancet Oncol. 2015;16:1015\u20137. https:\/\/doi.org\/10.1016\/S1470-2045(15)00195-3.","journal-title":"Lancet Oncol"},{"key":"489_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-022-01214-y","author":"KD Doig","year":"2022","unstructured":"Doig KD, et al. Findings from precision oncology in the clinic: rare, novel variants are a significant contributor to scaling molecular diagnostics. BMC Med Genomics. 2022. https:\/\/doi.org\/10.1186\/s12920-022-01214-y.","journal-title":"BMC Med Genomics"},{"key":"489_CR3","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-017-0427-z","volume":"9","author":"KD Doig","year":"2017","unstructured":"Doig KD, et al. PathOS: a decision support system for reporting high throughput sequencing of cancers in clinical diagnostic laboratories. Genome Med. 2017;9:38. https:\/\/doi.org\/10.1186\/s13073-017-0427-z.","journal-title":"Genome Med"},{"key":"489_CR4","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.gde.2017.01.001","volume":"42","author":"DC Hoskinson","year":"2017","unstructured":"Hoskinson DC, Dubuc AM, Mason-Suares H. The current state of clinical interpretation of sequence variants. Curr Opin Genet Dev. 2017;42:33\u20139. https:\/\/doi.org\/10.1016\/j.gde.2017.01.001.","journal-title":"Curr Opin Genet Dev"},{"key":"489_CR5","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1038\/s41436-021-01187-w","volume":"23","author":"SE Lincoln","year":"2021","unstructured":"Lincoln SE, et al. One in seven pathogenic variants can be challenging to detect by NGS: an analysis of 450,000 patients with implications for clinical sensitivity and genetic test implementation. Genet Med. 2021;23:1673\u201380. https:\/\/doi.org\/10.1038\/s41436-021-01187-w.","journal-title":"Genet Med"},{"key":"489_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1038\/s41588-018-0257-y","volume":"50","author":"BJ Ainscough","year":"2018","unstructured":"Ainscough BJ, et al. A deep learning approach to automate refinement of somatic variant calling from cancer sequencing data. Nat Genet. 2018;50:1735\u201343. https:\/\/doi.org\/10.1038\/s41588-018-0257-y.","journal-title":"Nat Genet"},{"key":"489_CR7","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1038\/s41588-020-0603-8","volume":"52","author":"AH Wagner","year":"2020","unstructured":"Wagner AH, et al. A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer. Nat Genet. 2020;52:448\u201357. https:\/\/doi.org\/10.1038\/s41588-020-0603-8.","journal-title":"Nat Genet"},{"key":"489_CR8","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1038\/gim.2015.30","volume":"17","author":"S Richards","year":"2015","unstructured":"Richards S, et al. Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American college of medical genetics and genomics and the association for molecular pathology. Genet Med. 2015;17:405\u201324. https:\/\/doi.org\/10.1038\/gim.2015.30.","journal-title":"Genet Med"},{"key":"489_CR9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.jmoldx.2016.10.002","volume":"19","author":"MM Li","year":"2017","unstructured":"Li MM, et al. Standards and guidelines for the interpretation and reporting of sequence variants in cancer: A joint consensus recommendation of the association for molecular Pathology, American society of clinical Oncology, and college of American pathologists. J Mol Diagnostics: JMD. 2017;19:4\u201323. https:\/\/doi.org\/10.1016\/j.jmoldx.2016.10.002.","journal-title":"J Mol Diagnostics: JMD"},{"key":"489_CR10","doi-asserted-by":"publisher","first-page":"D941","DOI":"10.1093\/nar\/gky1015","volume":"47","author":"JG Tate","year":"2018","unstructured":"Tate JG, et al. COSMIC: the catalogue of somatic mutations in cancer. Nucleic Acids Res. 2018;47:D941\u20137. https:\/\/doi.org\/10.1093\/nar\/gky1015.","journal-title":"Nucleic Acids Res"},{"key":"489_CR11","doi-asserted-by":"publisher","DOI":"10.1126\/science.adg7492","volume":"381","author":"J Cheng","year":"2023","unstructured":"Cheng J, et al. Accurate proteome-wide missense variant effect prediction with alphamissense. Science. 2023;381:eadg7492. https:\/\/doi.org\/10.1126\/science.adg7492.","journal-title":"Science"},{"key":"489_CR12","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/nbt.3391","volume":"34","author":"MT Chang","year":"2016","unstructured":"Chang MT, et al. Identifying recurrent mutations in cancer reveals widespread lineage diversity and mutational specificity. Nat Biotechnol. 2016;34:155\u201363. https:\/\/doi.org\/10.1038\/nbt.3391.","journal-title":"Nat Biotechnol"},{"key":"489_CR13","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1158\/2159-8290.Cd-17-0321","volume":"8","author":"MT Chang","year":"2018","unstructured":"Chang MT, et al. Accelerating discovery of functional mutant alleles in cancer. Cancer Discov. 2018;8:174\u201383. https:\/\/doi.org\/10.1158\/2159-8290.Cd-17-0321.","journal-title":"Cancer Discov"},{"key":"489_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-020-00803-9","volume":"12","author":"X Liu","year":"2020","unstructured":"Liu X, Li C, Mou C, Dong Y, Tu Y. DbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs. Genome Med. 2020;12:103. https:\/\/doi.org\/10.1186\/s13073-020-00803-9.","journal-title":"Genome Med"},{"key":"489_CR15","doi-asserted-by":"publisher","first-page":"D1143","DOI":"10.1093\/nar\/gkad989","volume":"52","author":"M Schubach","year":"2024","unstructured":"Schubach M, Maass T, Nazaretyan L, Roner S, Kircher M. CADD v1.7: using protein Language models, regulatory CNNs and other nucleotide-level scores to improve genome-wide variant predictions. Nucleic Acids Res. 2024;52:D1143\u201354. https:\/\/doi.org\/10.1093\/nar\/gkad989.","journal-title":"Nucleic Acids Res"},{"key":"489_CR16","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1038\/ng.3774","volume":"49","author":"M Griffith","year":"2017","unstructured":"Griffith M, et al. CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer. Nat Genet. 2017;49:170\u20134. https:\/\/doi.org\/10.1038\/ng.3774.","journal-title":"Nat Genet"},{"key":"489_CR17","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv1222","author":"MJ Landrum","year":"2015","unstructured":"Landrum MJ, et al. ClinVar: public archive of interpretations of clinically relevant variants. Nucleic Acids Res. 2015. https:\/\/doi.org\/10.1093\/nar\/gkv1222.","journal-title":"Nucleic Acids Res"},{"key":"489_CR18","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1038\/s41586-020-2308-7","volume":"581","author":"KJ Karczewski","year":"2020","unstructured":"Karczewski KJ, et al. The mutational constraint spectrum quantified from variation in 141,456 humans. Nature. 2020;581:434\u201343. https:\/\/doi.org\/10.1038\/s41586-020-2308-7.","journal-title":"Nature"},{"key":"489_CR19","doi-asserted-by":"publisher","unstructured":"Chakravarty D, et al. OncoKB: A Precision Oncology Knowledge Base. JCO Precis Oncol. 2017.\u00a0https:\/\/doi.org\/10.1200\/po.17.00011\u00a0.","DOI":"10.1200\/po.17.00011"},{"key":"489_CR20","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1038\/s41588-021-00949-1","volume":"53","author":"P Srinivasan","year":"2021","unstructured":"Srinivasan P, et al. The context-specific role of germline pathogenicity in tumorigenesis. Nat Genet. 2021;53:1577\u201385. https:\/\/doi.org\/10.1038\/s41588-021-00949-1.","journal-title":"Nat Genet"},{"key":"489_CR21","unstructured":"TimeSeriesSplit. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.model_selection.TimeSeriesSplit.html."},{"key":"489_CR22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE. 2015;10:e0118432. https:\/\/doi.org\/10.1371\/journal.pone.0118432.","journal-title":"PLoS ONE"},{"key":"489_CR23","doi-asserted-by":"publisher","unstructured":"Ho TK. Random Decision Forests. Proceedings of the Third International Conference onDocument Analysis and Recognition. 1995;1:278\u201382. https:\/\/doi.org\/10.1109\/ICDAR.1995.598994.","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"489_CR24","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Association for Computing Machinery large-scale machine learning, SanFrancisco, California, USA.\u00a0https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"489_CR25","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg SM, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell. 2020;2:56\u201367. https:\/\/doi.org\/10.1038\/s42256-019-0138-9.","journal-title":"Nat Mach Intell"},{"key":"489_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","volume":"17","author":"CJ Kelly","year":"2019","unstructured":"Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17:195. https:\/\/doi.org\/10.1186\/s12916-019-1426-2.","journal-title":"BMC Med"},{"key":"489_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01332-6","volume":"20","author":"J Amann","year":"2020","unstructured":"Amann J, et al. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak. 2020;20:310. https:\/\/doi.org\/10.1186\/s12911-020-01332-6.","journal-title":"BMC Med Inform Decis Mak"},{"key":"489_CR28","doi-asserted-by":"publisher","unstructured":"Rakers MM, van Buchem MM, Kucenko S, et al. Availability of evidence forpredictive machine learning algorithms in primary care: a systematic review. JAMA Netw Open. 2024;7(9):e2432990. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.32990.","DOI":"10.1001\/jamanetworkopen.2024.32990"},{"key":"489_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00549-7","author":"AAH de Hond","year":"2022","unstructured":"de Hond AAH, et al. Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review. NPJ Digit Med. 2022. https:\/\/doi.org\/10.1038\/s41746-021-00549-7.","journal-title":"NPJ Digit Med"},{"issue":"5","key":"489_CR30","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin C. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat Mach Intell. 2019;1(5):206\u201315. https:\/\/doi.org\/10.1038\/s42256-019-0048-x.","journal-title":"Nat Mach Intell"},{"key":"489_CR31","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1136\/amiajnl-2011-000089","volume":"19","author":"K Goddard","year":"2012","unstructured":"Goddard K, Roudsari A, Wyatt JC. Automation bias: a systematic review of frequency, effect mediators, and mitigators. J Am Med Inform Assoc. 2012;19:121\u20137. https:\/\/doi.org\/10.1136\/amiajnl-2011-000089.","journal-title":"J Am Med Inform Assoc"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00489-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-025-00489-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00489-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T11:42:08Z","timestamp":1761738128000},"score":1,"resource":{"primary":{"URL":"https:\/\/biodatamining.biomedcentral.com\/articles\/10.1186\/s13040-025-00489-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["489"],"URL":"https:\/\/doi.org\/10.1186\/s13040-025-00489-y","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"2 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethics approval was granted on 1 April 2022 (EPIC Study Code: PMC81837, HREC: 81837).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"74"}}