James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank
{"title":"优化结肠镜检查的使用,改善无症状患者的结直肠癌风险分层:决策曲线分析。","authors":"James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank","doi":"10.1177/00369330241266080","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.</p><p><strong>Design: </strong>All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.</p><p><strong>Results: </strong>3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.</p><p><strong>Conclusions: </strong>MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.</p>","PeriodicalId":21683,"journal":{"name":"Scottish Medical Journal","volume":" ","pages":"61-71"},"PeriodicalIF":1.4000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimising the use of colonoscopy to improve risk stratification for colorectal cancer in symptomatic patients: A decision-curve analysis.\",\"authors\":\"James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank\",\"doi\":\"10.1177/00369330241266080\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.</p><p><strong>Design: </strong>All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.</p><p><strong>Results: </strong>3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.</p><p><strong>Conclusions: </strong>MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.</p>\",\"PeriodicalId\":21683,\"journal\":{\"name\":\"Scottish Medical Journal\",\"volume\":\" \",\"pages\":\"61-71\"},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Scottish Medical Journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/00369330241266080\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/23 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scottish Medical Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/00369330241266080","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/23 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
Optimising the use of colonoscopy to improve risk stratification for colorectal cancer in symptomatic patients: A decision-curve analysis.
Objectives: Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.
Design: All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.
Results: 3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.
Conclusions: MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.
期刊介绍:
A unique international information source for the latest news and issues concerning the Scottish medical community. Contributions are drawn from Scotland and its medical institutions, through an array of international authors. In addition to original papers, Scottish Medical Journal publishes commissioned educational review articles, case reports, historical articles, and sponsoring society abstracts.This journal is a member of the Committee on Publications Ethics (COPE).