Can we screen for pancreatic cancer? Identifying a sub-population of patients at high risk of subsequent diagnosis using machine learning techniques applied to primary care data.
Can we screen for pancreatic cancer? Identifying a sub-population of patients at high risk of subsequent diagnosis using machine learning techniques applied to primary care data.
复制标题
DOI：
10.1371/journal.pone.0251876
复制
发表时间：
2021
期刊：
影响因子：
3.7
通讯作者：
Woods LM
中科院分区：
文献类型：
--
作者：
Malhotra A;Rachet B;Bonaventure A;Pereira SP;Woods LM
胰腺癌(PC)是严重的公共卫生负担。胰腺癌患者的存活率非常低，因为当肿瘤局限于起源部位并可治疗时，很难及早识别癌症。最近在确定血液和尿液中PC的生物标记物方面取得了进展，但这些标记物不能用于基于人群的筛查，因为这将是令人望而却步的昂贵和潜在的有害。我们进行了一项病例对照研究，使用前瞻性收集的初级保健电子健康记录，这些记录分别与癌症登记有关。我们的病例包括1,139名患者，年龄15-99岁，在2005年1月1日至2009年6月30日期间被诊断为胰腺癌。每个病例的年龄、性别和诊断时间都与四名非胰腺(癌症患者)对照组相匹配。诊断前24个月的疾病和处方代码被用来识别57个单独的症状。使用机器学习方法，我们在75%的数据上训练Logistic回归模型来预测后来发展为PC的患者，并在其余25%的数据上测试该模型的性能。在确诊前20个月，我们能够识别出41.3%的60岁以上的胰腺癌高危患者，敏感度为72.5%，特异度为59%，AUC为66%。43.2%的60岁患者在17个月时被类似地确定，敏感度为65%，特异度为57%，AUC为61%。我们估计，将我们的算法与目前可用的生物标记物测试相结合，每种癌症可能会有30名年龄较大的患者和400名年轻患者被确定为“潜在患者”，并对大约60%的肿瘤进行早期诊断。在进一步的工作后，这种方法可以应用于初级保健环境，并有可能与非侵入性生物标记物检测一起使用，以增加早期诊断。这将导致更多的患者在这种毁灭性的疾病中幸存下来。
Pancreatic cancer (PC) represents a substantial public health burden. Pancreatic cancer patients have very low survival due to the difficulty of identifying cancers early when the tumour is localised to the site of origin and treatable. Recent progress has been made in identifying biomarkers for PC in the blood and urine, but these cannot be used for population-based screening as this would be prohibitively expensive and potentially harmful. We conducted a case-control study using prospectively-collected electronic health records from primary care individually-linked to cancer registrations. Our cases were comprised of 1,139 patients, aged 15–99 years, diagnosed with pancreatic cancer between January 1, 2005 and June 30, 2009. Each case was age-, sex- and diagnosis time-matched to four non-pancreatic (cancer patient) controls. Disease and prescription codes for the 24 months prior to diagnosis were used to identify 57 individual symptoms. Using a machine learning approach, we trained a logistic regression model on 75% of the data to predict patients who later developed PC and tested the model’s performance on the remaining 25%. We were able to identify 41.3% of patients < = 60 years at ‘high risk’ of developing pancreatic cancer up to 20 months prior to diagnosis with 72.5% sensitivity, 59% specificity and, 66% AUC. 43.2% of patients >60 years were similarly identified at 17 months, with 65% sensitivity, 57% specificity and, 61% AUC. We estimate that combining our algorithm with currently available biomarker tests could result in 30 older and 400 younger patients per cancer being identified as ‘potential patients’, and the earlier diagnosis of around 60% of tumours. After further work this approach could be applied in the primary care setting and has the potential to be used alongside a non-invasive biomarker test to increase earlier diagnosis. This would result in a greater number of patients surviving this devastating disease.
登录
查看更多内容
DOI：
10.1158/1078-0432.ccr-14-0365
发表时间：
2015-02-01
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
O'Brien DP;Sandanayake NS;Jenkinson C;Gentry-Maharaj A;Apostolidou S;Fourkala EO;Camuzeaux S;Blyuss O;Gunu R;Dawnay A;Zaikin A;Smith RC;Jacobs IJ;Menon U;Costello E;Pereira SP;Timms JF
通讯作者：
Timms JF
影响因子：
3.8
作者：
Daoud, Afra Z.;Mulholland, Eoghan J.;McCarthy, Helen O.
通讯作者：
McCarthy, Helen O.
DOI：
10.1158/1078-0432.ccr-14-2467
发表时间：
2015-08-01
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Radon TP;Massat NJ;Jones R;Alrawashdeh W;Dumartin L;Ennis D;Duffy SW;Kocher HM;Pereira SP;Guarner posthumous L;Murta-Nascimento C;Real FX;Malats N;Neoptolemos J;Costello E;Greenhalf W;Lemoine NR;Crnogorac-Jurcevic T
通讯作者：
Crnogorac-Jurcevic T
影响因子：
8.8
作者：
Mitry, E.;Rachet, B.;Coleman, M. P.
通讯作者：
Coleman, M. P.
影响因子：
12.6
作者：
Holly, Elizabeth A.;Chaliha, Indranushi;Gautam, Manjushree
通讯作者：
Gautam, Manjushree