亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Developing machine learning algorithms for dynamic estimation of progression during active surveillance for prostate cancer

比例危险模型 计算机科学 机器学习 前列腺癌 聚类分析 人工智能 布里氏评分 事件(粒子物理) 基线(sea) 医学 癌症 内科学 量子力学 海洋学 物理 地质学
作者
Changhee Lee,Alexander Light,Evgeny S. Saveliev,Mihaela van der Schaar,Vincent J. Gnanapragasam
出处
期刊:npj digital medicine [Nature Portfolio]
卷期号:5 (1) 被引量:12
标识
DOI:10.1038/s41746-022-00659-w
摘要

Active Surveillance (AS) for prostate cancer is a management option that continually monitors early disease and considers intervention if progression occurs. A robust method to incorporate "live" updates of progression risk during follow-up has hitherto been lacking. To address this, we developed a deep learning-based individualised longitudinal survival model using Dynamic-DeepHit-Lite (DDHL) that learns data-driven distribution of time-to-event outcomes. Further refining outputs, we used a reinforcement learning approach (Actor-Critic) for temporal predictive clustering (AC-TPC) to discover groups with similar time-to-event outcomes to support clinical utility. We applied these methods to data from 585 men on AS with longitudinal and comprehensive follow-up (median 4.4 years). Time-dependent C-indices and Brier scores were calculated and compared to Cox regression and landmarking methods. Both Cox and DDHL models including only baseline variables showed comparable C-indices but the DDHL model performance improved with additional follow-up data. With 3 years of data collection and 3 years follow-up the DDHL model had a C-index of 0.79 (±0.11) compared to 0.70 (±0.15) for landmarking Cox and 0.67 (±0.09) for baseline Cox only. Model calibration was good across all models tested. The AC-TPC method further discovered 4 distinct outcome-related temporal clusters with distinct progression trajectories. Those in the lowest risk cluster had negligible progression risk while those in the highest cluster had a 50% risk of progression by 5 years. In summary, we report a novel machine learning approach to inform personalised follow-up during active surveillance which improves predictive power with increasing data input over time.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
3秒前
yizhiyang发布了新的文献求助10
5秒前
情怀的应助被白丶魈白采纳,获得10
8秒前
FIGGIEKIO发布了新的文献求助10
8秒前
超级哑铃完成签到,获得积分10
9秒前
10秒前
14秒前
19秒前
天天快乐的应助被科研通管家采纳,获得10
19秒前
香蕉觅云的应助被飘逸的雪珍采纳,获得10
27秒前
高高的念之完成签到 ,获得积分10
27秒前
Jasper的应助被白丶魈白采纳,获得10
29秒前
34秒前
玩命的芸遥完成签到,获得积分10
35秒前
35秒前
38秒前
40秒前
高大凌旋完成签到,获得积分10
41秒前
Harding完成签到,获得积分10
42秒前
45秒前
乐乐的应助被白丶魈白采纳,获得10
49秒前
辛勤寻凝发布了新的文献求助10
50秒前
wanci的应助被醋醋采纳,获得10
1分钟前
爆米花的应助被sugar采纳,获得10
1分钟前
1分钟前
Jasper的应助被FIGGIEKIO采纳,获得10
1分钟前
1分钟前
小二郎的应助被白丶魈白采纳,获得10
1分钟前
upcomingbias发布了新的文献求助30
1分钟前
苗条的奇异果完成签到,获得积分10
1分钟前
和谐早晨完成签到,获得积分10
1分钟前
醋醋完成签到,获得积分10
1分钟前
skycool完成签到,获得积分10
1分钟前
1分钟前
顾矜的应助被白丶魈白采纳,获得10
1分钟前
1分钟前
1分钟前
冰糖葫芦不加芝麻完成签到,获得积分10
1分钟前
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8195050
求助须知:如何正确求助?哪些是违规求助? 9580818
关于积分的说明 21872754
捐赠科研通 7794886
什么是DOI,文献DOI怎么找? 3437922
关于科研通互助平台的介绍 2561204
邀请新用户注册赠送积分活动 2484579