Is Supervised machine learning algorithm comparative over nomograms in predicting biochemical recurrence after prostatectomy: a validation study
Principal Investigator
Name
Kheng Sit Lim
Degrees
M.D, M.Medicine
Institution
AiM Medical Pte Ltd
Position Title
Chief Medical Officer
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1533
Initial CDAS Request Approval
Apr 18, 2024
Title
Is Supervised machine learning algorithm comparative over nomograms in predicting biochemical recurrence after prostatectomy: a validation study
Summary
Our team conducted a study in 2021 utilizing a prospective Uro‐oncology registry, 18 clinicopathological parameters of 1130 consecutive patients who underwent Radical Proctectomy (RP) (2009–2018) were recorded. The team concluded that supervised machine learning models robustly predicted biochemical recurrence at 1-, 3-, and 5-years post‐RP and outperformed classical nomograms. That conclusion presented an additional exciting armamentarium that AI could facilitate tailored care provisions by identifying high‐risk prostate cancer patients who may benefit from early multimodality treatments (The Prostate. 2022;82:298–305). However, that result was yielded based on the data from south east Asia patients only. A validation study is required to find out if the same result will be found using PLCO Data.
Aim:
Aim:
Aims
To validate 3 Machine Learning models (Naive Bayes, random forest, and support vector machine) demonstrate good prediction of Biochemical recurrence at 1-, 3-, and 5- years.
Collaborators
Andrew Fang, MBBM, Family Physician, Doctor Anywhere
Tan Yuguang, MBBS, Consultant Urologist, Singapore General Hospital