Comparing Active Surveillance and Watchful Waiting With Radical Treatment Using Machine Learning Models Among Patients With Prostate Cancer
PURPOSE: In 2021, 59.6% of low-risk patients with prostate cancer were under active surveillance (AS) as their first course of treatment. However, few studies have investigated AS and watchful waiting (WW) separately. The objectives of this study were to develop and validate a population-level machine learning model for distinguishing AS and WW in the conservative treatment group, and to investigate initial cancer management trends from 2004 to 2017 and the risk of chronic diseases among patients with prostate cancer with different treatment modalities.
METHODS: In a cohort of 18,134 patients with prostate adenocarcinoma diagnosed between 2004 and 2017, 1,926 patients with available AS/WW information were analyzed using machine learning algorithms with 10-fold cross-validation. Models were evaluated using performance metrics and Brier score. Cox proportional hazard models were used to estimate hazard ratios for chronic disease risk.
RESULTS: Logistic regression models achieved a test area under the receiver operating curve of 0.73, F-score of 0.79, accuracy of 0.71, and Brier score of 0.29, demonstrating good calibration, precision, and recall values. We noted a sharp increase in AS use between 2004 and 2016 among patients with low-risk prostate cancer and a moderate increase among intermediate-risk patients between 2008 and 2017. Compared with the AS group, radical treatment was associated with a lower risk of prostate cancer-specific mortality but higher risks of Alzheimer disease, anemia, glaucoma, hyperlipidemia, and hypertension.
CONCLUSION: A machine learning approach accurately distinguished AS and WW groups in conservative treatment in this decision analytical model study. Our results provide insight into the necessity to separate AS and WW in population-based studies.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:7 |
|---|---|
| Enthalten in: |
JCO clinical cancer informatics - 7(2023) vom: 29. Sept., Seite e2300083 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Hu, Siqi [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 23.11.2023 Date Revised 30.01.2024 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1200/CCI.23.00083 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM364799420 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM364799420 | ||
| 003 | DE-627 | ||
| 005 | 20240130232103.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1200/CCI.23.00083 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1275.xml |
| 035 | |a (DE-627)NLM364799420 | ||
| 035 | |a (NLM)37988640 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Hu, Siqi |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Comparing Active Surveillance and Watchful Waiting With Radical Treatment Using Machine Learning Models Among Patients With Prostate Cancer |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 23.11.2023 | ||
| 500 | |a Date Revised 30.01.2024 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a PURPOSE: In 2021, 59.6% of low-risk patients with prostate cancer were under active surveillance (AS) as their first course of treatment. However, few studies have investigated AS and watchful waiting (WW) separately. The objectives of this study were to develop and validate a population-level machine learning model for distinguishing AS and WW in the conservative treatment group, and to investigate initial cancer management trends from 2004 to 2017 and the risk of chronic diseases among patients with prostate cancer with different treatment modalities | ||
| 520 | |a METHODS: In a cohort of 18,134 patients with prostate adenocarcinoma diagnosed between 2004 and 2017, 1,926 patients with available AS/WW information were analyzed using machine learning algorithms with 10-fold cross-validation. Models were evaluated using performance metrics and Brier score. Cox proportional hazard models were used to estimate hazard ratios for chronic disease risk | ||
| 520 | |a RESULTS: Logistic regression models achieved a test area under the receiver operating curve of 0.73, F-score of 0.79, accuracy of 0.71, and Brier score of 0.29, demonstrating good calibration, precision, and recall values. We noted a sharp increase in AS use between 2004 and 2016 among patients with low-risk prostate cancer and a moderate increase among intermediate-risk patients between 2008 and 2017. Compared with the AS group, radical treatment was associated with a lower risk of prostate cancer-specific mortality but higher risks of Alzheimer disease, anemia, glaucoma, hyperlipidemia, and hypertension | ||
| 520 | |a CONCLUSION: A machine learning approach accurately distinguished AS and WW groups in conservative treatment in this decision analytical model study. Our results provide insight into the necessity to separate AS and WW in population-based studies | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Chang, Chun-Pin |e verfasserin |4 aut | |
| 700 | 1 | |a Snyder, John |e verfasserin |4 aut | |
| 700 | 1 | |a Deshmukh, Vikrant |e verfasserin |4 aut | |
| 700 | 1 | |a Newman, Michael |e verfasserin |4 aut | |
| 700 | 1 | |a Date, Ankita |e verfasserin |4 aut | |
| 700 | 1 | |a Galvao, Carlos |e verfasserin |4 aut | |
| 700 | 1 | |a Porucznik, Christina A |e verfasserin |4 aut | |
| 700 | 1 | |a Gren, Lisa H |e verfasserin |4 aut | |
| 700 | 1 | |a Sanchez, Alejandro |e verfasserin |4 aut | |
| 700 | 1 | |a Lloyd, Shane |e verfasserin |4 aut | |
| 700 | 1 | |a Haaland, Benjamin |e verfasserin |4 aut | |
| 700 | 1 | |a O'Neil, Brock |e verfasserin |4 aut | |
| 700 | 1 | |a Hashibe, Mia |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t JCO clinical cancer informatics |d 2017 |g 7(2023) vom: 29. Sept., Seite e2300083 |w (DE-627)NLM275406369 |x 2473-4276 |7 nnns |
| 773 | 1 | 8 | |g volume:7 |g year:2023 |g day:29 |g month:09 |g pages:e2300083 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1200/CCI.23.00083 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 7 |j 2023 |b 29 |c 09 |h e2300083 | ||