1
|
Talebi R, Celis-Morales CA, Akbari A, Talebi A, Borumandnia N, Pourhoseingholi MA. Machine learning-based classifiers to predict metastasis in colorectal cancer patients. Front Artif Intell 2024; 7:1285037. [PMID: 38327669 PMCID: PMC10847339 DOI: 10.3389/frai.2024.1285037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Accepted: 01/03/2024] [Indexed: 02/09/2024] Open
Abstract
Background The increasing prevalence of colorectal cancer (CRC) in Iran over the past three decades has made it a key public health burden. This study aimed to predict metastasis in CRC patients using machine learning (ML) approaches in terms of demographic and clinical factors. Methods This study focuses on 1,127 CRC patients who underwent appropriate treatments at Taleghani Hospital, a tertiary care facility. The patients were divided into training and test datasets in an 80:20 ratio. Various ML methods, including Naive Bayes (NB), random rorest (RF), support vector machine (SVM), neural network (NN), decision tree (DT), and logistic regression (LR), were used for predicting metastasis in CRC patients. Model performance was evaluated using 5-fold cross-validation, reporting sensitivity, specificity, the area under the curve (AUC), and other indexes. Results Among the 1,127 patients, 183 (16%) had experienced metastasis. In the predictionof metastasis, both the NN and RF algorithms had the highest AUC, while SVM ranked third in both the original and balanced datasets. The NN and RF algorithms achieved the highest AUC (100%), sensitivity (100% and 100%, respectively), and accuracy (99.2% and 99.3%, respectively) on the balanced dataset, followed by the SVM with an AUC of 98.8%, a sensitivity of 97.5%, and an accuracy of 97%. Moreover, lower false negative rate (FNR), false positive rate (FPR), and higher negative predictive value (NPV) can be confirmed by these two methods. The results also showed that all methods exhibited good performance in the test datasets, and the balanced dataset improved the performance of most ML methods. The most important variables for predicting metastasis were the tumor stage, the number of involved lymph nodes, and the treatment type. In a separate analysis of patients with tumor stages I-III, it was identified that tumor grade, tumor size, and tumor stage are the most important features. Conclusion This study indicated that NN and RF were the best among ML-based approaches for predicting metastasis in CRC patients. Both the tumor stage and the number of involved lymph nodes were considered the most important features.
Collapse
Affiliation(s)
- Raheleh Talebi
- Department of Pure Mathematics, Lecturer of Mathematics at Architecture and Computer Engineering Department, University of Applied Sciences and Technology (Unit 10), Tehran, Iran
| | - Carlos A. Celis-Morales
- School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, United Kingdom
- Human Performance Laboratory, Education, Physical Activity and Health Research Unit, Universidad Católica del Maule, Talca, Chile
| | - Abolfazl Akbari
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Atefeh Talebi
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
- British Heart Foundation Cardiovascular Research Centre, University of Glasgow, Glasgow, United Kingdom
| | - Nasrin Borumandnia
- Urology and Nephrology Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mohamad Amin Pourhoseingholi
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| |
Collapse
|
2
|
Gallois C, Shi Q, Meyers JP, Iveson T, Alberts SR, de Gramont A, Sobrero AF, Haller DG, Oki E, Shields AF, Goldberg RM, Kerr R, Lonardi S, Yothers G, Kelly C, Boukovinas I, Labianca R, Sinicrope FA, Souglakos I, Yoshino T, Meyerhardt JA, André T, Papamichael D, Taieb J. Prognostic Impact of Early Treatment and Oxaliplatin Discontinuation in Patients With Stage III Colon Cancer: An ACCENT/IDEA Pooled Analysis of 11 Adjuvant Trials. J Clin Oncol 2023; 41:803-815. [PMID: 36306483 DOI: 10.1200/jco.21.02726] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Revised: 07/08/2022] [Accepted: 08/30/2022] [Indexed: 11/06/2022] Open
Abstract
PURPOSE Oxaliplatin-based adjuvant chemotherapy in patients with stage III colon cancer (CC) for 6 months remains a standard in high-risk stage III patients. Data are lacking as to whether early discontinuation of all treatment (ETD) or early discontinuation of oxaliplatin (EOD) could worsen the prognosis. MATERIALS AND METHODS We studied the prognostic impact of ETD and EOD in patients with stage III CC from the ACCENT/IDEA databases, where patients were planned to receive 6 months of infusional fluorouracil, leucovorin, and oxaliplatin or capecitabine plus oxaliplatin. ETD was defined as discontinuation of treatment and EOD as discontinuation of oxaliplatin only before patients had received a maximum of 75% of planned cycles. Association between ETD/EOD and overall survival and disease-free survival (DFS) were assessed by Cox models adjusted for established prognostic factors. RESULTS Analysis of ETD and EOD included 10,447 (20.9% with ETD) and 7,243 (18.8% with EOD) patients, respectively. Compared with patients without ETD or EOD, patients with ETD or EOD were statistically more likely to be women, with Eastern Cooperative Oncology Group performance status ≥ 1, and for ETD, older with a lower body mass index. In multivariable analyses, ETD was associated with a decrease in disease-free survival and overall survival (hazard ratio [HR], 1.61, P < .001 and HR, 1.73, P < .001), which was not the case for EOD (HR, 1.07, P = .3 and HR, 1.13, P = .1). However, patients who received < 50% of the planned cycles of oxaliplatin had poorer outcomes. CONCLUSION In patients treated with 6 months of oxaliplatin-based chemotherapy for stage III CC, ETD was associated with poorer oncologic outcomes. However, this was not the case for EOD. These data favor discontinuing oxaliplatin while continuing fluoropyrimidine in individuals with significant neurotoxicity having received > 50% of the planned 6-month chemotherapy.
Collapse
Affiliation(s)
- Claire Gallois
- Paris-Cité University, Department of Gastroenterology and Digestive Oncology, Georges Pompidou European Hospital, SIRIC CARPEM, Paris, France
| | - Qian Shi
- Department of Health Science Research, Mayo Clinic, Rochester, MN
| | - Jeffrey P Meyers
- Department of Health Science Research, Mayo Clinic, Rochester, MN
| | - Timothy Iveson
- Department of Medical Oncology, University of Southampton, Southampton, United Kingdom
| | | | - Aimery de Gramont
- Department of Medical Oncology, Franco-British Institute, Levallois-Perret, France
| | | | - Daniel G Haller
- Division of Hematology/Oncology, University of Pennsylvania, Philadelphia, PA
| | - Eiji Oki
- Department of Surgery and Science, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | | | - Richard M Goldberg
- West Virginia University Cancer Institute and the Mary Babb Randolph Cancer Center, Morgantown, WV
| | - Rachel Kerr
- Department of Oncology, Oxford University, Oxford, United Kingdom
| | - Sara Lonardi
- Medical Oncology Unit 1, Clinical and Experimental Oncology Department, Veneto Institute of Oncology IRCCS, Padua, Italy
| | - Greg Yothers
- Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA
| | - Caroline Kelly
- Cancer Research UK Clinical Trials Unit, Institute of Cancer Sciences, University of Glasgow, Glasgow, United Kingdom
| | | | | | | | - Ioannis Souglakos
- Department of Medical Oncology, University Hospital of Heraklion, Heraklion, Greece
| | - Takayuki Yoshino
- Department of Gastrointestinal Oncology, National Cancer Center Hospital East, Kashiwa, Japan
| | | | - Thierry André
- Sorbonne Université, Department of Medical Oncology, Hôpital Saint-Antoine, Paris, France
| | | | - Julien Taieb
- Paris-Cité University, Department of Gastroenterology and Digestive Oncology, Georges Pompidou European Hospital, SIRIC CARPEM, Paris, France
| |
Collapse
|
3
|
Hayes CJ, Cucciare MA, Martin BC, Hudson TJ, Bush K, Lo-Ciganic W, Yu H, Charron E, Gordon AJ. Using data science to improve outcomes for persons with opioid use disorder. Subst Abus 2022; 43:956-963. [PMID: 35420927 PMCID: PMC9705076 DOI: 10.1080/08897077.2022.2060446] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
Medication treatment for opioid use disorder (MOUD) is an effective evidence-based therapy for decreasing opioid-related adverse outcomes. Effective strategies for retaining persons on MOUD, an essential step to improving outcomes, are needed as roughly half of all persons initiating MOUD discontinue within a year. Data science may be valuable and promising for improving MOUD retention by using "big data" (e.g., electronic health record data, claims data mobile/sensor data, social media data) and specific machine learning techniques (e.g., predictive modeling, natural language processing, reinforcement learning) to individualize patient care. Maximizing the utility of data science to improve MOUD retention requires a three-pronged approach: (1) increasing funding for data science research for OUD, (2) integrating data from multiple sources including treatment for OUD and general medical care as well as data not specific to medical care (e.g., mobile, sensor, and social media data), and (3) applying multiple data science approaches with integrated big data to provide insights and optimize advances in the OUD and overall addiction fields.
Collapse
Affiliation(s)
- Corey J Hayes
- Department of Biomedical Informatics, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
- Central Arkansas Veterans Healthcare System, Center for Mental Healthcare and Outcomes Research, North Little Rock, Arkansas, USA
| | - Michael A Cucciare
- Central Arkansas Veterans Healthcare System, Center for Mental Healthcare and Outcomes Research, North Little Rock, Arkansas, USA
- Center for Health Services Research, Department of Psychiatry, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
- Veterans Affairs South Central Mental Illness Research, Education and Clinical Center, Central Arkansas Veterans Healthcare System, North Little Rock, Arkansas, USA
| | - Bradley C Martin
- Division of Pharmaceutical Evaluation and Policy, College of Pharmacy, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Teresa J Hudson
- Central Arkansas Veterans Healthcare System, Center for Mental Healthcare and Outcomes Research, North Little Rock, Arkansas, USA
- Center for Health Services Research, Department of Psychiatry, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Keith Bush
- Brain Imaging Research Center, Department of Psychiatry, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - Weihsuan Lo-Ciganic
- Department of Pharmaceutical Outcomes and Policy, College of Pharmacy, University of Florida, Gainesville, Florida, USA
- Center for Drug Evaluation and Safety (CoDES), College of Pharmacy, University of Florida, Gainesville, Florida, USA
| | - Hong Yu
- Department of Computer Science, Kennedy College of Sciences, University of Massachusetts Lowell, Lowell, Florida, USA
- Center for Healthcare Organization and Implementation Research, VA Bedford Healthcare System, Bedford, MA
| | - Elizabeth Charron
- Program for Addiction Research, Clinical Care, Knowledge, and Advocacy (PARCKA), Division of Epidemiology, Department of Medicine, School of Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Adam J Gordon
- Program for Addiction Research, Clinical Care, Knowledge, and Advocacy (PARCKA), Division of Epidemiology, Department of Medicine, School of Medicine, University of Utah, Salt Lake City, Utah, USA
- Informatics, Decision-Enhancement and Analytic Sciences (IDEAS) Center, VA Salt Lake City Healthcare System, Salt Lake City, Utah, USA
| |
Collapse
|
4
|
Bektaş M, Tuynman JB, Costa Pereira J, Burchell GL, van der Peet DL. Machine Learning Algorithms for Predicting Surgical Outcomes after Colorectal Surgery: A Systematic Review. World J Surg 2022; 46:3100-3110. [PMID: 36109367 PMCID: PMC9636121 DOI: 10.1007/s00268-022-06728-1] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/22/2022] [Indexed: 01/14/2023]
Abstract
BACKGROUND Machine learning (ML) has been introduced in various fields of healthcare. In colorectal surgery, the role of ML has yet to be reported. In this systematic review, an overview of machine learning models predicting surgical outcomes after colorectal surgery is provided. METHODS Databases PubMed, EMBASE, Cochrane, and Web of Science were searched for studies using machine learning models for patients undergoing colorectal surgery. To be eligible for inclusion, studies needed to apply machine learning models for patients undergoing colorectal surgery. Absence of machine learning or colorectal surgery or studies reporting on reviews, children, study abstracts were excluded. The Probast risk of bias tool was used to evaluate the methodological quality of machine learning models. RESULTS A total of 1821 studies were analysed, resulting in the inclusion of 31 articles. A vast proportion of ML algorithms have been used to predict the course of disease and response to neoadjuvant chemoradiotherapy. Radiomics have been applied most frequently, along with predictive accuracies up to 91%. However, most studies included a retrospective study design without external validation or calibration. CONCLUSIONS Machine learning models have shown promising potential in predicting surgical outcomes after colorectal surgery. However, large-scale data is warranted to bridge the gap between calibration and external validation. Clinical implementation is needed to demonstrate the contribution of ML within daily practice.
Collapse
Affiliation(s)
- Mustafa Bektaş
- Department of Surgery, Amsterdam UMC Location Vrije Universiteit Amsterdam, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands
| | - Jurriaan B. Tuynman
- Department of Surgery, Amsterdam UMC Location Vrije Universiteit Amsterdam, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands
| | - Jaime Costa Pereira
- Department of Computer Science, Vrije Universiteit Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands
| | - George L. Burchell
- Medical Library, Amsterdam UMC Location Vrije Universiteit Amsterdam, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands
| | - Donald L. van der Peet
- Department of Surgery, Amsterdam UMC Location Vrije Universiteit Amsterdam, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands
| |
Collapse
|