Artificial Intelligence-Based Prediction of Recurrence after Curative Resection for Colorectal Cancer from Digital Pathological Images

Nakanishi, Ryota; Morooka, Ken’ichi; Omori, Kazuki; Toyota, Satoshi; Tanaka, Yasushi; Hasuda, Hirofumi; Koga, Naomichi; Nonaka, Kentaro; Hu, Qingjiang; Nakaji, Yu; Nakanoko, Tomonori; Ando, Koji; Ota, Mitsuhiko; Kimura, Yasue; Oki, Eiji; Oda, Yoshinao; Yoshizumi, Tomoharu

doi:10.1245/s10434-022-12926-x

Cited by 7 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tumour recurrences develop in 3%–38% of individuals with CRC within 3 years after a resection with curative intent, depending on stage at diagnosis 9 . Risk of recurrence has been reported to be higher in men than in women, and in people with rectal cancer compared to people with colon cancer 9,10 . Furthermore, the localisation of recurrences also seems to differ per location of the primary tumour, 9,11 and may differ for men and women, 11 implying different underlying mechanisms are involved leading to cancer recurrence.…”

Section: Introductionmentioning

confidence: 99%

Associations between low‐ and high‐fat dairy intake and recurrence risk in people with stage I–III colorectal cancer differ by sex and primary tumour location

van Lanen,

Kok,

Wesselink

et al. 2024

Intl Journal of Cancer

View full text Add to dashboard Cite

We previously demonstrated that intake of low‐fat dairy, but not high‐fat dairy, was associated with a decreased colorectal cancer (CRC) recurrence risk. These risks, however, may differ by sex, primary tumour location, and disease stage. Combining data from two similar prospective cohort studies of people with stage I–III CRC enabled these subgroup analyses. Participants completed a food frequency questionnaire at diagnosis (n = 2283). We examined associations between low‐ and high‐fat dairy intake and recurrence risk using multivariable Cox proportional hazard models, stratified by sex, and primary tumour location (colon and rectum), and disease stage (I/II and III). Upper quartiles were compared to lower quartiles of intake, and recurrence was defined as a locoregional recurrence and/or metastasis. During a median follow‐up of 5.0 years, 331 recurrences were detected. A higher intake of low‐fat dairy was associated with a reduced risk of recurrence (hazard ratio [HR]: 0.60, 95% confidence interval [CI]: 0.43–0.83), which seemed more pronounced in men (HR: 0.51, 95% CI: 0.34–0.77) than in women (HR: 0.84, 95% CI: 0.47–1.49). A higher intake of high‐fat dairy was associated with an increased risk of recurrence in participants with colon cancer (HR: 1.60, 95% CI: 1.03–2.50), but not rectal cancer (HR: 0.88, 95% CI: 0.54–1.45). No differences in associations were observed between strata of disease stage. Concluding, our findings imply that dietary advice regarding low‐fat dairy intake may be especially important for men with CRC, and that dietary advice regarding high‐fat dairy intake may be specifically important in people with colon cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Associations between low‐ and high‐fat dairy intake and recurrence risk in people with stage I–III colorectal cancer differ by sex and primary tumour location

van Lanen,

Kok,

Wesselink

et al. 2024

Intl Journal of Cancer

View full text Add to dashboard Cite

show abstract

“…Machine learning based algorithms, which forms the basis of artificial intelligence, have been developed over the past decades for predicting disease risk, prognosis, diagnosis, and even the course of treatment in healthcare settings [4]. Further, recent studies have reported the feasibility and utility of artificial intelligence-based predicting the recurrence of several malignant diseases, including colorectal, breast, and gastric cancer [5][6][7][8][9][10]. However, in colorectal cancer, only a few studies employing machine-learning methodologies focus exclusively on recurrence prediction for rectal cancer without including colon cancer.…”

Section: Introductionmentioning

confidence: 99%

Machine learning based prediction of recurrence after curative resection for rectal cancer

Jeon,

Kim,

Jeon

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Purpose Patients with rectal cancer without distant metastases are typically treated with radical surgery. Post curative resection, several factors can affect tumor recurrence. This study aimed to analyze factors related to rectal cancer recurrence after curative resection using different machine learning techniques. Methods Consecutive patients who underwent curative surgery for rectal cancer between 2004 and 2018 at Gil Medical Center were included. Patients with stage IV disease, colon cancer, anal cancer, other recurrent cancer, emergency surgery, or hereditary malignancies were excluded from the study. The Synthetic Minority Oversampling Technique with Tomek link (SMOTETomek) technique was used to compensate for data imbalance between recurrent and no-recurrent groups. Four machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), and Extreme gradient boosting (XGBoost), were used to identify significant factors. To overfit and improve the model performance, feature importance was calculated using the permutation importance technique. Results A total of 3320 patients were included in the study. After exclusion, the total sample size of the study was 961 patients. The median follow-up period was 60.8 months (range:1.2–192.4). The recurrence rate during follow-up was 13.2% (n = 127). After applying the SMOTETomek method, the number of patients in both groups, recurrent and non-recurrent group were equalized to 667 patients. After analyzing for 16 variables, the top eight ranked variables {pathologic Tumor stage (pT), sex, concurrent chemoradiotherapy, pathologic Node stage (pN), age, postoperative chemotherapy, pathologic Tumor-Node-Metastasis stage (pTNM), and perineural invasion} were selected based on the order of permutational importance. The highest area under the curve (AUC) was for the SVM method (0.831). The sensitivity, specificity, and accuracy were found to be 0.692, 0.814, and 0.798, respectively. The lowest AUC was obtained for the XGBoost method (0.804), with a sensitivity, specificity, and accuracy of 0.308, 0.928, and 0.845, respectively. The variable with highest importance was pT as assessed through SVM, RF, and XGBoost (0.06, 0.12, and 0.13, respectively), whereas pTNM had the highest importance when assessed by LR (0.05). Conclusions In the current study, SVM showed the best AUC, and the most influential factor across all machine learning methods except LR was found to be pT. The rectal cancer patients who have a high pT stage during postoperative follow-up are need to be more close surveillance.

show abstract

Artificial Intelligence in Predicting Postoperative Surgical Complications

Bhattacharya,

Kumar

et al. 2024

Indian J Surg

View full text Add to dashboard Cite

Artificial Intelligence-Based Prediction of Recurrence after Curative Resection for Colorectal Cancer from Digital Pathological Images

Cited by 7 publications

References 40 publications

Associations between low‐ and high‐fat dairy intake and recurrence risk in people with stage I–III colorectal cancer differ by sex and primary tumour location

Associations between low‐ and high‐fat dairy intake and recurrence risk in people with stage I–III colorectal cancer differ by sex and primary tumour location

Machine learning based prediction of recurrence after curative resection for rectal cancer

Artificial Intelligence in Predicting Postoperative Surgical Complications

Contact Info

Product

Resources

About