RESUMO
Objective: Colorectal cancer (CRC) is one of the most prevalent cancers worldwide. A considerable percentage of patients who undergo surgery with curative intent will experience cancer recurrence. Early identification of individuals with a higher risk of recurrence is crucial for healthcare professionals to intervene promptly and devise appropriate treatment strategies. In this study, we developed prognostic models for CRC recurrence using machine learning models on a limited number of CEA measurements. Method: A dataset of 1927 patients diagnosed with Stage I-III CRC and referred to Zuyderland Hospital for surgery between 2008 and 2016 was utilized. Machine learning models were trained using this comprehensive dataset, which included demographic details, clinicopathological factors, and serial measurements of Carcinoembryonic Antigen (CEA). In this study, the predictive performance of these models was assessed, and the key prognostic factors influencing colorectal cancer (CRC) recurrence were pinpointed. Result: Among the evaluated models, the gradient boosting classifier demonstrated superior performance, achieving an Area Under the Curve (AUC) score of 0.81 and a balanced accuracy rate of 0.73. Recurrence prediction was shown to be feasible with an AUC of 0.71 when using only five post-operative CEA measurements. Furthermore, key factors influencing recurrence were identified and elucidated. Conclusion: This study shows the transformative role of machine learning in recurrence prediction for CRC, particularly by investigating the minimum number of CEA measurements required for effective recurrence prediction. This approach not only contributes to the optimization of clinical workflows but also facilitates the development of more effective, individualized treatment plans, thereby laying the groundwork for future advancements in this area. Future directions involve validating these models in larger and more diverse cohorts. Building on these efforts, our ultimate goal is to develop a risk-based follow-up strategy that can improve patient outcomes and enhance healthcare efficiency.
RESUMO
OBJECTIVE: This study evaluated the nationwide trends in care and accompanied postoperative outcomes for patients with distal esophageal and gastro-esophageal junction cancer. SUMMARY OF BACKGROUND DATA: The introduction of transthoracic esophagectomy, minimally invasive surgery, and neo-adjuvant chemo(radio)therapy changed care for patients with esophageal cancer. METHODS: Patients after elective transthoracic and transhiatal esophagectomy for distal esophageal or gastroesophageal junction carcinoma in the Netherlands between 2007-2016 were included. The primary aim was to evaluate trends in both care and postoperative outcomes for the included patients. Additionally, postoperative outcomes after transthoracic and tran-shiatal esophagectomy were compared, stratified by time periods. RESULTS: Among 4712 patients included, 74% had distal esophageal tumors and 87% had adenocarcinomas. Between 2007 and 2016, the proportion of transthoracic esophagectomy increased from 41% to 81%, and neo-adjuvant treatment and minimally invasive esophagectomy increased from 31% to 96%, and from 7% to 80%, respectively. Over this 10-year period, postoperative outcomes improved: postoperative morbidity decreased from 66.6% to 61.8% ( P = 0.001), R0 resection rate increased from 90.0% to 96.5% (P <0.001), median lymph node harvest increased from 15 to 19 ( P <0.001), and median survival increased from 35 to 41 months ( P = 0.027). CONCLUSION: In this nationwide cohort, a transition towards more neo-adju-vant treatment, transthoracic esophagectomy and minimally invasive surgery was observed over a 10-year period, accompanied by decreased postoperative morbidity, improved surgical radicality and lymph node harvest, and improved survival.
