ABSTRACT
BACKGROUND AND OBJECTIVES: Deep learning models (DLMs) are applied across domains of health sciences to generate meaningful predictions. DLMs make use of neural networks to generate predictions from discrete data inputs. This study employs DLM on prechemotherapy cross-sectional imaging to predict patients' response to neoadjuvant chemotherapy. METHODS: Adult patients with colorectal liver metastasis who underwent surgery after neoadjuvant chemotherapy were included. A DLM was trained on computed tomography images using attention-based multiple-instance learning. A logistic regression model incorporating clinical parameters of the Fong clinical risk score was used for comparison. Both model performances were benchmarked against the Response Evaluation Criteria in Solid Tumors criteria. A receiver operating curve was created and resulting area under the curve (AUC) was determined. RESULTS: Ninety-five patients were included, with 33,619 images available for study inclusion. Ninety-five percent of patients underwent 5-fluorouracil-based chemotherapy with oxaliplatin and/or irinotecan. Sixty percent of the patients were categorized as chemotherapy responders (30% reduction in tumor diameter). The DLM had an AUC of 0.77. The AUC for the clinical model was 0.41. CONCLUSIONS: Image-based DLM for prediction of response to neoadjuvant chemotherapy in patients with colorectal cancer liver metastases was superior to a clinical-based model. These results demonstrate potential to identify nonresponders to chemotherapy and guide select patients toward earlier curative resection.
Subject(s)
Antineoplastic Combined Chemotherapy Protocols , Colorectal Neoplasms , Deep Learning , Liver Neoplasms , Neoadjuvant Therapy , Humans , Colorectal Neoplasms/pathology , Colorectal Neoplasms/drug therapy , Colorectal Neoplasms/diagnostic imaging , Liver Neoplasms/secondary , Liver Neoplasms/diagnostic imaging , Liver Neoplasms/drug therapy , Liver Neoplasms/surgery , Male , Female , Middle Aged , Aged , Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Tomography, X-Ray Computed , Fluorouracil/administration & dosage , Fluorouracil/therapeutic use , Chemotherapy, Adjuvant , Oxaliplatin/administration & dosage , Oxaliplatin/therapeutic use , Adult , Follow-Up Studies , Retrospective StudiesABSTRACT
Advances in perioperative care have increased the frequency of surgical intervention performed on the very elderly (≥80 years). This study aims to investigate the impact of Enhanced Recovery After Surgery (ERAS) on outcomes for octogenarians after major hepatopancreatobiliary (HPB) surgery. Patients ≥80 years old in a single HPB ERAS program (September 2015-July 2018) were prospectively tracked in the ERAS Interactive Audit System (EIAS). Postoperative length of stay (LOS) as well as 30-day major complications, readmissions, and mortality were compared to a pre-ERAS octogenarian control. Since ERAS implementation, octogenarians comprised 7.3% (27 of 370) of patients who underwent pancreaticoduodenectomy (n=17), distal pancreatectomy (n=7), or hepatectomy (n=3). Thirty-day readmissions decreased after ERAS implementation (50% to 15%, P=.037). Thirty-day major complications, mortality, and LOS were similar with 64% median protocol compliance. ERAS for octogenarians in HPB surgery is safe and may contribute to more sustainable recovery resulting in reduced readmissions.
