RESUMO
OBJECTIVES: Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate. MATERIALS AND METHODS: Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence. RESULTS: Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence. CONCLUSIONS: Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.
Assuntos
Carcinoma Ductal Pancreático , Neoplasias Pancreáticas , Humanos , Inteligência Artificial , Carcinoma Ductal Pancreático/diagnóstico por imagem , Carcinoma Ductal Pancreático/tratamento farmacológico , Carcinoma Ductal Pancreático/cirurgia , Neoplasias Pancreáticas/tratamento farmacológico , Neoplasias Pancreáticas/cirurgia , Prognóstico , Aprendizado de Máquina , Estudos RetrospectivosRESUMO
BACKGROUND: We evaluated the association of prostate volume (PV) with the efficacy and safety of transurethral enucleation with bipolar energy (TUEB) for treatment of benign prostatic hyperplasia (BPH). METHODS: We retrospectively evaluated data from 180 patients with symptomatic BPH who underwent TUEB between 2008 and 2015. Efficacy was assessed by perioperative changes in international prostate symptom score (IPSS), Quality of Life Score (QOLS), maximum flow rate on uroflowmetry (Qmax), and serum prostate-specific antigen level (PSA), which were recorded at 3 months postoperatively. Safety was assessed by perioperative incidence of adverse events (AEs). AEs were recorded up to 2 years after surgery. Patients were divided into two groups based on PV as the standard group (SG; PV < 80 mL) and large group (LG; PV ≥ 80 mL). RESULTS: A total of 132 (73%) patients were grouped as the SG, and 48 (27%) were grouped as the LG. No significant differences between the groups were observed in the preoperative variables age, IPSS, and QOLS. However, the LG had a significantly larger PV and higher serum PSA levels. Analysis of surgical outcomes revealed that postoperative changes in IPSS, QOLS, Qmax, serum PSA, serum sodium, and hemoglobin levels did not differ significantly between groups. However, LG had a significantly longer operative time and heavier specimen weight. The rates of early complications, including hyponatremia and blood transfusion, and late complications after surgery did not differ between the groups. CONCLUSION: The present findings suggest that TUEB is safe and effective for treatment of BPH, regardless of PV.