ABSTRACT
BACKGROUND: We sought to assess the impact of telemedicine on healthcare utilization and medical expenditures among patients with a diagnosis of gastrointestinal (GI) cancer. METHODS: Patients with newly diagnosed GI cancer from 2013 to 2020 were identified from the IBM MarketScan database (IBM Watson Health) . Healthcare utilization, total medical outpatient insurance payments within 1 year post-diagnosis, and out-of-pocket (OOP) expenses among telemedicine users and non-users were assessed after propensity score matching (PSM). RESULTS: Among the 32,677 patients with GI cancer (esophageal, n = 1862, 5.7%; gastric, n = 2009, 6.1%; liver, n = 2929, 9.0%; bile duct, n = 597, 1.8%; pancreas, n = 3083, 9.4%; colorectal, n = 22,197, 67.9%), a total of 3063 (9.7%) utilized telemedicine. After PSM (telemedicine users, n = 3064; non-users, n = 3064), telemedicine users demonstrated a higher frequency of clinic visits (median: 5.0 days, IQR 4.0-7.0 vs non-users: 2.0 days, IQR 2.0-3.0, P < .001) and fewer potential days missed from daily activities (median: 7.5 days, IQR 4.5-12.5 vs non-users: 8.5 days, IQR 5.5-13.5, P < .001). Total medical spending per month and utilization of emergency room (ER) visits for telemedicine users were higher vs non-users (median: $10,658, IQR $5112-$18,528 vs non-users: $10,103, IQR $4628-$16,750; 46.8% vs 42.6%, both P < .01), whereas monthly OOP costs were comparable (median: $273, IQR $137-$449 for telemedicine users vs non-users: $268, IQR $142-$434, P = .625). CONCLUSION: Telemedicine utilization was associated with increased outpatient clinic visits yet reduced potential days missed from daily activities among patients with GI cancer. Telemedicine users tended to have more ER visits and total medical spending per month, although monthly OOP costs were comparable with non-users.
ABSTRACT
BACKGROUND AND AIM: Hepatocellular carcinoma (HCC) diagnosis mainly relies on its pathognomonic radiological profile, obviating the need for biopsy. The project of incorporating artificial intelligence (AI) techniques in HCC aims to improve the performance of image recognition. Herein, we thoroughly analyze and evaluate proposed AI models in the field of HCC diagnosis. METHODS: A comprehensive review of the literature was performed utilizing MEDLINE/PubMed and Web of Science databases with the end of search date being the 30th of September 2023. The MESH terms "Artificial Intelligence," "Liver Cancer," "Hepatocellular Carcinoma," "Machine Learning," and "Deep Learning" were searched in the title and/or abstract. All references of the obtained articles were also evaluated for any additional information. RESULTS: Our search resulted in 183 studies meeting our inclusion criteria. Across all diagnostic modalities, reported area under the curve (AUC) of most developed models surpassed 0.900. A B-mode US and a contrast-enhanced US model achieved AUCs of 0.947 and 0.957, respectively. Regarding the more challenging task of HCC diagnosis, a 2021 deep learning model, trained with CT scans, classified hepatic malignant lesions with an AUC of 0.986. Finally, a MRI machine learning model developed in 2021 displayed an AUC of 0.975 when differentiating small HCCs from benign lesions, while another MRI-based model achieved HCC diagnosis with an AUC of 0.970. CONCLUSIONS: AI tools may lead to significant improvement in diagnostic management of HCC. Many models fared better or comparable to experienced radiologists while proving capable of elevating radiologists' accuracy, demonstrating promising results for AI implementation in HCC-related diagnostic tasks.
