Novel machine learning models outperform risk scores in predicting hepatocellular carcinoma in patients with chronic viral hepatitis

Abstract

Novel machine-learning models outperform risk scores in predicting hepatocellular carcinoma in patients with chronic viral hepatitis

A novel image-based machine learning model with superior accuracy and predictability for knee arthroplasty loosening detection and clinical decision making

“…Although this study has already employed 440 images for the development of the model, using more images may still further enhance the performance of the model. The use on using a larger quantity of images from territory-wide data source can be used toward the verification of the model or to provide more raw images for the training of the model, which these would significantly help to improve the precision of this model [ 29 ].…”

Patterns and factors associated with the prescription of psychotropic medications after diagnosis of cancer in Chinese patients: A population‐based cohort study

“…de-identified data from the HA, which have been used in large-scale epidemiological studies. 22 Data on this cohort of 200 000 patients who were treated in the public hospitals, which can be accessed through a self-service data platform, was used in the present study (Hospital Authority, 2021). This study was approved by the Survey and Behavioural Research Ethics Committee of the Chinese University of Hong Kong (SBRE-21-0112).…”

Improving prediction of hepatocellular carcinoma in chronic hepatitis B by machine learning: Productive relationship of medicine with computer science

“…It is anticipated that these new algorithms willhavearoleinHCCriskprediction. [18][19][20] In Liver International this month, Lee, Kim, and colleagues shed In the development cohort, the novel machine-learning model achieved an AUC of 0.900 (95% CI: 0.867-0.934), which was significantly higher than that of existing HCC risk scores including CAMD(0.778), 9 REAL-B(0.772), 10…”

“…Machine‐learning approaches, on the other hand, consider all possible interactions which may strengthen their predictive power. It is anticipated that these new algorithms will have a role in HCC risk prediction 18–20 …”