Assessment of LI-RADS efficacy in classification of hepatocellular carcinoma and benign liver nodules using DCE-MRI features and machine learning

A cost-effective predictive tool for AFP-negative focal hepatic lesions of retrospective study: enhancing clinical triage and decision-making

Background

Identifying alpha-fetal protein (AFP)-negative focal hepatic lesions presents a significant challenge, particularly in China. We sought to develop an economically portable tool for the diagnosis of benign and malignant liver lesions with AFP-negative status, and explore its clinical diagnostic efficiency.

Methods

A retrospective study was conducted at Peking University Shenzhen Hospital from January 2017 to February 2023, including a total of 348 inpatients with AFP-negative liver space-occupying lesions. The study used a training set of 252 inpatients from January 2017 to September 2021 to establish a diagnostic model for differentiating benign and malignant AFP-negative liver space-occupying lesions. Additionally, a validation cohort of 96 inpatients from October 2021 to February 2023 was used to confirm the diagnostic performance of the model. From January 2017 to February 2023, patients at JingNing People's Hospital, Gansu Province were assigned to the external cohort (n = 78).

Results

A predictive tool was established by screening age, gender, hepatitis B virus (HBV)/hepatitis C virus (HCV) infected, single lesion, alanine amino transferase (ALT), and lymphocyte-to-monocyte ratio (LMR) using multivariate logistic regression analysis and clinical practice. The area under the curve (AUC) of the model was 0.911 (95% CI [0.873-0.949]) in the training set and 0.882 (95% CI [0.815-0.949]) in the validation cohort. In addition, the model achieved an area under the curve of 0.811 (95% CI [0.687-0.935]) in the external validation cohort.

Conclusion

Our results demonstrated that the predictive tool has the characteristics of good diagnostic efficiency, economy and convenience, which is helpful for the clinical triage and decision-making of AFP-negative liver space-occupying lesions.

Diagnostic Performance of Artificial Intelligence in Detection of Hepatocellular Carcinoma: A Meta-analysis

Due to the increasing interest in the use of artificial intelligence (AI) algorithms in hepatocellular carcinoma detection, we performed a systematic review and meta-analysis to pool the data on diagnostic performance metrics of AI and to compare them with clinicians' performance. A search in PubMed and Scopus was performed in January 2024 to find studies that evaluated and/or validated an AI algorithm for the detection of HCC. We performed a meta-analysis to pool the data on the metrics of diagnostic performance. Subgroup analysis based on the modality of imaging and meta-regression based on multiple parameters were performed to find potential sources of heterogeneity. The risk of bias was assessed using Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Study Risk of Bias Assessment Tool (PROBAST) reporting guidelines. Out of 3177 studies screened, 44 eligible studies were included. The pooled sensitivity and specificity for internally validated AI algorithms were 84% (95% CI: 81,87) and 92% (95% CI: 90,94), respectively. Externally validated AI algorithms had a pooled sensitivity of 85% (95% CI: 78,89) and specificity of 84% (95% CI: 72,91). When clinicians were internally validated, their pooled sensitivity was 70% (95% CI: 60,78), while their pooled specificity was 85% (95% CI: 77,90). This study implies that AI can perform as a diagnostic supplement for clinicians and radiologists by screening images and highlighting regions of interest, thus improving workflow.