RESUMO
BACKGROUND: Hepatocellular carcinoma (HCC) recurrence following surgical resection remains a significant clinical challenge, necessitating reliable predictive models to guide personalised interventions. In this study, we sought to harness the power of artificial intelligence (AI) to develop a robust predictive model for HCC recurrence using comprehensive clinical datasets. METHODS: Leveraging data from 958 patients across multiple centres in Australia and Hong Kong, we employed a multilayer perceptron (MLP) as the optimal classifier for model generation. RESULTS: Through rigorous internal cross-validation, including a cohort from the Chinese University of Hong Kong (CUHK), our AI model successfully identified specific pre-surgical risk factors associated with HCC recurrence. These factors encompassed hepatic synthetic function, liver disease aetiology, ethnicity and modifiable metabolic risk factors, collectively contributing to the predictive synergy of our model. Notably, our model exhibited high accuracy during cross-validation (.857 ± .023) and testing on the CUHK cohort (.835), with a notable degree of confidence in predicting HCC recurrence within accurately classified patient cohorts. To facilitate clinical application, we developed an online AI digital tool capable of real-time prediction of HCC recurrence risk, demonstrating acceptable accuracy at the individual patient level. CONCLUSION: Our findings underscore the potential of AI-driven predictive models in facilitating personalised risk stratification and targeted interventions to mitigate HCC recurrence by identifying modifiable risk factors unique to each patient. This model aims to aid clinicians in devising strategies to disrupt the underlying carcinogenic network driving recurrence.
RESUMO
Acute myeloid leukemia (AML) is a fatal disease characterized by the accumulation of undifferentiated myeloblasts, and agents that promote differentiation have been effective in this disease but are not curative. Dihydroorotate dehydrogenase inhibitors (DHODHi) have the ability to promote AML differentiation and target aberrant malignant myelopoiesis. We introduce HOSU-53, a DHODHi with significant monotherapy activity, which is further enhanced when combined with other standard-of-care therapeutics. We further discovered that DHODHi modulated surface expression of CD38 and CD47, prompting the evaluation of HOSU-53 combined with anti-CD38 and anti-CD47 therapies, where we identified a compelling curative potential in an aggressive AML model with CD47 targeting. Finally, we explored using plasma dihydroorotate (DHO) levels to monitor HOSU-53 safety and found that the level of DHO accumulation could predict HOSU-53 intolerability, suggesting the clinical use of plasma DHO to determine safe DHODHi doses. Collectively, our data support the clinical translation of HOSU-53 in AML, particularly to augment immune therapies. Potent DHODHi to date have been limited by their therapeutic index; however, we introduce pharmacodynamic monitoring to predict tolerability while preserving antitumor activity. We additionally suggest that DHODHi is effective at lower doses with select immune therapies, widening the therapeutic index.