Deep Learning Model Could Predict Outcomes for HCC Patients

Cleveland Clinic researchers collaborated with Owkin to develop and validate a deep learning model to predict survival and outcomes for hepatocellular carcinoma (HCC) patients after liver transplantation.

The study was performed on 293 whole-slide images stained with haematoxylin/eosin and clinical data from HCC patients who had a liver transplant at Cleveland Clinic.

The findings indicate that the deep learning model trained on histopathology data predicted recurrence among transplant patients both in the whole cohort and in subgroups of patients treated with or without loco-regional therapy before transplantation. The results were comparable to a different model that incorporated clinical, biological, and pathological data.

Most significantly, combinations of both histological and clinical models outperformed the current scoring system. This study showcases the prognostic power of deep learning when applied to the histology slides to predict the recurrence of HCC patients after liver transplantation.

According to Federico Aucejo, MD, Director of the Liver Cancer Program and Surgical Director of the Liver Tumor Clinic, machine learning technology is rapidly improving outcomes in the medical community. Its application in patient populations, risk stratification, and personalized medicine can significantly enhance safety, allowing for a more cost-effective healthcare environment.

“In line with this, partnerships and alliances among healthcare networks and the tech industry will be instrumental to paving the way towards this paradigm change,” Aucejo said in a press release.

“This collaboration resulted in the development of an algorithm to predict outcome in patients undergoing liver transplantation with HCC by scrutinizing histopathology digital slides. This approach proved to be superior to predict tumor recurrence than conventional metrics.”

The collaborative research effort aims to advance the prediction of HCC patient outcomes through artificial intelligence and identify prognostic markers after treatment.

“The richness and uniqueness of Cleveland Clinic’s research cohorts, together with Owkin’s extensive expertise in developing predictive AI models, can pave the way for breakthrough, forward-thinking science and will allow the opportunity to further develop our collaboration in future research areas,” Chief Data and Clinical Solutions Officer Meriem Sefta, PhD, said.

HCC is one of the leading causes of cancer-related deaths globally, making up around 90 percent of primary liver cancers. Currently, liver transplantation is the best treatment option for cirrhotic patients with early-stage HCC. However, tumor recurrence after a liver transplant occurs in 15–20 percent of cares, correlating with poor survivorship.

Currently, there are no reliable histological markers of relapse-free survival in HCC patients following a liver transplant, which is crucial in predicting patient prognosis.

Building on these results, additional deep-learning models and multimodal models trained on medical imaging, molecular, and genomics data as well as clinical and histopathological data should provide future insights into diagnostic and biomarkers predicting HCC prognosis and survivorship after treatment and improve patient care and long-term outcomes.