More

    Miltenyi Biotech Uses Machine Learning to Assess HCC Risk

    New Screening Tool May Boost HCC Five-Year Survival Rate to 90%

    Researchers at the University of Pittsburgh School of Medicine have developed a novel serum-fusion-gene machine-learning (ML) model that could revolutionize the early diagnosis of hepatocellular carcinoma (HCC), potentially increasing the five-year survival rate from 20% to 90%.

    Currently, the most common screening method for HCC involves testing for the biomarker serum alpha-fetal protein. However, this method is often inaccurate, leading to late-stage diagnoses in up to 60% of liver cancer cases, which drastically lowers patient survival rates. Dr. Jian-Hua Luo, the lead investigator from the Department of Pathology, High Throughput Genome Center, and Pittsburgh Liver Research Center at the University of Pittsburgh School of Medicine, emphasized the need for a more reliable and cost-effective test: “What we need is a cost-effective, accurate, and convenient test to screen early-stage liver cancer in human populations. We wanted to explore if a machine-learning approach could be used to increase the accuracy of screening for HCC based on the status of the fusion genes.”

    The research team analyzed nine fusion transcripts in serum samples from 61 HCC patients and 75 non-HCC patients using real-time quantitative reverse transcription PCR (RT-PCR). They discovered that seven of the nine fusions were frequently present in HCC patients. By using these serum fusion-gene levels, they developed ML models to predict HCC.

    The results were promising. A four fusion gene logistic regression model achieved an accuracy of 83% to 91% in predicting HCC. When combined with serum alpha-fetal protein, a two-fusion gene plus alpha-fetal protein logistic regression model achieved an impressive 95% accuracy across all cohorts. Additionally, the quantification of fusion gene transcripts in serum samples effectively evaluated treatment impact and monitored cancer recurrence.

    Dr. Luo highlighted the significance of this breakthrough: “The fusion gene machine-learning model significantly improves the early detection rate of HCC over the serum alpha-fetal protein alone. It may serve as an important tool in screening for HCC and in monitoring the impact of HCC treatment. This test will find patients who are likely to have HCC.”

    The study detailing these findings was published in The American Journal of Pathology

    Related topics:

    The Vital Difference Between Machine Learning And Generative AI

    Klarity Intelligence Secures $70 Million to Automate Document Review

    ChatGPT-4 passes the “Turing Test” Scientists: AI intelligence is comparable to humans

    Recent Articles

    TAGS

    Related Stories