{
  "abstract": "Background Immunotherapy has become an essential therapeutic strategy in the treatment of various cancers. However, the variability in patients’ response remains a major challenge, highlighting the need for effective predictive models.Methods This study aims to develop an artificial intelligence model to predict patients’ response to immunotherapy based on transcriptomic data.We used an artificial neural network (ANN) trained on gene expression data from patients classified as responders or non-responders to immunotherapy. The model’s performance was evaluated using metrics such as mean squared error (MSE) and accuracy rate.Results The model achieved a low MSE and an accuracy of 71%, demonstrating a good ability to predict patients likely to respond to immunotherapy.Conclusions This AI-based model could be a promising tool for precision medicine, helping to better select patients likely to benefit from immunotherapy and avoiding unnecessary treatments in non-responders.",
  "authors": [
    {
      "affiliations": [
        "University Hassan II Casablanca, Casablanca, Morocco"
      ],
      "name": "Zaynab EL Moudden"
    },
    {
      "affiliations": [
        "Immuno-Genetics and human pathology laboratory, Faculty of Medicine and Pharmacy, Casablanca, Casablanca, Morocco"
      ],
      "name": "Khadija Elazhary"
    },
    {
      "affiliations": [
        "Immuno-Genetics and human pathology laboratory, Faculty of Medicine and Pharmacy, Casablanca, Casablanca, Morocco"
      ],
      "name": "Sanaa Souat"
    },
    {
      "affiliations": [
        "Computer Science and Smart Systems Laboratory, Higher School of Technology of Casablanca, Casablanca, Casablanca, Morocco"
      ],
      "name": "Mostafa Jebbar"
    },
    {
      "affiliations": [
        "Immuno-Genetics and human pathology laboratory, Faculty of Medicine and Pharmacy, Casablanca, Casablanca, Morocco"
      ],
      "name": "Abdallah Badou"
    }
  ],
  "title": "1079 Artificial neural network-based prediction of immunotherapy response in glioblastoma patients using transcriptomic data",
  "uid": "a7923cf3-3a52-5f4a-b09d-dcfeeb2b3d3f"
}