Mohanty Prasant Kumar, Anand John Francis Sharmila, Barik Rabindra Kumar, Reddy K Hemant Kumar, Sinha Roy Diptendu, Saikia Manob Jyoti
Department of Computer Science and Engineering, National Institute of Technology, Shillong, Meghalaya, India.
Department of Computer Science, Rijal Alma'a, King Khalid University, Abha, Saudi Arabia.
PeerJ Comput Sci. 2025 Apr 29;11:e2839. doi: 10.7717/peerj-cs.2839. eCollection 2025.
Multi-disease conditions strain the body's defenses, complicating recovery and increasing mortality risk. Therefore, effective concurrent prevention of multiple diseases is essential for mitigating complications and improving overall well-being. Explainable artificial intelligence (XAI) with an advanced multimodal large language model (LLM) can create an interactive system enabling the general public to engage in natural language without any specialized knowledge prerequisites. Counterfactual explanation, an XAI method, offers valuable insights by suggesting adjustments to patient features to minimize disease risks. However, addressing multiple diseases simultaneously poses challenging barriers. This article proposes an interactive multi-disease prevention system that uses Google Gemini Pro, a multimodal LLM, and a non-dominated sorting genetic algorithm, namely NSGA-II, to overcome such problems. This system recommends changes in feature values to concurrently minimize the risk of diseases such as heart attacks and diabetes. The system facilitates personalized feature value selection, significantly reducing disease attack probabilities to as low as possible. Such an approach holds the potential to simultaneously address the unresolved issue of preventing and managing multiple diseases for the general public.
多病共存的情况会给身体的防御系统带来压力，使康复过程复杂化并增加死亡风险。因此，有效同时预防多种疾病对于减轻并发症和改善整体健康状况至关重要。具有先进多模态大语言模型（LLM）的可解释人工智能（XAI）可以创建一个交互式系统，使普通公众无需任何专业知识前提就能以自然语言参与其中。反事实解释作为一种XAI方法，通过建议调整患者特征以最小化疾病风险提供了有价值的见解。然而，同时应对多种疾病存在具有挑战性的障碍。本文提出了一种交互式多疾病预防系统，该系统使用多模态LLM谷歌Gemini Pro和一种非支配排序遗传算法，即NSGA-II，来克服此类问题。该系统推荐特征值的变化，以同时最小化心脏病发作和糖尿病等疾病的风险。该系统有助于进行个性化特征值选择，将疾病发作概率显著降低到尽可能低的水平。这种方法有可能同时解决普通公众预防和管理多种疾病这一未解决的问题。
