Tribulations and future opportunities for artificial intelligence in precision medicine

Abstract

Upon a diagnosis, the clinical team faces two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate the reported response from relevant clinical trials. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies with the changes in their condition. In practice, the drug and the dose selection depend significantly on the medical protocol and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data and Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit their application. AI is a rapidly evolving and dynamic field with the potential to revolutionize various aspects of human life. AI has become increasingly crucial in drug discovery and development. AI enhances decision-making across different disciplines, such as medicinal chemistry, molecular and cell biology, pharmacology, pathology, and clinical practice. In addition to these, AI contributes to patient population selection and stratification. The need for AI in healthcare is evident as it aids in enhancing data accuracy and ensuring the quality care necessary for effective patient treatment. AI is pivotal in improving success rates in clinical practice. The increasing significance of AI in drug discovery, development, and clinical trials is underscored by many scientific publications. Despite the numerous advantages of AI, such as enhancing and advancing Precision Medicine (PM) and remote patient monitoring, unlocking its full potential in healthcare requires addressing fundamental concerns. These concerns include data quality, the lack of well-annotated large datasets, data privacy and safety issues, biases in AI algorithms, legal and ethical challenges, and obstacles related to cost and implementation. Nevertheless, integrating AI in clinical medicine will improve diagnostic accuracy and treatment outcomes, contribute to more efficient healthcare delivery, reduce costs, and facilitate better patient experiences, making healthcare more sustainable. This article reviews AI applications in drug development and clinical practice, making healthcare more sustainable, and highlights concerns and limitations in applying AI.

Keywords: Artificial intelligence; Deep learning; Disease diagnosis; Drug discovery and development; Health technology assessment; Machine learning; Precision medicine; Prediction; Prevention.

Fig. 1

Precision medicine paradigm. Current approaches for precision medicine often involve assessment of various cancer drugs including chemotherapy, targeted therapies, or immunotherapy and others using patient derived tissue cancer cells or models such as spheroid or organoid as well as orthotopic murine xenograft models. With the rise of AI-based systems and technology platforms, it is anticipated that this process can be accelerated. Created with BioRender.com. (Accessed on 18 January 2024, 2024)

Fig. 2

AI-based technologies can accelerate the drug discovery and development process and reduce the cost. Left panel: AI-based techniques can accelerate the drug discovery and development process, potentially reducing the attrition rate, time, and the cost. AI-based drug discovery and screening alongside laboratory automation could augment human drug design, chemical synthesis, drug screening, biological testing, and decision-making in design–make–test–analyze cycles involved in drug discovery and development, potentially overcoming low success rates, long drug development process, and high-cost often associated with traditional drug discovery and development process. Right panel: in clinical trial space, AI-based techniques can help physicians to leverage patient’s genomic data to identify suitable drugs that target those genomic aberrations. This approach offers the potential for enhanced drug effectiveness, improved safety profiles, decreased adverse reactions, expanded treatment choices, and, ultimately, a potential for saving lives. Abbreviations: DNN, deep neural network; EHR, electronic health records; IoMT, internet of medical things; ML, machine learning. Created with BioRender.com. (Accessed on 18 January 2024, 2024).

Fig. 3

AI in drug discovery and laboratory automation for preclinical testing. AI-based drug discovery and screening alongside laboratory automation could augment human drug design, chemical synthesis, drug screening, biological testing, and decision-making in design–make–test–analyze cycles involved in drug discovery. Created with BioRender.com. (Accessed on 18 January 2024, 2024)

Fig. 4

Leveraging AI for personalized treatment. AI-focused workflow explores the opportunities and challenges of applying AI in digital pathology, drug discovery and development, and dynamic drug dosing. Created with BioRender.com. (Accessed on 18 January 2024, 2024)

Fig. 5

Illustration of integration of AI into PM. Recent attempts to integrate AI into PM have demonstrated significant potential and progress in personalized care, clinical decision support systems, early disease detection, and disease monitoring. However, there are outstanding challenges and concerns involving technical challenges and ethical issues and concerns (e.g., fairness and bias, trust, transparency and liability, trust, safety and security, as well as requirement of high quality large data, data deluge, and data drift) that may hinder the progress and reliability of the field and delay clinical implementation. Created with BioRender.com. (Accessed on 18 January 2024, 2024)