Artificial Intelligence and Machine Learning Applied at the Point of Care.

INTRODUCTION: The increasing availability of healthcare data and rapid development of big data analytic methods has opened new avenues for use of Artificial Intelligence (AI)- and Machine Learning (ML)-based technology in medical practice. However, applications at the point of care are still scarce. OBJECTIVE: Review and discuss case studies to understand current capabilities for applying AI/ML in the healthcare setting, and regulatory requirements in the US, Europe and China. METHODS: A targeted narrative literature review of AI/ML based digital tools was performed. Scientific publications (identified in PubMed) and grey literature (identified on the websites of regulatory agencies) were reviewed and analyzed. RESULTS: From the regulatory perspective, AI/ML-based solutions can be considered medical devices (i.e., Software as Medical Device, SaMD). A case series of SaMD is presented. First, tools for monitoring and remote management of chronic diseases are presented. Second, imaging applications for diagnostic support are discussed. Finally, clinical decision support tools to facilitate the choice of treatment and precision dosing are reviewed. While tested and validated algorithms for precision dosing exist, their implementation at the point of care is limited, and their regulatory and commercialization pathway is not clear. Regulatory requirements depend on the level of risk associated with the use of the device in medical practice, and can be classified into administrative (manufacturing and quality control), software-related (design, specification, hazard analysis, architecture, traceability, software risk analysis, cybersecurity, etc.), clinical evidence (including patient perspectives in some cases), non-clinical evidence (dosing validation and biocompatibility/toxicology) and other, such as e.g. benefit-to-risk determination, risk assessment and mitigation. There generally is an alignment between the US and Europe. China additionally requires that the clinical evidence is applicable to the Chinese population and recommends that a third-party central laboratory evaluates the clinical trial results. CONCLUSIONS: The number of promising AI/ML-based technologies is increasing, but few have been implemented widely at the point of care. The need for external validation, implementation logistics, and data exchange and privacy remain the main obstacles.

Aspirin blocks binding of photosensitizer SnET2 into human serum albumin: implications for photodynamic therapy.

Tin etiopurpurin dichloride (SnET2) is one of the photosensitizers under investigation to be used in photodynamic therapy of prostate cancer. The drug is delivered intravenously, transported in vivo by liposomes and plasma proteins and localized within the prostate. SnET2 exists in two tautomeric forms (I - closed ring, II - open ring) with I converting spontaneously into the more energetically stable form II at physiological pH. Up to approximately 50% of the drug can be carried by serum albumin, although this association can increase photo-bleaching and diminish the drug efficiency. Molecular modeling and force field calculations indicate that Sudlow Site I in human serum albumin (HSA) is the most probable binding site for both forms of SnET2, with the porphyrin moiety nestling between domains IIA and IB, and the esterolytic side group oriented toward domain IIIA of HSA. Other drugs, including aspirin, bind to the same part of HSA. SnET2 does not bind to HSA when pre-incubated with aspirin, which confirms that its place of binding to this protein must be located near Lys199. This observation could be exploited to improve photo-efficiency of SnET2 by finding drugs that could compete with the photosensitizer for binding into Sudlow Site I of HSA.

Singlet oxygen luminescence as an in vivo photodynamic therapy dose metric: validation in normal mouse skin with topical amino-levulinic acid.

Although singlet oxygen ((1)O(2)) has long been proposed as the primary reactive oxygen species in photodynamic therapy (PDT), it has only recently been possible to detect it in biological systems by its luminescence at 1270 nm. Having previously demonstrated this in vitro and in vivo, we showed that cell survival was strongly correlated to the (1)O(2) luminescence in cell suspensions over a wide range of treatment parameters. Here, we extend this to test the hypothesis that the photobiological response in vivo is also correlated with (1)O(2) generation, independent of individual treatment parameters. The normal skin of SKH1-HR hairless mice was sensitised with 20% amino-levulinic acid-induced protoporophyrin IX and exposed to 5, 11, 22 or 50 J cm(-2) of pulsed 523 nm light at 50 mW cm(-2), or to 50 J cm(-2) at 15 or 150 mW cm(-2). (1)O(2) luminescence was measured during treatment and the photodynamic response of the skin was scored daily for 2 weeks after treatment. As observed by other authors, a strong irradiance dependence of the PDT effect was observed. However, in all cases the responses increased with the (1)O(2) luminescence, independent of the irradiance, demonstrating for the first time in vivo an unequivocal mechanistic link between (1)O(2) generation and photobiological response.