Emerging frontiers of artificial intelligence and machine learning in ischemic stroke: a comprehensive investigation of state-of-the-art methodologies, clinical applications, and unraveling challenges.

At present, stroke remains the second highest cause of death globally and a leading cause of disability. From 1990 to 2019, the absolute number of strokes worldwide increased by 70.0%, and the prevalence of stroke increased by 85.0%, causing millions of deaths and disability. Ischemic stroke accounts for the majority of strokes, which is caused by arterial occlusion. Effective primary prevention strategies, early diagnosis, and timely interventions such as rapid reperfusion are in urgent implementation to control ischemic stroke. Otherwise, the stroke burden will probably continue to grow across the world as a result of population aging and an ongoing high prevalence of risk factors. To help with the diagnosis and management of ischemic stroke, newer techniques such as artificial intelligence (AI) are highly anticipated and may bring a new revolution. AI is a recent fast-growing research area which aims to mimic cognitive processes through a number of techniques such as machine learning (ML) methods of random forest learning (RFL) and convolutional neural networks (CNNs). With the help of AI, several momentous milestones have already been attained across diverse dimensions of ischemic stroke. In the context of predictive, preventive, and personalized medicine (PPPM/3PM), we aim to transform stroke care from a reactive to a proactive and individualized paradigm. In this way, AI demonstrates strong clinical utility across all three levels of prevention in ischemic stroke. In this paper, we synoptically illustrated the history and current situation of AI and ML. Then, we summarized their clinical applications and efficacy in the management of stroke. We finally provided an outlook on how AI approaches might contribute to enhancing favorable outcomes after stroke and proposed our suggestions on developing AI-based PPPM strategies. Supplementary Information: The online version contains supplementary material available at 10.1007/s13167-023-00343-3.

New insight of metabolomics in ocular diseases in the context of 3P medicine.

Metabolomics refers to the high-through untargeted or targeted screening of metabolites in biofluids, cells, and tissues. Metabolome reflects the functional states of cells and organs of an individual, influenced by genes, RNA, proteins, and environment. Metabolomic analyses help to understand the interaction between metabolism and phenotype and reveal biomarkers for diseases. Advanced ocular diseases can lead to vision loss and blindness, reducing patients' quality of life and aggravating socio-economic burden. Contextually, the transition from reactive medicine to the predictive, preventive, and personalized (PPPM / 3P) medicine is needed. Clinicians and researchers dedicate a lot of efforts to explore effective ways for disease prevention, biomarkers for disease prediction, and personalized treatments, by taking advantages of metabolomics. In this way, metabolomics has great clinical utility in the primary and secondary care. In this review, we summarized much progress achieved by applying metabolomics to ocular diseases and pointed out potential biomarkers and metabolic pathways involved to promote 3P medicine approach in healthcare.

Targeting phytoprotection in the COVID-19-induced lung damage and associated systemic effects-the evidence-based 3PM proposition to mitigate individual risks.

The risks related to the COVID-19 are multi-faceted including but by far not restricted to the following: direct health risks by poorly understood effects of COVID-19 infection, overloaded capacities of healthcare units, restricted and slowed down care of patients with non-communicable disorders such as cancer, neurologic and cardiovascular pathologies, among others; social risks-restricted and broken social contacts, isolation, professional disruption, explosion of aggression in the society, violence in the familial environment; mental risks-loneliness, helplessness, defenceless, depressions; and economic risks-slowed down industrial productivity, broken delivery chains, unemployment, bankrupted SMEs, inflation, decreased capacity of the state to perform socially important programs and to support socio-economically weak subgroups in the population. Directly or indirectly, the above listed risks will get reflected in a healthcare occupation and workload which is a tremendous long-term challenge for the healthcare capacity and robustness. The article does not pretend to provide solutions for all kind of health risks. However, it aims to present the scientific evidence of great clinical utility for primary, secondary, and tertiary care to protect affected individuals in a cost-effective manner. To this end, due to pronounced antimicrobial, antioxidant, anti-inflammatory, and antiviral properties, naturally occurring plant substances are capable to protect affected individuals against COVID-19-associated life-threatening complications such as lung damage. Furthermore, they can be highly effective, if being applied to secondary and tertiary care of noncommunicable diseases under pandemic condition. Thus, the stratification of patients evaluating specific health conditions such as sleep quality, periodontitis, smoking, chronic inflammation and diseases, metabolic disorders and obesity, vascular dysfunction, and cancers would enable effective managemenet of COVID-19-associated complications in primary, secondary, and tertiary care in the context of predictive, preventive, and personalized medicine (3PM).

Flavonoids as an effective sensitizer for anti-cancer therapy: insights into multi-faceted mechanisms and applicability towards individualized patient profiles.

Cost-efficacy of currently applied treatments is an issue in overall cancer management challenging healthcare and causing tremendous economic burden to societies around the world. Consequently, complex treatment models presenting concepts of predictive diagnostics followed by targeted prevention and treatments tailored to the personal patient profiles earn global appreciation as benefiting the patient, healthcare economy, and the society at large. In this context, application of flavonoids as a spectrum of compounds and their nano-technologically created derivatives is extensively under consideration, due to their multi-faceted anti-cancer effects applicable to the overall cost-effective cancer management, primary, secondary, and even tertiary prevention. This article analyzes most recently updated data focused on the potent capacity of flavonoids to promote anti-cancer therapeutic effects and interprets all the collected research achievements in the frame-work of predictive, preventive, and personalized (3P) medicine. Main pillars considered are: - Predictable anti-neoplastic, immune-modulating, drug-sensitizing effects; - Targeted molecular pathways to improve therapeutic outcomes by increasing sensitivity of cancer cells and reversing their resistance towards currently applied therapeutic modalities.

Mass spectrometry analysis of human tear fluid biomarkers specific for ocular and systemic diseases in the context of 3P medicine.

Over the last two decades, a large number of non-communicable/chronic disorders reached an epidemic level on a global scale such as diabetes mellitus type 2, cardio-vascular disease, several types of malignancies, neurological and eye pathologies-all exerted system's enormous socio-economic burden to primary, secondary, and tertiary healthcare. The paradigm change from reactive to predictive, preventive, and personalized medicine (3PM/PPPM) has been declared as an essential transformation of the overall healthcare approach to benefit the patient and society at large. To this end, specific biomarker panels are instrumental for a cost-effective predictive approach of individualized prevention and treatments tailored to the person. The source of biomarkers is crucial for specificity and reliability of diagnostic tests and treatment targets. Furthermore, any diagnostic approach preferentially should be noninvasive to increase availability of the biomaterial, and to decrease risks of potential complications as well as concomitant costs. These requirements are clearly fulfilled by tear fluid, which represents a precious source of biomarker panels. The well-justified principle of a "sick eye in a sick body" makes comprehensive tear fluid biomarker profiling highly relevant not only for diagnostics of eye pathologies but also for prediction, prognosis, and treatment monitoring of systemic diseases. One prominent example is the Sicca syndrome linked to a cascade of severe complications that include dry eye, neurologic, and oncologic diseases. In this review, protein profiles in tear fluid are highlighted and corresponding biomarkers are exemplified for several relevant pathologies, including dry eye disease, diabetic retinopathy, cancers, and neurological disorders. Corresponding analytical approaches such as sample pre-processing, differential proteomics, electrophoretic techniques, high-performance liquid chromatography (HPLC), enzyme-linked immuno-sorbent assay (ELISA), microarrays, and mass spectrometry (MS) methodology are detailed. Consequently, we proposed the overall strategies based on the tear fluid biomarkers application for 3P medicine practice. In the context of 3P medicine, tear fluid analytical pathways are considered to predict disease development, to target preventive measures, and to create treatment algorithms tailored to individual patient profiles.

Differences in cohort study data affect external validation of artificial intelligence models for predictive diagnostics of dementia - lessons for translation into clinical practice.

Artificial intelligence (AI) approaches pose a great opportunity for individualized, pre-symptomatic disease diagnosis which plays a key role in the context of personalized, predictive, and finally preventive medicine (PPPM). However, to translate PPPM into clinical practice, it is of utmost importance that AI-based models are carefully validated. The validation process comprises several steps, one of which is testing the model on patient-level data from an independent clinical cohort study. However, recruitment criteria can bias statistical analysis of cohort study data and impede model application beyond the training data. To evaluate whether and how data from independent clinical cohort studies differ from each other, this study systematically compares the datasets collected from two major dementia cohorts, namely, the Alzheimer's Disease Neuroimaging Initiative (ADNI) and AddNeuroMed. The presented comparison was conducted on individual feature level and revealed significant differences among both cohorts. Such systematic deviations can potentially hamper the generalizability of results which were based on a single cohort dataset. Despite identified differences, validation of a previously published, ADNI trained model for prediction of personalized dementia risk scores on 244 AddNeuroMed subjects was successful: External validation resulted in a high prediction performance of above 80% area under receiver operator characteristic curve up to 6 years before dementia diagnosis. Propensity score matching identified a subset of patients from AddNeuroMed, which showed significantly smaller demographic differences to ADNI. For these patients, an even higher prediction performance was achieved, which demonstrates the influence systematic differences between cohorts can have on validation results. In conclusion, this study exposes challenges in external validation of AI models on cohort study data and is one of the rare cases in the neurology field in which such external validation was performed. The presented model represents a proof of concept that reliable models for personalized predictive diagnostics are feasible, which, in turn, could lead to adequate disease prevention and hereby enable the PPPM paradigm in the dementia field.