Integrating AI/ML Models for Patient Stratification Leveraging Omics Dataset and Clinical Biomarkers from COVID-19 Patients: A Promising Approach to Personalized Medicine.

The COVID-19 pandemic has presented an unprecedented challenge to the healthcare system. Identifying the genomics and clinical biomarkers for effective patient stratification and management is critical to controlling the spread of the disease. Omics datasets provide a wealth of information that can aid in understanding the underlying molecular mechanisms of COVID-19 and identifying potential biomarkers for patient stratification. Artificial intelligence (AI) and machine learning (ML) algorithms have been increasingly used to analyze large-scale omics and clinical datasets for patient stratification. In this manuscript, we demonstrate the recent advances and predictive accuracies in AI- and ML-based patient stratification modeling linking omics and clinical biomarker datasets, focusing on COVID-19 patients. Our ML model not only demonstrates that clinical features are enough of an indicator of COVID-19 severity and survival, but also infers what clinical features are more impactful, which makes our approach a useful guide for clinicians for prioritization best-fit therapeutics for a given cohort of patients. Moreover, with weighted gene network analysis, we are able to provide insights into gene networks that have a significant association with COVID-19 severity and clinical features. Finally, we have demonstrated the importance of clinical biomarkers in identifying high-risk patients and predicting disease progression.

Genetic risk factors for ME/CFS identified using combinatorial analysis.

BACKGROUND: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating chronic disease that lacks known pathogenesis, distinctive diagnostic criteria, and effective treatment options. Understanding the genetic (and other) risk factors associated with the disease would begin to help to alleviate some of these issues for patients. METHODS: We applied both GWAS and the PrecisionLife combinatorial analytics platform to analyze ME/CFS cohorts from UK Biobank, including the Pain Questionnaire cohort, in a case-control design with 1000 cycles of fully random permutation. Results from this study were supported by a series of replication and cohort comparison experiments, including use of disjoint Verbal Interview CFS, post-viral fatigue syndrome and fibromyalgia cohorts also derived from UK Biobank, and compared results for overlap and reproducibility. RESULTS: Combinatorial analysis revealed 199 SNPs mapping to 14 genes that were significantly associated with 91% of the cases in the ME/CFS population. These SNPs were found to stratify by shared cases into 15 clusters (communities) made up of 84 high-order combinations of between 3 and 5 SNPs. p-values for these communities range from 2.3 × 10-10 to 1.6 × 10-72. Many of the genes identified are linked to the key cellular mechanisms hypothesized to underpin ME/CFS, including vulnerabilities to stress and/or infection, mitochondrial dysfunction, sleep disturbance and autoimmune development. We identified 3 of the critical SNPs replicated in the post-viral fatigue syndrome cohort and 2 SNPs replicated in the fibromyalgia cohort. We also noted similarities with genes associated with multiple sclerosis and long COVID, which share some symptoms and potentially a viral infection trigger with ME/CFS. CONCLUSIONS: This study provides the first detailed genetic insights into the pathophysiological mechanisms underpinning ME/CFS and offers new approaches for better diagnosis and treatment of patients.

Characterization of oral and gut microbiome and plasma metabolomics in COVID-19 patients after 1-year follow-up.

BACKGROUND: Due to the outbreak and rapid spread of coronavirus disease 2019 (COVID-19), more than 160 million patients have become convalescents worldwide to date. Significant alterations have occurred in the gut and oral microbiome and metabonomics of patients with COVID-19. However, it is unknown whether their characteristics return to normal after the 1-year recovery. METHODS: We recruited 35 confirmed patients to provide specimens at discharge and one year later, as well as 160 healthy controls. A total of 497 samples were prospectively collected, including 219 tongue-coating, 129 stool and 149 plasma samples. Tongue-coating and stool samples were subjected to 16S rRNA sequencing, and plasma samples were subjected to untargeted metabolomics testing. RESULTS: The oral and gut microbiome and metabolomics characteristics of the 1-year convalescents were restored to a large extent but did not completely return to normal. In the recovery process, the microbial diversity gradually increased. Butyric acid-producing microbes and Bifidobacterium gradually increased, whereas lipopolysaccharide-producing microbes gradually decreased. In addition, sphingosine-1-phosphate, which is closely related to the inflammatory factor storm of COVID-19, increased significantly during the recovery process. Moreover, the predictive models established based on the microbiome and metabolites of patients at the time of discharge reached high efficacy in predicting their neutralizing antibody levels one year later. CONCLUSIONS: This study is the first to characterize the oral and gut microbiome and metabonomics in 1-year convalescents of COVID-19. The key microbiome and metabolites in the process of recovery were identified, and provided new treatment ideas for accelerating recovery. And the predictive models based on the microbiome and metabolomics afford new insights for predicting the recovery situation which benefited affected individuals and healthcare.

Tangled quest of post-COVID-19 infection-caused neuropathology and what 3P nano-bio-medicine can solve?

COVID-19-caused neurological problems are the important post-CoV-2 infection complications, which are recorded in ~ 40% of critically ill COVID-19 patients. Neurodegeneration (ND) is one of the most serious complications. It is necessary to understand its molecular mechanism(s), define research gaps to direct research to, hopefully, design new treatment modalities, for predictive diagnosis, patient stratification, targeted prevention, prognostic assessment, and personalized medical services for this type of complication. Individualized nano-bio-medicine combines nano-medicine (NM) with clinical and molecular biomarkers based on omics data to improve during- and post-illness management or post-infection prognosis, in addition to personalized dosage profiling and drug selection for maximum treatment efficacy, safety with least side-effects. This review will enumerate proteins, receptors, and enzymes involved in CoV-2 entrance into the central nervous system (CNS) via the blood-brain barrier (BBB), and list the repercussions after that entry, ranging from neuroinflammation to neurological symptoms disruption mechanism. Moreover, molecular mechanisms that mediate the host effect or viral detrimental effect on the host are discussed here, including autophagy, non-coding RNAs, inflammasome, and other molecular mechanisms of CoV-2 infection neuro-affection that are defined here as hallmarks of neuropathology related to COVID-19 infection. Thus, a couple of questions are raised; for example, "What are the hallmarks of neurodegeneration during COVID-19 infection?" and "Are epigenetics promising solution against post-COVID-19 neurodegeneration?" In addition, nano-formulas might be a better novel treatment for COVID-19 neurological complications, which raises one more question, "What are the challenges of nano-bio-based nanocarriers pre- or post-COVID-19 infection?" especially in the light of omics-based changes/challenges, research, and clinical practice in the framework of predictive preventive personalized medicine (PPPM / 3P medicine).

A Multicenter Study Assessing Artificial Intelligence Capability in Scoring Lung Ultrasound Videos of COVID-19 Patients

Lung ultrasound (LUS) imaging is playing an important role in the current pandemic, allowing the evaluation of patients affected by COVID-19 pneumonia. However, LUS is limited to the visual inspection of ultrasound data, which negatively affects the reproducibility and reliability of the findings. For these reasons, we were the first to propose a standardized imaging protocol and a scoring system, from which we developed the first artificial intelligence (AI) models able to evaluate LUS videos. Furthermore, we demonstrated the prognostic value of our approach and its utility for patients' stratification. In this study, we report on the level of agreement between the AI and LUS clinical experts (MD) when evaluating LUS data. Specifically, in the stratification between patients at high risk of clinical worsening and patients at low risk, the agreement between MDs and AI reached 82%. These encouraging results open to the possibility of exploiting AI for fast and accurate stratification of COVID-19 patients. © 2021 IEEE.

2AI&7D Model of Resistomics to Counter the Accelerating Antibiotic Resistance and the Medical Climate Crisis

The antimicrobial resistance (AMR) crisis is referred to as ‘Medical Climate Crisis’. Inappropriate use of antimicrobial drugs is driving the resistance evolution in pathogenic microorganisms. In 2014 it was estimated that by 2050 more people will die due to antimicrobial resistance compared to cancer. It will cause a reduction of 2% to 3.5% in Gross Domestic Product (GDP) and cost the world up to 100 trillion USD. The indiscriminate use of antibiotics for COVID-19 patients has accelerated the resistance rate. COVID-19 reduced the window of opportunity for the fight against AMR. This man-made crisis can only be averted through accurate actionable antibiotic knowledge, usage, and a knowledge driven Resistomics. In this paper, we present the 2AI (Artificial Intelligence and Augmented Intelligence) and 7D (right Diagnosis, right Disease-causing-agent, right Drug, right Dose, right Duration, right Documentation, and De-escalation) model of antibiotic stewardship. The resistance related integrated knowledge of resistomics is stored as a knowledge graph in a Neo4j properties graph database for 24 × 7 access. This actionable knowledge is made available through smartphones and the Web as a Progressive Web Applications (PWA). The 2AI&7D Model delivers the right knowledge at the right time to the specialists and non-specialist alike at the point-of-action (Stewardship committee, Smart Clinic, and Smart Hospital) and then delivers the actionable accurate knowledge to the healthcare provider at the point-of-care in realtime. © 2021, Springer Nature Switzerland AG.

Combinatorial Analysis of Phenotypic and Clinical Risk Factors Associated With Hospitalized COVID-19 Patients.

Characterization of the risk factors associated with variability in the clinical outcomes of COVID-19 is important. Our previous study using genomic data identified a potential role of calcium and lipid homeostasis in severe COVID-19. This study aimed to identify similar combinations of features (disease signatures) associated with severe disease in a separate patient population with purely clinical and phenotypic data. The PrecisionLife combinatorial analytics platform was used to analyze features derived from de-identified health records in the UnitedHealth Group COVID-19 Data Suite. The platform identified and analyzed 836 disease signatures in two cohorts associated with an increased risk of COVID-19 hospitalization. Cohort 1 was formed of cases hospitalized with COVID-19 and a set of controls who developed mild symptoms. Cohort 2 included Cohort 1 individuals for whom additional laboratory test data was available. We found several disease signatures where lower levels of lipids were found co-occurring with lower levels of serum calcium and leukocytes. Many of the low lipid signatures were independent of statin use and 50% of cases with hypocalcemia signatures were reported with vitamin D deficiency. These signatures may be attributed to similar mechanisms linking calcium and lipid signaling where changes in cellular lipid levels during inflammation and infection affect calcium signaling in host cells. This study and our previous genomics analysis demonstrate that combinatorial analysis can identify disease signatures associated with the risk of developing severe COVID-19 separately from genomic or clinical data in different populations. Both studies suggest associations between calcium and lipid signaling in severe COVID-19.

Biosensor and Lab-on-a-chip Biomarker-identifying Technologies for Oral and Periodontal Diseases.

Periodontitis is a complex multifactorial disease that can lead to destruction of tooth supporting tissues and subsequent tooth loss. The most recent global burden of disease studies highlight that severe periodontitis is one of the most prevalent chronic inflammatory conditions affecting humans. Periodontitis risk is attributed to genetics, host-microbiome and environmental factors. Empirical diagnostic and prognostic systems have yet to be validated in the field of periodontics. Early diagnosis and intervention prevents periodontitis progression in most patients. Increased susceptibility and suboptimal control of modifiable risk factors can result in poor response to therapy, and relapse. The chronic immune-inflammatory response to microbial biofilms at the tooth or dental implant surface is associated with systemic conditions such as cardiovascular disease, diabetes or gastrointestinal diseases. Oral fluid-based biomarkers have demonstrated easy accessibility and potential as diagnostics for oral and systemic diseases, including the identification of SARS-CoV-2 in saliva. Advances in biotechnology have led to innovations in lab-on-a-chip and biosensors to interface with oral-based biomarker assessment. This review highlights new developments in oral biomarker discovery and their validation for clinical application to advance precision oral medicine through improved diagnosis, prognosis and patient stratification. Their potential to improve clinical outcomes of periodontitis and associated chronic conditions will benefit the dental and overall public health.

Comparison of hemoglobin level and neutrophil to lymphocyte ratio as prognostic markers in patients with COVID-19.

BACKGROUND: Anemia can negatively affect the outcome of many diseases, including infections and inflammatory conditions. AIM: To compare the prognostic value of hemoglobin level and the neutrophil/lymphocyte ratio (NLR) for prediction of coronavirus disease 2019 (COVID-19) severity. METHODS: In this retrospective cohort study, clinical data from patients with laboratory-confirmed COVID-19 were collected from hospital records from 10 April 2020 to 30 July 2020. RESULTS: The proportions of patients with mild, moderate, and severe COVID-19 differed significantly in association with hemoglobin levels, neutrophil counts, lymphocyte counts, NLR, and total leukocyte counts. Patients with severe COVID-19 had significantly lower hemoglobin levels than those with moderate or mild COVID-19. There were statistically significant negative associations between hemoglobin and D-dimer, age, and creatinine. The optimal hemoglobin cut-off value for prediction of disease severity was 11.6 g/dL. Using this cut-off value, hemoglobin had higher negative predictive value and sensitivity than NLR (92.4% and 51.3%, respectively). The specificity of hemoglobin as a prognostic marker was 79.3%. CONCLUSION: Both NLR and hemoglobin level are of prognostic value for predicting severity of COVID-19. However, hemoglobin level displayed higher sensitivity than NLR. Hemoglobin level should be assessed upon admission in all patients and closely monitored throughout the disease course.

The interplay between the vaginal microbiome and innate immunity in the focus of predictive, preventive, and personalized medical approach to combat HPV-induced cervical cancer.

HPVs representing the most common sexually transmitted disease are a group of carcinogenic viruses with different oncogenic potential. The immune system and the vaginal microbiome represent the modifiable and important risk factors in HPV-induced carcinogenesis. HPV infection significantly increases vaginal microbiome diversity, leading to gradual increases in the abundance of anaerobic bacteria and consequently the severity of cervical dysplasia. Delineation of the exact composition of the vaginal microbiome and immune environment before HPV acquisition, during persistent/progressive infections and after clearance, provides insights into the complex mechanisms of cervical carcinogenesis. It gives hints regarding the prediction of malignant potential. Relative high HPV prevalence in the general population is a challenge for modern and personalized diagnostics and therapeutic guidelines. Identifying the dominant microbial biomarkers of high-grade and low-grade dysplasia could help us to triage the patients with marked chances of lesion regression or progression. Any unnecessary surgical treatment of cervical dysplasia could negatively affect obstetrical outcomes and sexual life. Therefore, understanding the effect and role of microbiome-based therapies is a breaking point in the conservative management of HPV-associated precanceroses. The detailed evaluation of HPV capabilities to evade immune mechanisms from various biofluids (vaginal swabs, cervicovaginal lavage/secretions, or blood) could promote the identification of new immunological targets for novel individualized diagnostics and therapy. Qualitative and quantitative assessment of local immune and microbial environment and associated risk factors constitutes the critical background for preventive, predictive, and personalized medicine that is essential for improving state-of-the-art medical care in patients with cervical precanceroses and cervical cancer. The review article focuses on the influence and potential diagnostic and therapeutic applications of the local innate immune system and the microbial markers in HPV-related cancers in the context of 3P medicine.

Positive influence of gut microbiota on the effects of Korean red ginseng in metabolic syndrome: a randomized, double-blind, placebo-controlled clinical trial.

BACKGROUND: Ginseng, a traditional herbal medicine, has been used for thousands of years to treat various diseases including metabolic syndrome (MS). However, the underlying mechanism(s) of such beneficial actions of ginseng against MS is poorly understood. Emerging evidence indicates a close association of the host gut microbiota with MS. The present study was conducted to examine, whether the beneficial effects of Korean red ginseng (KRG) against MS could be influenced by gut microbial population and whether gut microbial profile could be considered a valuable biomarker for targeted treatment strategy for MS in compliance with the predictive, preventive, and personalized medicine (PPPM / 3PM). METHODS: This clinical study was a randomized, double-blind, placebo-controlled trial evaluating the effects of KRG treatment for 8 weeks on patients with MS. The anthropometric parameters, vital signs, metabolic biomarkers, and gut microbial composition through 16S rRNA gene sequencing were assessed at the baseline and endpoint. The impact of KRG was also evaluated after categorizing the subjects into responders and non-responders, as well as enterotypes 1 and 2 based on their gut microbial profile at the baseline. RESULTS: Fifty out of 60 subjects who meet the MS criteria completed the trial without showing adverse reactions. The KRG treatment caused a significant decrease in systolic blood pressure (SBP). Microbial analysis revealed a decrease in Firmicutes, Proteobacteria, and an increase in Bacteroidetes in response to KRG. In patient stratification analysis, the responders showing marked improvement in the serum levels of lipid metabolic biomarkers TC and LDL due to the KRG treatment exhibited higher population of both the family Lachnospiraceae and order Clostridiales compared to the non-responders. The homeostasis model assessment-insulin resistance (HOMA-IR) and insulin level were decreased in enterotype 1 (Bacteroides-abundant group) and increased in enterotype 2 (prevotella-abundant group) following the KRG treatment. CONCLUSION: In this study, the effects of KRG on the glucose metabolism in MS patients were influenced by the relative abundances of gut microbial population and differed according to the individual enterotype. Therefore, the analysis of enterotype categories is considered to be helpful in predicting the effectiveness of KRG on glucose homeostasis of MS patients individually. This will further help to decide on the appropriate treatment strategy for MS, in compliance with the perspective of PPPM.

Making a complex dental care tailored to the person: population health in focus of predictive, preventive and personalised (3P) medical approach.

An evident underestimation of the targeted prevention of dental diseases is strongly supported by alarming epidemiologic statistics globally. For example, epidemiologists demonstrated 100% prevalence of dental caries in the Russian population followed by clinical manifestation of periodontal diseases. Inadequately provided oral health services in populations are caused by multi-factorial deficits including but not limited to low socio-economic status of affected individuals, lack of insurance in sub-populations, insufficient density of dedicated medical units. Another important aspect is the "participatory" medicine based on the active participation of population in maintaining oral health: healthcare will remain insufficient as long as the patient is not motivated and does not feel responsible for their oral health. To this end, nearly half of chronically diseased people do not comply with adequate medical services suffering from severely progressing pathologies. Noteworthy, the prominent risk factors and comorbidities linked to the severe disease course and poor outcomes in COVID-19-infected individuals, such as elderly, diabetes mellitus, hypertension and cardiovascular disease, are frequently associated with significantly altered oral microbiome profiles, systemic inflammatory processes and poor oral health. Suggested pathomechanisms consider potential preferences in the interaction between the viral particles and the host microbiota including oral cavity, the respiratory and gastrointestinal tracts. Since an aspiration of periodontopathic bacteria induces the expression of angiotensin-converting enzyme 2, the receptor for SARS-CoV-2, and production of inflammatory cytokines in the lower respiratory tract, poor oral hygiene and periodontal disease have been proposed as leading to COVID-19 aggravation. Consequently, the issue-dedicated expert recommendations are focused on the optimal oral hygiene as being crucial for improved individual outcomes and reduced morbidity under the COVID-19 pandemic condition. Current study demonstrated that age, gender, socio-economic status, quality of environment and life-style, oral hygiene quality, regularity of dental services requested, level of motivation and responsibility for own health status and corresponding behavioural patterns are the key parameters for the patient stratification considering person-tailored approach in a complex dental care in the population. Consequently, innovative screening programmes and adapted treatment schemes are crucial for the complex person-tailored dental care to improve individual outcomes and healthcare provided to the population.

Sleep quality and COVID-19 outcomes: the evidence-based lessons in the framework of predictive, preventive and personalised (3P) medicine.

Sleep quality and duration play a pivotal role in maintaining physical and mental health. In turn, sleep shortage, deprivation and disorders are per evidence the risk factors and facilitators of a broad spectrum of disorders, amongst others including depression, stroke, chronic inflammation, cancers, immune defence insufficiency and individual predisposition to infection diseases with poor outcomes, for example, related to the COVID-19 pandemic. Keeping in mind that COVID-19-related global infection distribution is neither the first nor the last pandemic severely affecting societies around the globe to the costs of human lives accompanied with enormous economic burden, lessons by predictive, preventive and personalised (3P) medical approach are essential to learn and to follow being better prepared to defend against global pandemics. To this end, under extreme conditions such as the current COVID-19 pandemic, the reciprocal interrelationship between the sleep quality and individual outcomes becomes evident, namely, at the levels of disease predisposition, severe versus mild disease progression, development of disease complications, poor outcomes and related mortality for both - population and healthcare givers. The latter is the prominent example clearly demonstrating the causality of severe outcomes, when the long-lasting work overload and shift work rhythm evidently lead to the sleep shortage and/or deprivation that in turn causes immune response insufficiency and strong predisposition to the acute infection with complications. This article highlights and provides an in-depth analysis of the concerted risk factors related to the sleep disturbances under the COVID-19 pandemic followed by the evidence-based recommendations in the framework of predictive, preventive and personalised medical approach.

Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment.

Since December 2019, the world has been devastated by the Coronavirus Disease 2019 (COVID-19) pandemic. Emergency Departments have been experiencing situations of urgency where clinical experts, without long experience and mature means in the fight against COVID-19, have to rapidly decide the most proper patient treatment. In this context, we introduce an artificially intelligent tool for effective and efficient Computed Tomography (CT)-based risk assessment to improve treatment and patient care. In this paper, we introduce a data-driven approach built on top of volume-of-interest aware deep neural networks for automatic COVID-19 patient risk assessment (discharged, hospitalized, intensive care unit) based on lung infection quantization through segmentation and, subsequently, CT classification. We tackle the high and varying dimensionality of the CT input by detecting and analyzing only a sub-volume of the CT, the Volume-of-Interest (VoI). Differently from recent strategies that consider infected CT slices without requiring any spatial coherency between them, or use the whole lung volume by applying abrupt and lossy volume down-sampling, we assess only the "most infected volume" composed of slices at its original spatial resolution. To achieve the above, we create, present and publish a new labeled and annotated CT dataset with 626 CT samples from COVID-19 patients. The comparison against such strategies proves the effectiveness of our VoI-based approach. We achieve remarkable performance on patient risk assessment evaluated on balanced data by reaching 88.88%, 89.77%, 94.73% and 88.88% accuracy, sensitivity, specificity and F1-score, respectively.

Flavonoids against the Warburg phenotype-concepts of predictive, preventive and personalised medicine to cut the Gordian knot of cancer cell metabolism.

The Warburg effect is characterised by increased glucose uptake and lactate secretion in cancer cells resulting from metabolic transformation in tumour tissue. The corresponding molecular pathways switch from oxidative phosphorylation to aerobic glycolysis, due to changes in glucose degradation mechanisms known as the 'Warburg reprogramming' of cancer cells. Key glycolytic enzymes, glucose transporters and transcription factors involved in the Warburg transformation are frequently dysregulated during carcinogenesis considered as promising diagnostic and prognostic markers as well as treatment targets. Flavonoids are molecules with pleiotropic activities. The metabolism-regulating anticancer effects of flavonoids are broadly demonstrated in preclinical studies. Flavonoids modulate key pathways involved in the Warburg phenotype including but not limited to PKM2, HK2, GLUT1 and HIF-1. The corresponding molecular mechanisms and clinical relevance of 'anti-Warburg' effects of flavonoids are discussed in this review article. The most prominent examples are provided for the potential application of targeted 'anti-Warburg' measures in cancer management. Individualised profiling and patient stratification are presented as powerful tools for implementing targeted 'anti-Warburg' measures in the context of predictive, preventive and personalised medicine.

Infections of the lung: a predictive, preventive and personalized perspective through the lens of evolution, the emergence of SARS-CoV-2 and its pathogenesis.

The long evolutionary battle between humans and pathogens has played an important role in shaping the current network of host-pathogen interactions. Each organ brings new challenges from the perspective of a pathogen to establish a suitable niche for survival while subverting the protective mechanisms of the host. Lungs, the organ for oxygen exchange, have been an easy target for pathogens due to its accessibility. The organ has evolved diverse capabilities to provide the flexibility required for an organism's health and at the same time maintain protective functionality to prevent and resolve assault by pathogens. The pathogenic invasions are strongly challenged by healthy lung architecture which includes the presence and activity of the epithelium, mucous, antimicrobial proteins, surfactants, and immune cells. Competitively, the pathogens in the form of viruses, bacteria, and fungi have evolved an arsenal of strategies that can over-ride the host's protective mechanisms. While bacteria such as Mycobacterium tuberculosis (M. tuberculosis) can survive in dormant form for years before getting active in humans, novel pathogens can wreak havoc as they pose a high risk of morbidity and mortality in a very short duration of time. Recently, a coronavirus strain SARS-CoV-2 has caused a pandemic which provides us an opportunity to look at the host manipulative strategies used by respiratory pathogens. Their ability to hide, modify, evade, and exploit cell's processes are key to their survival. While pathogens like M. tuberculosis have been infecting humans for thousands of years, SARS-CoV-2 has been the cause of the recent pandemic. Molecular understanding of the strategies used by these pathogens could greatly serve in design of predictive, preventive, personalized medicine (PPPM). In this article, we have emphasized on the clinically relevant evasive strategies of the pathogens in the lungs with emphasis on M. tuberculosis and SARS-CoV-2. The molecular basis of these evasive strategies illuminated through advances in genomics, cell, and structural biology can assist in the mapping of vulnerable molecular networks which can be exploited translationally. These evolutionary approaches can further assist in generating screening and therapeutic options for susceptible populations and could be a promising approach for the prediction, prevention of disease, and the development of personalized medicines. Further, tailoring the clinical data of COVID-19 patients with their physiological responses in light of known host-respiratory pathogen interactions can provide opportunities to improve patient profiling and stratification according to identified therapeutic targets.

Optimal multiparametric set-up modelled for best survival outcomes in palliative treatment of liver malignancies: unsupervised machine learning and 3 PM recommendations.

Over the last decade, a rapid rise in deaths due to liver disease has been observed especially amongst young people. Nowadays liver disease accounts for approximately 2 million deaths per year worldwide: 1 million due to complications of cirrhosis and 1 million due to viral hepatitis and hepatocellular carcinoma. Besides primary liver malignancies, almost all solid tumours are capable to spread metastases to the liver, in particular, gastrointestinal cancers, breast and genitourinary cancers, lung cancer, melanomas and sarcomas. A big portion of liver malignancies undergo palliative care. To this end, the paradigm of the palliative care in the liver cancer management is evolving from "just end of the life" care to careful evaluation of all aspects relevant for the survivorship. In the presented study, an evidence-based approach has been taken to target molecular pathways and subcellular components for modelling most optimal conditions with the longest survival rates for patients diagnosed with advanced liver malignancies who underwent palliative treatments. We developed an unsupervised machine learning (UML) approach to robustly identify patient subgroups based on estimated survival curves for each individual patient and each individual potential biomarker. UML using consensus hierarchical clustering of biomarker derived risk profiles resulted into 3 stable patient subgroups. There were no significant differences in age, gender, therapy, diagnosis or comorbidities across clusters. Survival times across clusters differed significantly. Furthermore, several of the biomarkers demonstrated highly significant pairwise differences between clusters after correction for multiple testing, namely, "comet assay" patterns of classes I, III, IV and expression rates of calgranulin A (S100), SOD2 and profilin-all measured ex vivo in circulating leucocytes. Considering worst, intermediate and best survival curves with regard to identified clusters and corresponding patterns of parameters measured, clear differences were found for "comet assay" and S100 expression patterns. In conclusion, multi-faceted cancer control within the palliative care of liver malignancies is crucial for improved disease outcomes including individualised patient profiling, predictive models and implementation of corresponding cost-effective risks mitigating measures detailed in the paper. The "proof-of-principle" model is presented.