Novel automated non-invasive detection of ocular surface squamous neoplasia using artificial intelligence.

Ocular surface squamous neoplasia (OSSN) is a common eye surface tumour, characterized by the growth of abnormal cells on the ocular surface. OSSN includes invasive squamous cell carcinoma (SCC), in which tumour cells penetrate the basement membrane and infiltrate the stroma, as well as non-invasive conjunctival intraepithelial neoplasia, dysplasia, and SCC in-situ thereby presenting a challenge in early detection and diagnosis. Early identification and precise demarcation of the OSSN border leads to straightforward and curative treatments, such as topical medicines, whereas advanced invasive lesions may need orbital exenteration, which carries a risk of death. Artificial intelligence (AI) has emerged as a promising tool in the field of eye care and holds potential for its application in OSSN management. AI algorithms trained on large datasets can analyze ocular surface images to identify suspicious lesions associated with OSSN, aiding ophthalmologists in early detection and diagnosis. AI can also track and monitor lesion progression over time, providing objective measurements to guide treatment decisions. Furthermore, AI can assist in treatment planning by offering personalized recommendations based on patient data and predicting the treatment response. This manuscript highlights the role of AI in OSSN, specifically focusing on its contributions in early detection and diagnosis, assessment of lesion progression, treatment planning, telemedicine and remote monitoring, and research and data analysis.

Diagnosis of pediatric central nervous system tumors using methylation profiling of cfDNA from cerebrospinal fluid.

Pediatric central nervous system tumors remain challenging to diagnose. Imaging approaches do not provide sufficient detail to discriminate between different tumor types, while the histopathological examination of tumor tissue shows high inter-observer variability. Recent studies have demonstrated the accurate classification of central nervous system tumors based on the DNA methylation profile of a tumor biopsy. However, a brain biopsy holds significant risk of bleeding and damaging the surrounding tissues. Liquid biopsy approaches analyzing circulating tumor DNA show high potential as an alternative and less invasive tool to study the DNA methylation pattern of tumors. Here, we explore the potential of classifying pediatric brain tumors based on methylation profiling of the circulating cell-free DNA (cfDNA) in cerebrospinal fluid (CSF). For this proof-of-concept study, we collected cerebrospinal fluid samples from 19 pediatric brain cancer patients via a ventricular drain placed for reasons of increased intracranial pressure. Analyses on the cfDNA showed high variability of cfDNA quantities across patients ranging from levels below the limit of quantification to 40 ng cfDNA per milliliter of CSF. Classification based on methylation profiling of cfDNA from CSF was correct for 7 out of 20 samples in our cohort. Accurate results were mostly observed in samples of high quality, more specifically those with limited high molecular weight DNA contamination. Interestingly, we show that centrifugation of the CSF prior to processing increases the fraction of fragmented cfDNA to high molecular weight DNA. In addition, classification was mostly correct for samples with high tumoral cfDNA fraction as estimated by computational deconvolution (> 40%). In summary, analysis of cfDNA in the CSF shows potential as a tool for diagnosing pediatric nervous system tumors especially in patients with high levels of tumoral cfDNA in the CSF. Further optimization of the collection procedure, experimental workflow and bioinformatic approach is required to also allow classification for patients with low tumoral fractions in the CSF.

A first assessment of the safe brain initiative care bundle for addressing postoperative delirium in the postanesthesia care unit.

BACKGROUND: Postoperative delirium (POD) following surgery is a prevalent and distressing condition associated with adverse patient outcomes and an increased healthcare burden. OBJECTIVES: To assess the effectiveness of the Safe Brain Initiative care bundle (SBI-CB) in reducing POD in the postanesthesia care unit (PACU). DESIGN: A multicenter, quality-improvement initiative with retrospective analysis of collected data. SETTING: The study was conducted in the operating rooms and postanesthesia care units (PACUs) of four hospitals across Denmark and Turkey. PATIENTS: The convenience sample of patients were aged ≥18 years, scheduled for surgery, and could communicate verbally. Age, sex, preoperative delirium, and the American Society for Anesthesiology physical status classification were used in statistical methods to control for potential confounding influences. INTERVENTION: The SBI-CB, 18 delirium-reducing recommendations aligned with international guidelines. The intervention included patient education, staff training, coordination meetings across centers, and a dashboard for the monitoring of outcomes in the PACU. MAIN OUTCOME MEASURES: The primary outcome was the POD trend in the PACU during implementation months, assessed through Nu-DESC screening at up to three time points in the PACU. We also examined the length of hospital stay. RESULTS: Data were collected from 18,697 adult patients across four hospitals. Initial POD incidence in the PACU after the first three months was 16.36% across all sites (n = 1021). POD in the PACU was observed across all age groups, with peak incidence in younger (18-35 years) and older (>75 years) patients. General anesthesia and longer surgical duration (>1 h) were identified as significant risk factors for POD in the PACU. Matched patients who experienced POD in the PACU had longer stays in hospital, with a mean increase from 35 to 69 h (p < 0.001). Implementation of the SBI-CB was associated with a decreased risk of POD in the PACU for each month of SBI-CB implementation (adjusted odds ratio 0.96, 95% confidence interval: [0.94, 0.97], p < 0.001). CONCLUSIONS: The presented pragmatic implementation of a multidisciplinary care bundle, encompassing pre-, intra-, and postoperative measures alongside outcome monitoring, has the potential to significantly reduce the incidence of POD in the PACU. Improved patient outcomes may be achieved for general surgical departments with patient cohorts not typically considered at risk for developing POD. TRIAL REGISTRATION: Clinicaltrials.gov, identifier NCT05765162.

Genetic Characterization of Kidney Failure of Unknown Etiology in Spain: Findings From the GENSEN Study.

RATIONALE & OBJECTIVE: Chronic kidney disease (CKD) of unknown etiology (CKDUE) is one of the main global causes of kidney failure. While genetic studies may identify an etiology in these patients, few studies have implemented genetic testing of CKDUE in population-based series of patients which was the focus of the GENSEN. STUDY DESIGN: Case series. SETTINGS & PARTICIPANTS: 818 patients aged ≤45 years at 51 Spanish centers with CKDUE, and either an estimated GFR <15 mL/min/1.73 m2 or treatment with maintenance dialysis or transplantation. OBSERVATIONS: Genetic testing for 529 genes associated to inherited nephropathies using high-throughput sequencing (HTS). Pathogenic and/or likely pathogenic (P/LP) gene variants concordant with the inheritance pattern were detected in 203 (24.8%) patients. Variants in type IV collagen genes were the most frequent (COL4A5, COL4A4, COL4A3; 35% of total gene variants), followed by NPHP1, PAX2, UMOD, MUC1 and INF2 (7.3%, 5.9%, 2.5%, 2.5% and 2.5% respectively). Overall, 87 novel variants classified as P/LP were identified. The top 5 most common previously undiagnosed diseases were Alport syndrome spectrum (35% of total positive reports), genetic podocytopathies (19%), nephronophthisis (11%), autosomal dominant tubulointerstitial kidney disease (7%) and congenital anomalies of the kidney and urinary tract (CAKUT: 5%). Family history of kidney disease was reported by 191 (23.3 %) participants and by 65/203 (32.0%) patients with P/LP variants. LIMITATIONS: Missing data. Selection bias resulting from voluntary enrollment. CONCLUSIONS: Genomic testing with HTS identified a genetic cause of kidney disease in approximately one quarter of young patients with CKDUE and advanced kidney disease. These findings suggest that genetic studies are a potentially useful tool for the evaluation of people with CKDUE.

A Multi-Biomarker Panel for Predicting Tocilizumab Response in Rheumatoid Arthritis Patients.

Rheumatoid arthritis (RA) is a chronic systemic autoimmune disease characterized by inflammation in the synovial lining of the joints. Key inflammatory cytokines such as interleukin-6 (IL-6), TNF-α, and others play a critical role in the activation of local synovial leukocytes and the induction of chronic inflammation. Tocilizumab (TCZ), a humanized anti-IL-6 receptor monoclonal antibody, has demonstrated significant clinical efficacy in treating RA patients. However, similar to other inflammatory cytokine blockers, such as TNF-alpha inhibitors, Interleukin-1 inhibitors, or CD20 inhibitors, some patients do not respond to treatment. To address this challenge, our study employed a high-precision proteomics approach to identify protein biomarkers capable of predicting clinical responses to Tocilizumab in RA patients. Through the use of data-independent acquisition (DIA) mass spectrometry, we analyzed serum samples from both TCZ responders and non-responders to discover potential biomarker candidates. These candidates were subsequently validated using individual serum samples from two independent cohorts: a training set (N=70) and a test set (N=18), allowing for the development of a robust multi-biomarker panel. The constructed multi-biomarker panel demonstrated an average discriminative power of 86% between response and non-response groups, with a high area under the curve (AUC) value of 0.84. Additionally, the panel exhibited 100% sensitivity and 60% specificity. Collectively, our multi-biomarker panel holds promise as a diagnostic tool to predict non-responders to TCZ treatment in RA patients.

Dataset of DNA methylation profiles of 189 pediatric central nervous system, soft tissue, and bone tumors.

Alterations in DNA methylation profiles belong to important mechanisms in cancer development, and their assessment can be utilized for rapid and precise diagnostics. Therefore, establishing datasets of methylation profiles can improve and deepen our understanding of the role of epigenetic changes in cancer development as well as improve our diagnostic capabilities. In this dataset, we generated NGS data for 189 samples of pediatric CNS, soft tissue, and bone tumors. The sequencing libraries were prepared using methyl capture bisulfite sequencing, an effective compromise between whole-genome bisulfite sequencing and array-based methods with a more limited scope of target regions. The larger part of the cohort was processed with the Agilent SureSelectXT Human Methyl-Seq kit (149 samples) and the rest with the Illumina TruSeq Methyl Capture EPIC Library Prep Kit (40 samples). The data presented in this article may help other researchers further elucidate the importance of methylation in diagnosing pediatric CNS tumors, soft tissue, and bone tumors.

The Role of Pharmacogenomics Studies for Precision Medicine Among Ethiopian Patients and Their Clinical Implications: A Scoping Review.

Background: Pharmacogenomics research is currently revolutionizing treatment optimization by discovering molecular markers. Medicines are the cornerstone of treatment for both acute and chronic diseases. Pharmacogenomics associated treatment response varies from 20% to 95%, resulting in from lack of efficacy to serious toxicity. Pharmacogenomics has emerged as a useful tool for therapy optimization and plays a bigger role in clinical care going forward. However, in Africa, in particular in Ethiopia, such studies are scanty and not generalizing. Therefore, the objective of this review was to outline such studies, generating comprehensive evidence and identify studied variants' association with treatment responses in Ethiopian patients. Methods: The Joanna Briggs Institute's updated 2020 methodological guidelines for conducting and guidance for scoping reviews were used. We meticulously adhered to the systemic review reporting items checklist and scoping review meta-analyses extension. Results: Two hundred twenty-nine possibly relevant studies were searched. These include: 64, 54, 21, 48 and 42 from PubMed, Scopus, Google Scholar, EMBASE, and manual search, respectively. Seventy-seven duplicate studies were removed. Thirty-nine papers were rejected with justification, whereas 58 studies were qualified for full-text screening. Finally 19 studies were examined. The primary pharmacogene that was found to have a significant influence on the pharmacokinetics of efavirenz was CYP2B6. Drug-induced liver injury has frequently identified toxicity among studied medications. Conclusion and Future Perspectives: Pharmacogenomics studies in Ethiopian populations are less abundant. The studies conducted focused on infectious diseases, specifically on HAART commonly efavirenz and backbone first-line anti-tuberculosis drugs. There is a high need for further pharmacogenomics research to verify the discrepancies among the studies and for guiding precision medicine. Systematic review and meta-analysis are also recommended for pooled effects of different parameters in pharmacogenomics studies.

Revolutionizing Neurology: The Role of Artificial Intelligence in Advancing Diagnosis and Treatment.

Artificial intelligence (AI) has emerged as a powerful tool in the field of neurology, significantly impacting the diagnosis and treatment of neurological disorders. Recent technological breakthroughs have given us access to a plethora of information relevant to many aspects of neurology. Neuroscience and AI share a long history of collaboration. Along with great potential, we encounter obstacles relating to data quality, ethics, and inherent difficulty in applying data science in healthcare. Neurological disorders pose intricate challenges due to their complex manifestations and variability. Automating image interpretation tasks, AI algorithms accurately identify brain structures and detect abnormalities. This accelerates diagnosis and reduces the workload on medical professionals. Treatment optimization benefits from AI simulations that model different scenarios and predict outcomes. These AI systems can currently perform many of the sophisticated perceptual and cognitive capacities of biological systems, such as object identification and decision making. Furthermore, AI is rapidly being used as a tool in neuroscience research, altering our understanding of brain functioning. It has the ability to revolutionize healthcare as we know it into a system in which humans and robots collaborate to deliver better care for our patients. Image analysis activities such as recognizing particular brain regions, calculating changes in brain volume over time, and detecting abnormalities in brain scans can be automated by AI systems. This lessens the strain on radiologists and neurologists while improving diagnostic accuracy and efficiency. It is now obvious that cutting-edge artificial intelligence models combined with high-quality clinical data will lead to enhanced prognostic and diagnostic models in neurological illness, permitting expert-level clinical decision aids across healthcare settings. In conclusion, AI's integration into neurology has revolutionized diagnosis, treatment, and research. As AI technologies advance, they promise to unravel the complexities of neurological disorders further, leading to improved patient care and quality of life. The symbiosis of AI and neurology offers a glimpse into a future where innovation and compassion converge to reshape neurological healthcare. This abstract provides a concise overview of the role of AI in neurology and its transformative potential.

Functional Nanomaterials for the Treatment of Osteoarthritis.

Osteoarthritis (OA) is the most common degenerative joint disease, affecting more than 595 million people worldwide. Nanomaterials possess superior physicochemical properties and can influence pathological processes due to their unique structural features, such as size, surface interface, and photoelectromagnetic thermal effects. Unlike traditional OA treatments, which suffer from short half-life, low stability, poor bioavailability, and high systemic toxicity, nanotherapeutic strategies for OA offer longer half-life, enhanced targeting, improved bioavailability, and reduced systemic toxicity. These advantages effectively address the limitations of traditional therapies. This review aims to inspire researchers to develop more multifunctional nanomaterials and promote their practical application in OA treatment.

Quantitative Angiography: The Dawn of a New Era in Cardiovascular Medicine.

This comprehensive review explores the transformative role of quantitative angiography in the landscape of cardiovascular medicine. Tracing the historical evolution of cardiovascular diagnostics, we emphasize the significance of angiography in diagnosis and treatment. The primary focus on quantitative angiography reveals its capacity to move beyond qualitative assessments, providing clinicians with precise measurements and objective parameters. This paradigm shift enhances diagnostic accuracy, promising far-reaching implications for the future of cardiovascular medicine. The ability to tailor interventions based on meticulous measurements optimizes therapeutic strategies and positions the field on the brink of a new era where personalized approaches become the norm. However, challenges such as image quality, radiation exposure, and interpretation variability persist, necessitating a collective call to action for continued research and development. As we confront these issues, collaborative efforts across disciplines are essential to refine existing technologies and usher in innovative solutions. This review concludes with a resounding call for ongoing research initiatives, large-scale clinical studies, and collective commitment to propel quantitative angiography into a universally accepted standard, ensuring its full realization in enhancing patient care and outcomes in cardiovascular medicine.

Revolutionary Point-of-Care Wearable Diagnostics for Early Disease Detection and Biomarker Discovery through Intelligent Technologies.

Early-stage disease detection, particularly in Point-Of-Care (POC) wearable formats, assumes pivotal role in advancing healthcare services and precision-medicine. Public benefits of early detection extend beyond cost-effectively promoting healthcare outcomes, to also include reducing the risk of comorbid diseases. Technological advancements enabling POC biomarker recognition empower discovery of new markers for various health conditions. Integration of POC wearables for biomarker detection with intelligent frameworks represents ground-breaking innovations enabling automation of operations, conducting advanced large-scale data analysis, generating predictive models, and facilitating remote and guided clinical decision-making. These advancements substantially alleviate socioeconomic burdens, creating a paradigm shift in diagnostics, and revolutionizing medical assessments and technology development. This review explores critical topics and recent progress in development of 1) POC systems and wearable solutions for early disease detection and physiological monitoring, as well as 2) discussing current trends in adoption of smart technologies within clinical settings and in developing biological assays, and ultimately 3) exploring utilities of POC systems and smart platforms for biomarker discovery. Additionally, the review explores technology translation from research labs to broader applications. It also addresses associated risks, biases, and challenges of widespread Artificial Intelligence (AI) integration in diagnostics systems, while systematically outlining potential prospects, current challenges, and opportunities.

Broadening the scope of multigene panel analysis for adult epilepsy patients.

OBJECTIVE: Epilepsy is a suitable target for gene panel sequencing because a considerable portion of epilepsy is now explained by genetic components, especially in syndromic cases. However, previous gene panel studies on epilepsy have mostly focused on pediatric patients. METHODS: We enrolled adult epilepsy patients meeting any of the following criteria: family history of epilepsy, seizure onset age ≤ 19 years, neuronal migration disorder, and seizure freedom not achieved by dual anti-seizure medications. We sequenced the exonic regions of 211 epilepsy genes in these patients. To confirm the pathogenicity of a novel MTOR truncating variant, we electroporated vectors with different MTOR variants into developing mouse brains. RESULTS: A total of 92 probands and 4 affected relatives were tested, and the proportion of intellectual disability (ID) and/or developmental disability (DD) was 21.7%. As a result, twelve probands (13.0%) had pathogenic or likely pathogenic variants in the following genes or regions: DEPDC5, 15q12-q13 duplication (n = 2), SLC6A1, SYNGAP1, EEF1A2, LGI1, MTOR, KCNQ2, MEF2C, and TSC1 (n = 1). We confirmed the functional impact of a novel truncating mutation in the MTOR gene (c.7570C > T, p.Gln2524Ter) that disrupted neuronal migration in a mouse model. The diagnostic yield was higher in patients with ID/DD or childhood-onset seizures. We also identified additional candidate variants in 20 patients that could be reassessed by further studies. SIGNIFICANCE: Our findings underscore the clinical utility of gene panel sequencing in adult epilepsy patients suspected of having genetic etiology, especially those with ID/DD or early-onset seizures. Gene panel sequencing could not only lead to genetic diagnosis in a substantial portion of adult epilepsy patients but also inform more precise therapeutic decisions based on their genetic background. PLAIN LANGUAGE SUMMARY: This study demonstrated the effectiveness of gene panel sequencing in adults with epilepsy, revealing pathogenic or likely pathogenic variants in 13.0% of patients. Higher diagnostic yields were observed in those with neurodevelopmental disorders or childhood-onset seizures. Additionally, we have shown that expanding genetic studies into adult patients would uncover new types of pathogenic variants for epilepsy, contributing to the advancement of precision medicine for individuals with epilepsy. In conclusion, our results highlight the practical value of employing gene panel sequencing in adult epilepsy patients, particularly when genetic etiology is clinically suspected.

Leveraging human-mouse studies to advance the genetics of hearing impairment in Africa.

Mouse models are used extensively to understand human pathobiology and mechanistic functions of disease-associated loci. However, in this review, we investigate the potential of using genetic mouse models to identify genetic markers that can disrupt hearing thresholds in mice and then target the hearing-enriched orthologues and loci in humans. Currently, little is known about the real prevalence of genes that cause hearing impairment (HI) in Africa. Pre-screening mouse cell lines to identify orthologues of interest has the potential to improve the genetic diagnosis for HI in Africa to a significant percentage, for example, 10-20%. Furthermore, the functionality of a candidate gene derived from mouse screening with heterogeneous genetic backgrounds and multi-omic approaches can shed light on the molecular, genetic heterogeneity and plausible mode of inheritance of a gene in hearing-impaired individuals especially in the absence of large families to investigate.

Exosomes in Bone Cancer: Unveiling their Vital Role in Diagnosis, Prognosis, and Therapeutic Advancements.

Bone cancer among adolescents and children exhibits varying survival outcomes based on disease state. While localized bone cancer cases have a survival rate exceeding 70%, metastatic, refractory, and recurrent forms are associated with significantly poorer prognoses. Initially believed to be mere vehicles for cellular waste disposal, exosomes are now recognized as extracellular vesicles facilitating intercellular communication. These vesicles influence cellular behaviors by transporting various biomolecules, such as proteins, DNA, RNA, and lipids, among cells. The role of exosomes in regulating the progression of bone cancer is increasingly evident, impacting critical processes like tumorigenesis, proliferation, metastasis, angiogenesis, immune evasion, and drug resistance. Current research underscores the substantial potential of exosomes in promoting the progression and development of bone cancer. This review delves into the complex process of exosome biogenesis, the variety of cell-derived exosome sources, and their applications in drug delivery and therapeutics. It also examines ongoing clinical trials focused on exosome cargo levels and discusses the challenges and future directions in exosome research. Unlike costly and invasive traditional diagnostic methods, exosomal biomarkers offer a non-invasive, cost-effective, and readily accessible routine screening through simple fluid collection that aims to inspire researchers to investigate the potential of exosomes for cancer theragnostic. Through comprehensive exploration of these areas, the review seeks to enhance understanding and foster innovative solutions to cancer biology in the near future.

Theranostic digital twins: Concept, framework and roadmap towards personalized radiopharmaceutical therapies.

Radiopharmaceutical therapy (RPT) is a rapidly developing field of nuclear medicine, with several RPTs already well established in the treatment of several different types of cancers. However, the current approaches to RPTs often follow a somewhat inflexible "one size fits all" paradigm, where patients are administered the same amount of radioactivity per cycle regardless of their individual characteristics and features. This approach fails to consider inter-patient variations in radiopharmacokinetics, radiation biology, and immunological factors, which can significantly impact treatment outcomes. To address this limitation, we propose the development of theranostic digital twins (TDTs) to personalize RPTs based on actual patient data. Our proposed roadmap outlines the steps needed to create and refine TDTs that can optimize radiation dose to tumors while minimizing toxicity to organs at risk. The TDT models incorporate physiologically-based radiopharmacokinetic (PBRPK) models, which are additionally linked to a radiobiological optimizer and an immunological modulator, taking into account factors that influence RPT response. By using TDT models, we envisage the ability to perform virtual clinical trials, selecting therapies towards improved treatment outcomes while minimizing risks associated with secondary effects. This framework could empower practitioners to ultimately develop tailored RPT solutions for subgroups and individual patients, thus improving the precision, accuracy, and efficacy of treatments while minimizing risks to patients. By incorporating TDT models into RPTs, we can pave the way for a new era of precision medicine in cancer treatment.

Fast and efficient isolation of murine circulating tumor cells using screencell technology for pre-clinical analyzes.

Circulating tumor cells (CTCs) represent a rare and heterogeneous population of cancer cells that are detached from the tumor site and entered blood or lymphatic circulation. Once disseminated in distant tissues, CTCs could remain dormant or create a tumor mass causing serious danger for patients. Many technologies exist to isolate CTCs from patients' blood samples, mostly based on microfluidic systems or by sorting them according to their surface antigens, notably EpCAM, and/or cytokeratins for carcinoma. ScreenCell has developed an easy-to-use, antigen-independent, rapid, cost-effective, and efficient technology that isolates CTCs according to their bigger size compared to the blood cells. This study provides the technical information necessary to isolate and characterize CTCs from mouse blood. By using blood samples from transgenic mice with breast cancer or from WT mice in which we spiked cancer cells, we showed that ScreenCell technology is compatible with standard EDTA blood collection tubes. Furthermore, the ScreenCell Cyto kit could treat up to 500 µl and the ScreenCell MB kit up to 200 µl of mouse blood. As the ScreenCell MB kit captures unaltered live CTCs, we have shown that their DNA could be efficiently extracted, and the isolated cells could be grown in culture. In conclusion, ScreenCell provides a rapid, easy, antigen-independent, cost-effective, and efficient technology to isolate and characterize CTCs from the blood samples of cancer patients and murine models. Thanks to this technology CTCs could be captured fixed or alive. Murine cancer models are extensively used in pre-clinical studies. Therefore, this study demonstrates the crucial technical points necessary while manipulating mouse blood samples using ScreenCell technology.

A deep learning approach for overall survival prediction in lung cancer with missing values.

BACKGROUND AND OBJECTIVE: In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges. METHODS: We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time. RESULTS: We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used. CONCLUSIONS: The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.

Individual longitudinal changes in DNA-methylome identify signatures of early-life adversity and correlate with later outcome.

Adverse early-life experiences (ELA) affect a majority of the world's children. Whereas the enduring impact of ELA on cognitive and emotional health is established, there are no tools to predict vulnerability to ELA consequences in an individual child. Epigenetic markers including peripheral-cell DNA-methylation profiles may encode ELA and provide predictive outcome markers, yet the interindividual variance of the human genome and rapid changes in DNA methylation in childhood pose significant challenges. Hoping to mitigate these challenges we examined the relation of several ELA dimensions to DNA methylation changes and outcome using a within-subject longitudinal design and a high methylation-change threshold. DNA methylation was analyzed in buccal swab/saliva samples collected twice (neonatally and at 12 months) in 110 infants. We identified CpGs differentially methylated across time for each child and determined whether they associated with ELA indicators and executive function at age 5. We assessed sex differences and derived a sex-dependent 'impact score' based on sites that most contributed to methylation changes. Changes in methylation between two samples of an individual child reflected age-related trends and correlated with executive function years later. Among tested ELA dimensions and life factors including income to needs ratios, maternal sensitivity, body mass index and infant sex, unpredictability of parental and household signals was the strongest predictor of executive function. In girls, high early-life unpredictability interacted with methylation changes to presage executive function. Thus, longitudinal, within-subject changes in methylation profiles may provide a signature of ELA and a potential predictive marker of individual outcome.

scDrug+: predicting drug-responses using single-cell transcriptomics and molecular structure.

Predicting drug responses based on individual transcriptomic profiles holds promise for refining prognosis and advancing precision medicine. Although many studies have endeavored to predict the responses of known drugs to novel transcriptomic profiles, research into predicting responses for newly discovered drugs remains sparse. In this study, we introduce scDrug+, a comprehensive pipeline that seamlessly integrates single-cell analysis with drug-response prediction. Importantly, scDrug+ is equipped to predict the response of new drugs by analyzing their molecular structures. The open-source tool is available as a Docker container, ensuring ease of deployment and reproducibility. It can be accessed at https://github.com/ailabstw/scDrugplus.