Exploring Molecular Mechanisms and Biomarkers in COPD: An Overview of Current Advancements and Perspectives.

Chronic obstructive pulmonary disease (COPD) plays a significant role in global morbidity and mortality rates, typified by progressive airflow restriction and lingering respiratory symptoms. Recent explorations in molecular biology have illuminated the complex mechanisms underpinning COPD pathogenesis, providing critical insights into disease progression, exacerbations, and potential therapeutic interventions. This review delivers a thorough examination of the latest progress in molecular research related to COPD, involving fundamental molecular pathways, biomarkers, therapeutic targets, and cutting-edge technologies. Key areas of focus include the roles of inflammation, oxidative stress, and protease-antiprotease imbalances, alongside genetic and epigenetic factors contributing to COPD susceptibility and heterogeneity. Additionally, advancements in omics technologies-such as genomics, transcriptomics, proteomics, and metabolomics-offer new avenues for comprehensive molecular profiling, aiding in the discovery of novel biomarkers and therapeutic targets. Comprehending the molecular foundation of COPD carries substantial potential for the creation of tailored treatment strategies and the enhancement of patient outcomes. By integrating molecular insights into clinical practice, there is a promising pathway towards personalized medicine approaches that can improve the diagnosis, treatment, and overall management of COPD, ultimately reducing its global burden.

Functional Genomics in Psoriasis.

Psoriasis is an autoimmune cutaneous condition that significantly impacts quality of life and represents a burden on society due to its prevalence. Genome-wide association studies (GWASs) have pinpointed several psoriasis-related risk loci, underlining the disease's complexity. Functional genomics is paramount to unveiling the role of such loci in psoriasis and disentangling its complex nature. In this review, we aim to elucidate the main findings in this field and integrate our discussion with gold-standard techniques in molecular biology-i.e., Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-and high-throughput technologies. These tools are vital to understanding how disease risk loci affect gene expression in psoriasis, which is crucial in identifying new targets for personalized treatments in advanced precision medicine.

A genome-wide CRISPR screen reveals that antagonism of glutamine metabolism sensitizes head and neck squamous cell carcinoma to ferroptotic cell death.

Glutamine is a conditionally essential amino acid for the growth and survival of rapidly proliferating cancer cells. Many cancers are addicted to glutamine, and as a result, targeting glutamine metabolism has been explored clinically as a therapeutic approach. Glutamine-catalyzing enzymes are highly expressed in primary and metastatic head and neck squamous cell carcinoma (HNSCC). However, the nature of the glutamine-associated pathways in this aggressive cancer type has not been elucidated. Here, we explored the therapeutic potential of a broad glutamine antagonist, DRP-104 (sirpiglenastat), in HNSCC tumors and aimed at shedding light on glutamine-dependent pathways in this disease. We observed a potent antitumoral effect of sirpiglenastat in HPV- and HPV + HNSCC xenografts. We conducted a whole-genome CRISPR screen and metabolomics analyses to identify mechanisms of sensitivity and resistance to glutamine metabolism blockade. These approaches revealed that glutamine metabolism blockade results in the rapid buildup of polyunsaturated fatty acids (PUFAs) via autophagy nutrient-sensing pathways. Finally, our analysis demonstrated that GPX4 mediates the protection of HNSCC cells from accumulating toxic lipid peroxides; hence, glutamine blockade sensitizes HNSCC cells to ferroptosis cell death upon GPX4 inhibition. These findings demonstrate the therapeutic potential of sirpiglenastat in HNSCC and establish a novel link between glutamine metabolism and ferroptosis, which may be uniquely translated into targeted glutamine-ferroptosis combination therapies.

Clinical Impact of Telomere Length Testing for Interstitial Lung Disease.

BACKGROUND: Shortened telomere length (TL) is a genomic risk factor for fibrotic interstitial lung disease (ILD), but its role in clinical management is unknown. RESEARCH QUESTION: What is the clinical impact of TL testing on the management of ILD? STUDY DESIGN AND METHODS: Patients were evaluated in the Columbia University ILD clinic and underwent CLIA-certified TL testing by flow cytometry and fluorescence in-situ hybridization (FlowFISH) as part of clinical management. Short TL was defined as below the 10th age-adjusted percentile for either granulocytes or lymphocytes by FlowFISH. Patients were offered genetic counseling and testing if they had short TL or a family history of ILD. FlowFISH TL was compared against research qPCR TL measurement. RESULTS: A total of 108 patients underwent TL testing, including those with clinical features of short telomere syndrome such as familial pulmonary fibrosis (50%) or extrapulmonary manifestations in the patient (25%) or a relative (41%). The overall prevalence of short TL was 46% and was similar across clinical ILD diagnoses. The number of short telomere clinical features was independently associated with detecting short TL (OR 2.00, 95% CI [1.27, 3.32]). TL testing led to clinical management changes for 35 (32%) patients, most commonly resulting in reduction or avoidance of immunosuppression. Of the patients who underwent genetic testing (n=34), a positive or candidate diagnostic finding in telomere-related genes was identified in 10 (29%) patients. Inclusion of TL testing below the 1st percentile helped reclassify 8 of 9 variants of uncertain significance (VUS) into actionable findings. The qPCR test correlated with FlowFISH, but age-adjusted percentile cutoffs may not be equivalent between the two assays. INTERPRETATION: Incorporating TL testing in ILD impacted clinical management and led to the discovery of new actionable genetic variants.

Lung Adenocarcinoma Systems Biomarker and Drug Candidates Identified by Machine Learning, Gene Expression Data, and Integrative Bioinformatics Pipeline.

Lung adenocarcinoma (LUAD) is a significant planetary health challenge with its high morbidity and mortality rate, not to mention the marked interindividual variability in treatment outcomes and side effects. There is an urgent need for robust systems biomarkers that can help with early cancer diagnosis, prediction of treatment outcomes, and design of precision/personalized medicines for LUAD. The present study aimed at systems biomarkers of LUAD and deployed integrative bioinformatics and machine learning tools to harness gene expression data. Predictive models were developed to stratify patients based on prognostic outcomes. Importantly, we report here several potential key genes, for example, PMEL and BRIP1, and pathways implicated in the progression and prognosis of LUAD that could potentially be targeted for precision/personalized medicine in the future. Our drug repurposing analysis and molecular docking simulations suggested eight drug candidates for LUAD such as heat shock protein 90 inhibitors, cardiac glycosides, an antipsychotic agent (trifluoperazine), and a calcium ionophore (ionomycin). In summary, this study identifies several promising leads on systems biomarkers and drug candidates for LUAD. The findings also attest to the importance of integrative bioinformatics, structural biology and machine learning techniques in biomarker discovery, and precision oncology research and development.

Congenital syndromic Chiari-like malformation (CSCM) in Holstein cattle: towards unravelling of possible genetic causes.

BACKGROUND: Chiari malformation type II (CMII) was originally reported in humans as a rare disorder characterized by the downward herniation of the hindbrain and towering cerebellum. The congenital brain malformation is usually accompanied by spina bifida, a congenital spinal anomaly resulting from incomplete closure of the dorsal aspect of the spinal neural tube, and occasionally by other lesions. A similar disorder has been reported in several animal species, including cattle, particularly as a congenital syndrome. A cause of congenital syndromic Chiari-like malformation (CSCM) in cattle has not been reported to date. We collected a series of 14 CSCM-affected Holstein calves (13 purebred, one Red Danish Dairy F1 cross) and performed whole-genome sequencing (WGS). WGS was performed on 33 cattle, including eight cases with parents (trio-based; group 1), three cases with one parent (group 2), and three single cases (solo-based; group 3). RESULTS: Sequencing-based genome-wide association study of the 13 Holstein calves with CSCM and 166 controls revealed no significantly associated genome region. Assuming a single Holstein breed-specific recessive allele, no region of shared homozygosity was detected suggesting heterogeneity. Subsequent filtering for protein-changing variants that were only homozygous in the genomes of the individual cases allowed the identification of two missense variants affecting different genes, SHC4 in case 4 in group 1 and WDR45B in case 13 in group 3. Furthermore, these two variants were only observed in Holstein cattle when querying WGS data of > 5,100 animals. Alternatively, potential de novo mutational events were assessed in each case. Filtering for heterozygous private protein-changing variants identified one DYNC1H1 frameshift variant as a candidate causal dominant acting allele in case 12 in group 3. Finally, the presence of larger structural DNA variants and chromosomal abnormalities was investigated in all cases. Depth of coverage analysis revealed two different partial monosomies of chromosome 2 segments in cases 1 and 7 in group 1 and a trisomy of chromosome 12 in the WDR45B homozygous case 13 in group 3. CONCLUSIONS: This study presents for the first time a detailed genomic evaluation of CSCM in Holstein cattle and suggests an unexpected genetic and allelic heterogeneity considering the mode of inheritance, as well as the type of variant. For the first time, we propose candidate causal variants that may explain bovine CSCM in a certain proportion of affected calves. We present cattle as a large animal model for human CMII and propose new genes and genomic variants as possible causes for related diseases in both animals and humans.

Advancing healthcare: the role and impact of AI and foundation models.

BACKGROUND: The integration of artificial intelligence (AI) into the healthcare domain is a monumental shift with profound implications for diagnostics, medical interventions, and the overall structure of healthcare systems. PURPOSE: This study explores the transformative journey of foundation AI models in healthcare, shedding light on the challenges, ethical considerations, and vast potential they hold for improving patient outcome and system efficiency. Notably, in this investigation we observe a relatively slow adoption of AI within the public sector of healthcare. The evolution of AI in healthcare is un-paralleled, especially its prowess in revolutionizing diagnostic processes. RESULTS: This research showcases how these foundational models can unravel hidden patterns within complex medical datasets. The impact of AI reverberates through medical interventions, encompassing pathology, imaging, genomics, and personalized healthcare, positioning AI as a cornerstone in the quest for precision medicine. The paper delves into the applications of generative AI models in critical facets of healthcare, including decision support, medical imaging, and the prediction of protein structures. The study meticulously evaluates various AI models, such as transfer learning, RNN, autoencoders, and their roles in the healthcare landscape. A pioneering concept introduced in this exploration is that of General Medical AI (GMAI), advocating for the development of reusable and flexible AI models. CONCLUSION: The review article discusses how AI can revolutionize healthcare by stressing the significance of transparency, fairness and accountability, in AI applications regarding patient data privacy and biases. By tackling these issues and suggesting a governance structure the article adds to the conversation about AI integration in healthcare environments.

Development and validation of an LC-MS/MS method for ruxolitinib quantification: advancing personalized therapy in hematologic malignancies.

Background: Hematologic malignancies such as leukemia and lymphoma present treatment challenges due to their genetic and molecular heterogeneity. Ruxolitinib, a Janus kinase (JAK) inhibitor, has demonstrated efficacy in managing these cancers. However, optimal therapeutic outcomes are contingent upon maintaining drug levels within a therapeutic window, highlighting the necessity for precise drug monitoring. Methods: We developed a sensitive liquid chromatography-tandem mass spectrometry (LC-MS/MS) method to quantify ruxolitinib in human plasma, improving upon traditional methods in specificity, sensitivity, and efficiency. The process involved the use of advanced chromatographic techniques and robust mass spectrometric conditions to ensure high accuracy and minimal matrix effects. The study was conducted using samples from 20 patients undergoing treatment, with calibration standards ranging from 10 to 2000 ng/mL. Results: The method displayed linearity (R 2 > 0.99) across the studied range and proved highly selective with no significant interference observed. The method's precision and accuracy met FDA guidelines, with recovery rates consistently exceeding 85%. Clinical application demonstrated significant variability in ruxolitinib plasma levels among patients, reinforcing the need for individualized dosing schedules. Conclusion: The validated LC-MS/MS method offers a reliable and efficient tool for the therapeutic drug monitoring of ruxolitinib, facilitating personalized treatment approaches in hematologic malignancies. This approach promises to enhance patient outcomes by optimizing dosing to reduce toxicity and improve efficacy.

Radiogenomics as an Integrated Approach to Glioblastoma Precision Medicine.

PURPOSE OF REVIEW: Isocitrate dehydrogenase wild-type glioblastoma is the most aggressive primary brain tumour in adults. Its infiltrative nature and heterogeneity confer a dismal prognosis, despite multimodal treatment. Precision medicine is increasingly advocated to improve survival rates in glioblastoma management; however, conventional neuroimaging techniques are insufficient in providing the detail required for accurate diagnosis of this complex condition. RECENT FINDINGS: Advanced magnetic resonance imaging allows more comprehensive understanding of the tumour microenvironment. Combining diffusion and perfusion magnetic resonance imaging to create a multiparametric scan enhances diagnostic power and can overcome the unreliability of tumour characterisation by standard imaging. Recent progress in deep learning algorithms establishes their remarkable ability in image-recognition tasks. Integrating these with multiparametric scans could transform the diagnosis and monitoring of patients by ensuring that the entire tumour is captured. As a corollary, radiomics has emerged as a powerful approach to offer insights into diagnosis, prognosis, treatment, and tumour response through extraction of information from radiological scans, and transformation of these tumour characteristics into quantitative data. Radiogenomics, which links imaging features with genomic profiles, has exhibited its ability in characterising glioblastoma, and determining therapeutic response, with the potential to revolutionise management of glioblastoma. The integration of deep learning algorithms into radiogenomic models has established an automated, highly reproducible means to predict glioblastoma molecular signatures, further aiding prognosis and targeted therapy. However, challenges including lack of large cohorts, absence of standardised guidelines and the 'black-box' nature of deep learning algorithms, must first be overcome before this workflow can be applied in clinical practice.

Machine Learning for Predicting Biologic Agent Efficacy in Ulcerative Colitis: An Analysis for Generalizability and Combination with Computational Models.

Machine learning (ML) has been applied to predict the efficacy of biologic agents in ulcerative colitis (UC). ML can offer precision, personalization, efficiency, and automation. Moreover, it can improve decision support in predicting clinical outcomes. However, it faces challenges related to data quality and quantity, overfitting, generalization, and interpretability. This paper comments on two recent ML models that predict the efficacy of vedolizumab and ustekinumab in UC. Models that consider multiple pathways, multiple ethnicities, and combinations of real-world and clinical trial data are required for optimal shared decision-making and precision medicine. This paper also highlights the potential of combining ML with computational models to enhance clinical outcomes and personalized healthcare. Key Insights: (1) ML offers precision, personalization, efficiency, and decision support for predicting the efficacy of biologic agents in UC. (2) Challenging aspects in ML prediction include data quality, overfitting, and interpretability. (3) Multiple pathways, multiple ethnicities, and combinations of real-world and clinical trial data should be considered in predictive models for optimal decision-making. (4) Combining ML with computational models may improve clinical outcomes and personalized healthcare.

Gene-Based Predictive Modelling for Enhanced Detection of Systemic Lupus Erythematosus Using CNN-Based DL Algorithm.

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune disease that presents with a diverse array of clinical signs and unpredictable disease progression. Conventional diagnostic methods frequently fall short in terms of sensitivity and specificity, which can result in delayed diagnosis and less-than-optimal management. In this study, we introduce a novel approach for improving the identification of SLE through the use of gene-based predictive modelling and Stacked deep learning classifiers. The study proposes a new method for diagnosing SLE using Stacked Deep Learning Classifiers (SDLC) trained on Gene Expression Omnibus (GEO) database data. By combining transcriptomic data from GEO with clinical features and laboratory results, the SDLC model achieves a remarkable accuracy value of 0.996, outperforming traditional methods. Individual models within the SDLC, such as SBi-LSTM and ACNN, achieved accuracies of 92% and 95%, respectively. The SDLC's ensemble learning approach allows for identifying complex patterns in multi-modal data, enhancing accuracy in diagnosing SLE. This study emphasises the potential of deep learning methods, in conjunction with open repositories like GEO, to advance the diagnosis and management of SLE. Overall, this research shows strong performance and potential for improving precision medicine in managing SLE.

Immunological Signatures for Early Detection of Human Head and Neck Squamous Cell Carcinoma through RNA Transcriptome Analysis of Blood Platelets.

Although there has been a reduction in head and neck squamous cell carcinoma occurrence, it continues to be a serious global health concern. The lack of precise early diagnostic biomarkers and postponed diagnosis in the later stages are notable constraints that contribute to poor survival rates and emphasize the need for innovative diagnostic methods. In this study, we employed machine learning alongside weighted gene co-expression network analysis (WGCNA) and network biology to investigate the gene expression patterns of blood platelets, identifying transcriptomic markers for HNSCC diagnosis. Our comprehensive examination of publicly available gene expression datasets revealed nine genes with significantly elevated expression in samples from individuals diagnosed with HNSCC. These potential diagnostic markers were further assessed using TCGA and GTEx datasets, demonstrating high accuracy in distinguishing between HNSCC and non-cancerous samples. The findings indicate that these gene signatures could revolutionize early HNSCC identification. Additionally, the study highlights the significance of tumor-educated platelets (TEPs), which carry RNA signatures indicative of tumor-derived material, offering a non-invasive source for early-detection biomarkers. Despite using platelet and tumor samples from different individuals, our results suggest that TEPs reflect the transcriptomic and epigenetic landscape of tumors. Future research should aim to directly correlate tumor and platelet samples from the same patients to further elucidate this relationship. This study underscores the potential of these biomarkers in transforming early diagnosis and personalized treatment strategies for HNSCC, advocating for further research to validate their predictive and therapeutic potential.

Emerging Therapeutic Strategies to Overcome Drug Resistance in Cancer Cells.

The rise of drug resistance in cancer cells presents a formidable challenge in modern oncology, necessitating the exploration of innovative therapeutic strategies. This review investigates the latest advancements in overcoming drug resistance mechanisms employed by cancer cells, focusing on emerging therapeutic modalities. The intricate molecular insights into drug resistance, including genetic mutations, efflux pumps, altered signaling pathways, and microenvironmental influences, are discussed. Furthermore, the promising avenues offered by targeted therapies, combination treatments, immunotherapies, and precision medicine approaches are highlighted. Specifically, the synergistic effects of combining traditional cytotoxic agents with molecularly targeted inhibitors to circumvent resistance pathways are examined. Additionally, the evolving landscape of immunotherapeutic interventions, including immune checkpoint inhibitors and adoptive cell therapies, is explored in terms of bolstering anti-tumor immune responses and overcoming immune evasion mechanisms. Moreover, the significance of biomarker-driven strategies for predicting and monitoring treatment responses is underscored, thereby optimizing therapeutic outcomes. For insights into the future direction of cancer treatment paradigms, the current review focused on prevailing drug resistance challenges and improving patient outcomes, through an integrative analysis of these emerging therapeutic strategies.

CT-based radiogenomics of intrahepatic cholangiocarcinoma.

BACKGROUND: Intrahepatic cholangiocarcinoma (ICC) is an aggressive disease with increasing incidence and its genetic alterations could be the target of systemic therapies. AIMS: To elucidate if radiomics extracted from computed tomography (CT) may non-invasively predict ICC genetic alterations. METHODS: All consecutive patients with a diagnosis of a mass-forming ICC (01/2016-06/2022) were considered. Inclusion criteria were availability of a high-quality contrast-enhanced CT and molecular profiling by NGS or FISH for FGFR2 fusion/rearrangement. The CT scan at diagnosis was considered. Genetic analyses were performed on surgical specimens (resectable patients) or biopsies (unresectable ones). The radiomic features were extracted using the LifeX software. Multivariate predictive models of the commonest genetic alterations were built. RESULTS: In the 90 enrolled patients (58 NGS/32 FISH, median age 65 years), the most common genetic alterations were FGFR2 (20/90), IDH1 (10/58), and KRAS (9/58). At internal validation, the combined clinical-radiomic models achieved the best performance for the prediction of FGFR2 (AUC = 0.892) and IDH1 status (AUC = 0.819), outperforming the pure clinical and radiomic models. The radiomic model for predicting KRAS mutations achieved an AUC = 0.767 (vs. 0.660 of the clinical model) without further improvements with the addition of clinical features. CONCLUSIONS: CT-based radiomics provides a reliable non-invasive prediction of ICC genetic status with a major impact on therapeutic strategies.

Prevalence and Factors Associated With Awareness of Precision Medicine Among Individuals With Depression and Anxiety.

OBJECTIVE: This study investigates the prevalence and determinants of awareness of precision medicine among a nationally representative sample of individuals with self-reported depression and anxiety in the United States." METHODS: Data were obtained from the Health Information National Trends Survey (HINTS) 5, Cycle 4, which is a study administered by the National Cancer Institute and is nationally representative. The survey, conducted between February and June 2020, targeted non-institutionalized, civilian US adults aged 18 years and older. Utilizing survey-weighted logistic regression, predictors of precision medicine awareness were assessed, encompassing sociodemographic, health-related, and technological factors. RESULTS: Among 890 individuals with self-reported depression and/or anxiety, approximately 15.3% reported awareness of precision medicine. Participants who had a higher level of education and those who had increased health-linked social media usage were three times more likely to be aware of precision medicine compared to those who did not. Old age was also positively associated with increased awareness. CONCLUSION: The present study's findings have disclosed an alarming lack of awareness of precision medicine, particularly among mentally ill persons with anxiety or depression, in which the targeted subgroups, including individuals with lower education levels and limited health-linked social media utilization, indicated lower levels of awareness. As such, it is recommended that such disparities be tackled using customized interventions along with educational initiatives, as this is likely to improve awareness levels while also ensuring equitable and increased access to precision medicine within the context of mental health.

Predictive enrichment for the need of renal replacement in sepsis-associated acute kidney injury: combination of furosemide stress test and urinary biomarkers TIMP-2 and IGFBP-7.

BACKGROUND: In sepsis, initial resuscitation with fluids is followed by efforts to achieve a negative fluid balance. However, patients with sepsis-associated acute kidney injury (SA-AKI) often need diuretic or renal replacement therapy (RRT). The dilemma is to predict whether early RRT might be advantageous or diuretics will suffice. Both the Furosemide Stress Test (FST) and measurements of the urinary biomarkers TIMP-2*IGFBP-7, if applied solely, do not provide sufficient guidance. We tested the hypothesis that a combination of two tests, i.e., an upstream FST combined with downstream measurements of urinary TIMP-2*IGFBP-7 concentrations improves the accuracy in predicting RRT necessity. METHODS: In this prospective, multicenter study 100 patients with sepsis (diagnosed < 48h), AKI stage ≥ 2, and an indication for negative fluid balance were included between 02/2020 and 12/2022. All patients received a standardized FST and urinary biomarkers TIMP-2*IGFBP-7 were serially measured immediately before and up to 12 h after the FST. The primary outcome was the RRT requirement within 7 days after inclusion. RESULTS: 32% (n = 32/99) of SA-AKI patients eventually required RRT within 7 days. With the FST, urine TIMP-2*IGFBP-7 decreased within 2 h from 3.26 ng2/mL2/1000 (IQR: 1.38-5.53) to 2.36 ng2/mL2/1000 (IQR: 1.61-4.87) in RRT and 1.68 ng2/mL2/1000 (IQR: 0.56-2.94) to 0.27 ng2/mL2/1000 (IQR: 0.12-0.89) and non-RRT patients, respectively. While TIMP-2*IGFBP-7 concentrations remained low for up to 12 h in non-RRT patients, we noted a rebound in RRT patients after 6 h. TIMP-2*IGFBP-7 before FST (accuracy 0.66; 95%-CI 0.55-0.78) and the FST itself (accuracy 0.74; 95%-CI: 0.64-0.82) yielded moderate test accuracies in predicting RRT requirement. In contrast, a two-step approach, utilizing FST as an upstream screening tool followed by TIMP-2*IGFBP-7 quantification after 2 h improved predictive accuracy (0.83; 95%-CI 0.74-0.90, p = 0.03) compared to the FST alone, resulting in a positive predictive value of 0.86 (95%-CI 0.64-0.97), and a specificity of 0.96 (95%-CI 0.88-0.99). CONCLUSIONS: The combined application of an upstream FST followed by urinary TIMP-2*IGFBP-7 measurements supports highly specific identification of SA-AKI patients requiring RRT. Upcoming interventional trials should elucidate if this high-risk SA-AKI subgroup, identified by our predictive enrichment approach, benefits from an early RRT initiation.

Building on the clinical applicability of ctDNA analysis in non-metastatic pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma represents one of the solid tumors showing the worst prognosis worldwide, with a high recurrence rate after adjuvant or neoadjuvant therapy. Circulating tumor DNA analysis raised as a promising non-invasive tool to characterize tumor genomics and to assess treatment response. In this study, surgical tumor tissue and sequential blood samples were analyzed by next-generation sequencing and were correlated with clinical and pathological characteristics. Thirty resectable/borderline pancreatic ductal adenocarcinoma patients treated at the Hospital Universitario de Navarra were included. Circulating tumoral DNA sequencing identified pathogenic variants in KRAS and TP53, and in other cancer-associated genes. Pathogenic variants at diagnosis were detected in patients with a poorer outcome, and were correlated with response to neoadjuvant therapy in borderline pancreatic ductal adneocarcinoma patients. Higher variant allele frequency at diagnosis was associated with worse prognosis, and thesum of variant allele frequency was greater in samples at progression. Our results build on the potential value of circulating tumor DNA for non-metastatic pancreatic ductal adenocarcinoma patients, by complementing tissue genetic information and as a non-invasive tool for treatment decision. Confirmatory studies are needed to corroborate these findings.

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.

Rethinking Blood Eosinophils for Assessing ICS Response in COPD: A Post-Hoc Analysis from FLAME.

BACKGROUND: The varied treatment response to inhaled corticosteroids (ICS) in COPD, and the increased risk of pneumonia necessitate a personalised ICS therapeutic approach. This is informed by blood eosinophil count (BEC), which predicts ICS treatment response. However, BEC appears to change in response to ICS treatment. RESEARCH QUESTION: Does BEC measured on or off ICS treatment or the change in BEC during ICS treatment, best predict treatment response to ICS in COPD? STUDY DESIGN AND METHODS: FLAME, a 52-week, double-blind RCT compared LABA/LAMA versus LABA/ICS. Corticosteroids were prohibited during a 4-week run-in period. We chose patients previously on ICS, thereby allowing pre- and post-run-in period BEC to represent BEC on and off ICS, respectively. In this post-hoc analysis, we revisited outcome data, exploring how the three BEC biomarkers interacted with treatment response to the ICS containing regimen. RESULTS: Our study confirms that LABA/LAMA combination is superior, or at least non-inferior, to LABA/ICS in curbing exacerbations for most FLAME participants. However, higher BEC off and BEC on ICS and significant BEC suppression during ICS treatment corresponded to superior response to LABA/ICS in terms of exacerbation rate, time-to-first exacerbation, and time-to-first pneumonia. In a subgroup, including 9% of participants, BEC changed significantly during ICS treatment (≥200 cells/µL), and higher BEC on ICS did not predict ICS treatment response. For these patients, BEC off ICS and BEC change proved more predictive. Excess pneumonia risk associated with ICS appeared to be confined to patients who do not benefit from this treatment. BEC were not predictive of treatment effects on lung function and health status. INTERPRETATION: This exploratory analysis advocates preferentially using BEC off ICS or BEC change during ICS treatment for guiding ICS treatment decisions. BEC measured on ICS is less predictive of treatment response. CLINICAL TRIAL REGISTRATION: NCT01782326.