Digital pathology, deep learning, and cancer: a narrative review.

Background and Objective: Cancer is a leading cause of morbidity and mortality worldwide. The emergence of digital pathology and deep learning technologies signifies a transformative era in healthcare. These technologies can enhance cancer detection, streamline operations, and bolster patient care. A substantial gap exists between the development phase of deep learning models in controlled laboratory environments and their translations into clinical practice. This narrative review evaluates the current landscape of deep learning and digital pathology, analyzing the factors influencing model development and implementation into clinical practice. Methods: We searched multiple databases, including Web of Science, Arxiv, MedRxiv, BioRxiv, Embase, PubMed, DBLP, Google Scholar, IEEE Xplore, Semantic Scholar, and Cochrane, targeting articles on whole slide imaging and deep learning published from 2014 and 2023. Out of 776 articles identified based on inclusion criteria, we selected 36 papers for the analysis. Key Content and Findings: Most articles in this review focus on the in-laboratory phase of deep learning model development, a critical stage in the deep learning lifecycle. Challenges arise during model development and their integration into clinical practice. Notably, lab performance metrics may not always match real-world clinical outcomes. As technology advances and regulations evolve, we expect more clinical trials to bridge this performance gap and validate deep learning models' effectiveness in clinical care. High clinical accuracy is vital for informed decision-making throughout a patient's cancer care. Conclusions: Deep learning technology can enhance cancer detection, clinical workflows, and patient care. Challenges may arise during model development. The deep learning lifecycle involves data preprocessing, model development, and clinical implementation. Achieving health equity requires including diverse patient groups and eliminating bias during implementation. While model development is integral, most articles focus on the pre-deployment phase. Future longitudinal studies are crucial for validating models in real-world settings post-deployment. A collaborative approach among computational pathologists, technologists, industry, and healthcare providers is essential for driving adoption in clinical settings.

Recurrence prediction of lung adenocarcinoma using an immune gene expression and clinical data trained and validated support vector machine classifier.

Background: Immune microenvironment plays a critical role in cancer from onset to relapse. Machine learning (ML) algorithm can facilitate the analysis of lab and clinical data to predict lung cancer recurrence. Prompt detection and intervention are crucial for long-term survival in lung cancer relapse. Our study aimed to evaluate the clinical and genomic prognosticators for lung cancer recurrence by comparing the predictive accuracy of four ML models. Methods: A total of 41 early-stage lung cancer patients who underwent surgery between June 2007 and October 2014 at New York University Langone Medical Center were included (with recurrence, n=16; without recurrence, n=25). All patients had tumor tissue and buffy coat collected at the time of resection. The CIBERSORT algorithm quantified tumor-infiltrating immune cells (TIICs). Protein-protein interaction (PPI) network and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted to unearth potential molecular drivers of tumor progression. The data was split into training (75%) and validation sets (25%). Ensemble linear kernel support vector machine (SVM) ML models were developed using optimized clinical and genomic features to predict tumor recurrence. Results: Activated natural killer (NK) cells, M0 macrophages, and M1 macrophages showed a positive correlation with progression. Conversely, T CD4+ memory resting cells were negatively correlated. In the PPI network, TNF and IL6 emerged as prominent hub genes. Prediction models integrating clinicopathological prognostic factors, tumor gene expression (45 genes), and buffy coat gene expression (47 genes) yielded varying receiver operating characteristic (ROC)-area under the curves (AUCs): 62.7%, 65.4%, and 59.7% in the training set, 58.3%, 83.3%, and 75.0% in the validation set, respectively. Notably, merging gene expression with clinical data in a linear SVM model led to a significant accuracy boost, with an AUC of 92.0% in training and 91.7% in validation. Conclusions: Using ML algorithm, immune gene expression data from tumor tissue and buffy coat may enhance the precision of lung cancer recurrence prediction.

A machine learning-based prediction of the micropapillary/solid growth pattern in invasive lung adenocarcinoma with radiomics.

BACKGROUND: Micropapillary/solid (MP/S) growth patterns of lung adenocarcinoma are vital for making clinical decisions regarding surgical intervention. This study aimed to predict the presence of a MP/S component in lung adenocarcinoma using radiomics analysis. METHODS: Between January 2011 and December 2013, patients undergoing curative invasive lung adenocarcinoma resection were included. Using the "PyRadiomics" package, we extracted 90 radiomics features from the preoperative computed tomography (CT) images. Subsequently, four prediction models were built by utilizing conventional machine learning approaches fitting into radiomics analysis: a generalized linear model (GLM), Naïve Bayes, support vector machine (SVM), and random forest classifiers. The models' accuracy was assessed using a receiver operating curve (ROC) analysis, and the models' stability was validated both internally and externally. RESULTS: A total of 268 patients were included as a primary cohort, and 36.6% (98/268) of them had lung adenocarcinoma with an MP/S component. Patients with an MP/S component had a higher rate of lymph node metastasis (18.4% versus 5.3%) and worse recurrence-free and overall survival. Five radiomics features were selected for model building, and in the internal validation, the four models achieved comparable performance of MP/S prediction in terms of area under the curve (AUC): GLM, 0.74 [95% confidence interval (CI): 0.65-0.83]; Naïve Bayes, 0.75 (95% CI: 0.65-0.85); SVM, 0.73 (95% CI: 0.61-0.83); and random forest, 0.72 (95% CI: 0.63-0.81). External validation was performed using a test cohort with 193 patients, and the AUC values were 0.70, 0.72, 0.73, and 0.69 for Naïve Bayes, SVM, random forest, and GLM, respectively. CONCLUSIONS: Radiomics-based machine learning approach is a very strong tool for preoperatively predicting the presence of MP/S growth patterns in lung adenocarcinoma, and can help customize treatment and surveillance strategies.

Candida auris in the Age of Resistance.

Candida auris (C. auris) is an opportunistic ascomycetous budding yeast that has been emerging as an invasive, multidrug-resistant pathogen over the past 10 years since its discovery. This fungi is the first to be labeled as a public health threat according to the Centers for Disease Control (CDC) and has since become a major problem in the United States. This serves as a detailed overview of the various factors contributing to the pathogenicity of C. auris.

A Meta-Analysis on the Effects of Hydroxychloroquine on COVID-19.

Introduction Since December 2019, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has rapidly spread throughout the world with a large medical and economic impact. On March 12, 2020, the World Health Organization (WHO) classified SARS-CoV-2 as a pandemic. As a result of this worldwide public health crisis, politicians, elected officials, and healthcare professionals emergently began trialing hydroxychloroquine (HCQ) in efforts to treat and prevent the transmission of the virus. This meta-analysis was performed to assess the effects of HCQ on patients with COVID-19. Methods  This meta-analysis adheres to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRIMA) guidelines. Selected articles published between December 2019 and July 2020 were found utilizing the following search engines: PubMed, Google Scholar, Cochrane Library, DisasterLit, Clinicaltrials.gov, Medrxiv, and Embase. Two independent physician reviewers screened eligible articles that met the inclusion and exclusion criteria of the analysis. The outcome measures analyzed were mortality rate, rate of disease progression/improvement, rate of disease severity, and adverse effects of treatment. Six out of 14 studies that met the study's eligibility criteria were selected and further analyzed, with a total of 381 participants (n= 381). Conclusion From the studies analyzed, it was found that groups treated with HCQ had an overall mortality rate that was 2.5 times greater than that of the control group. HCQ treated patients had higher rates of adverse clinical outcomes and side effects compared with the control populations. Lastly, there was a 1.2 times higher rate of improvement in the group of HCQ treated patients with mild to moderate symptoms as compared to the control group.

Automated Lung Cancer Detection Using Artificial Intelligence (AI) Deep Convolutional Neural Networks: A Narrative Literature Review.

Lung cancer is the number one cause of cancer-related deaths in the United States as well as worldwide. Radiologists and physicians experience heavy daily workloads, thus are at high risk for burn-out. To alleviate this burden, this narrative literature review compares the performance of four different artificial intelligence (AI) models in lung nodule cancer detection, as well as their performance to physicians/radiologists reading accuracy. A total of 648 articles were selected by two experienced physicians with over 10 years of experience in the fields of pulmonary critical care, and hospital medicine. The data bases used to search and select the articles are PubMed/MEDLINE, EMBASE, Cochrane library, Google Scholar, Web of science, IEEEXplore, and DBLP. The articles selected range from the years between 2008 and 2019. Four out of 648 articles were selected using the following inclusion criteria: 1) 18-65 years old, 2) CT chest scans, 2) lung nodule, 3) lung cancer, 3) deep learning, 4) ensemble and 5) classic methods. The exclusion criteria used in this narrative review include: 1) age greater than 65 years old, 2) positron emission tomography (PET) hybrid scans, 3) chest X-ray (CXR) and 4) genomics. The model performance outcomes metrics are measured and evaluated in sensitivity, specificity, accuracy, receiver operator characteristic (ROC) curve, and the area under the curve (AUC). This hybrid deep-learning model is a state-of-the-art architecture, with high-performance accuracy and low false-positive results. Future studies, comparing each model accuracy at depth is key. Automated physician-assist systems as this model in this review article help preserve a quality doctor-patient relationship.

Impact of epoetin alfa on left ventricular structure, function, and pressure volume relations as assessed by cardiac magnetic resonance: the heart failure preserved ejection fraction (HFPEF) anemia trial.

Anemia, a common comorbidity in older adults with heart failure and a preserved ejection fraction (HFPEF), is associated with worse outcomes. The authors quantified the effect of anemia treatment on left ventricular (LV) structure and function as measured by cardiac magnetic resonance (CMR) imaging. A prospective, randomized single-blind clinical trial (NCT NCT00286182) comparing the safety and efficacy of epoetin alfa vs placebo for 24 weeks in which a subgroup (n=22) had cardiac magnetic resonance imaging (MRI) at baseline and after 3 and 6 months to evaluate changes in cardiac structure and function. Pressure volume (PV) indices were derived from MRI measures of ventricular volume coupled with sphygmomanometer-measured pressure and Doppler estimates of filling pressure. The end-systolic and end-diastolic PV relations and the area between them as a function of end-diastolic pressure, the isovolumic PV area (PVAiso), were calculated. Patients (75±10 years, 64% women) with HFPEF (EF=63%±15%) with an average hemoglobin of 10.3±1.1 gm/dL were treated with epoetin alfa using a dose-adjusted algorithm that increased hemoglobin compared with placebo (P<.0001). As compared with baseline, there were no significant changes in end-diastolic (-7±8 mL vs -3±8 mL, P=.81) or end-systolic (-0.4±2 mL vs -0.7±5 mL, P=.96) volumes at 6-month follow-up between epoetin alfa compared with placebo. LV function as measured based on EF (-1.5%±1.6% vs -2.6%±3.3%, P=.91) and pressure volume indices (PVAiso-EDP at 30 mm Hg, -5071±4308 vs -1662±4140, P=.58) did not differ between epoetin alfa and placebo. Administration of epoetin alfa to older adult patients with HFPEF resulted in a significant increase in hemoglobin, without evident change in LV structure, function, or pressure volume relationships as measured quantitatively using CMR imaging.

Cancer and clots: all cases of venous thromboembolism are not treated the same.

Idiopathic venous thromboembolism (VTE) can be the first sign of cancer, although how extensively one should search for cancer in a patient with idiopathic VTE is not clear. Treating VTE is more complex in cancer patients than in those without cancer. The authors discuss their approach to searching for undiagnosed cancer in patients with idiopathic VTE and to managing VTE in patients with cancer.