Search

BACKGROUND Several groups have previously developed logistic regression models for predicting delayed graft function (DGF). In this study, we used an automated machine learning (ML) modeling pipeline to generate and optimize DGF prediction models en masse. METHODS Deceased donor renal transplants at our institution from 2010 to 2018 were included. Input data consisted of 21 donor features from United Network for Organ Sharing. A training set composed of ~50%/50% split in DGF-positive and DGF-negative cases was used to generate 400 869 models. Each model was based on 1 of 7 ML algorithms (gradient boosting machine, k-nearest neighbor, logistic regression, neural network, naive Bayes, random forest, support vector machine) with various combinations of feature sets and hyperparameter values. Performance of each model was based on a separate secondary test dataset and assessed by common statistical metrics. RESULTS The best performing models were based on neural network algorithms, with the highest area under the receiver operating characteristic curve of 0.7595. This model used 10 out of the original 21 donor features, including age, height, weight, ethnicity, serum creatinine, blood urea nitrogen, hypertension history, donation after cardiac death status, cause of death, and cold ischemia time. With the same donor data, the highest area under the receiver operating characteristic curve for logistic regression models was 0.7484, using all donor features. CONCLUSIONS Our automated en masse ML modeling approach was able to rapidly generate ML models for DGF prediction. The performance of the ML models was comparable with classic logistic regression models.

Context.— Delayed recognition of acute kidney injury (AKI) results in poor outcomes in military and civilian burn-trauma care. Poor predictive ability of urine output (UOP) and creatinine contribute to the delayed recognition of AKI. Objective.— To determine the impact of point-of-care (POC) AKI biomarker enhanced by machine learning (ML) algorithms in burn-injured and trauma patients. Design.— We conducted a 2-phased study to develop and validate a novel POC device for measuring neutrophil gelatinase-associated lipocalin (NGAL) and creatinine from blood samples. In phase I, 40 remnant plasma samples were used to evaluate the analytic performance of the POC device. Next, phase II enrolled 125 adults with either burns that were 20% or greater of total body surface area or nonburn trauma with suspicion of AKI for clinical validation. We applied an automated ML approach to develop models predicting AKI, using a combination of NGAL, creatinine, and/or UOP as features. Results.— Point-of-care NGAL (mean [SD] bias: 9.8 [38.5] ng/mL, P = .10) and creatinine results (mean [SD] bias: 0.28 [0.30] mg/dL, P = .18) were comparable to the reference method. NGAL was an independent predictor of AKI (odds ratio, 1.6; 95% CI, 0.08–5.20; P = .01). The optimal ML model achieved an accuracy, sensitivity, and specificity of 96%, 92.3%, and 97.7%, respectively, with NGAL, creatinine, and UOP as features. Area under the receiver operator curve was 0.96. Conclusions.— Point-of-care NGAL testing is feasible and produces results comparable to reference methods. Machine learning enhanced the predictive performance of AKI biomarkers including NGAL and was superior to the current techniques.

COVID-19 serological test must have high sensitivity as well as specificity to rule out cross-reactivity with common coronaviruses (HCoVs). We have developed a quantitative multiplex test, measuring antibodies against spike (S) proteins of SARS-CoV-2, SARS-CoV, MERS-CoV, and common human coronavirus strains (229E, NL63, OC43, HKU1), and nucleocapsid (N) protein of SARS-CoV viruses. Receptor binding domain of S protein of SARS-CoV-2 (S-RBD), and N protein, demonstrated sensitivity (94% and 92.5%, respectively) in COVID-19 patients (n = 53), with 98% specificity in non-COVID-19 respiratory-disease (n = 98), and healthy-controls (n = 129). Anti S-RBD and N antibodies appeared five to ten days post-onset of symptoms, peaking at approximately four weeks. The appearance of IgG and IgM coincided while IgG subtypes, IgG1 and IgG3 appeared soon after the total IgG; IgG2 and IgG4 remained undetectable. Several inflammatory cytokines/chemokines were found to be elevated in many COVID-19 patients (e.g., Eotaxin, Gro-α, CXCL-10 (IP-10), RANTES (CCL5), IL-2Rα, MCP-1, and SCGF-b); CXCL-10 was elevated in all. In contrast to antibody titers, levels of CXCL-10 decreased with the improvement in patient health suggesting it as a candidate for disease resolution. Importantly, anti-N antibodies appear before S-RBD and differentiate between vaccinated and infected people—current vaccines (and several in the pipeline) are S protein-based.

Sepsis is the primary cause of burn-related mortality and morbidity. Traditional indicators of sepsis exhibit poor performance when used in this unique population due to their underlying hypermetabolic and inflammatory response following burn injury. To address this challenge, we developed the Machine Intelligence Learning Optimizer (MILO), an automated machine learning (ML) platform, to automatically produce ML models for predicting burn sepsis. We conducted a retrospective analysis of 211 adult patients (age ≥ 18 years) with severe burn injury (≥ 20% total body surface area) to generate training and test datasets for ML applications. The MILO approach was compared against an exhaustive “non-automated” ML approach as well as standard statistical methods. For this study, traditional multivariate logistic regression (LR) identified seven predictors of burn sepsis when controlled for age and burn size (OR 2.8, 95% CI 1.99–4.04, P = 0.032). The area under the ROC (ROC-AUC) when using these seven predictors was 0.88. Next, the non-automated ML approach produced an optimal model based on LR using 16 out of the 23 features from the study dataset. Model accuracy was 86% with ROC-AUC of 0.96. In contrast, MILO identified a k-nearest neighbor-based model using only five features to be the best performer with an accuracy of 90% and a ROC-AUC of 0.96. Machine learning augments burn sepsis prediction. MILO identified models more quickly, with less required features, and found to be analytically superior to traditional ML approaches. Future studies are needed to clinically validate the performance of MILO-derived ML models for sepsis prediction.

The following fictional case is intended as a learning tool within the Pathology Competencies for Medical Education (PCME), a set of national standards for teaching pathology. These are divided into three basic competencies: Disease Mechanisms and Processes, Organ System Pathology, and Diagnostic Medicine and Therapeutic Pathology. For additional information, and a full list of learning objectives for all three competencies, see http://journals.sagepub.com/doi/10.1177/2374289517715040.1.

Severely burned and non-burned trauma patients are at risk for acute kidney injury (AKI). The study objective was to assess the theoretical performance of artificial intelligence (AI)/machine learning (ML) algorithms to augment AKI recognition using the novel biomarker, neutrophil gelatinase associated lipocalin (NGAL), combined with contemporary biomarkers such as N-terminal pro B-type natriuretic peptide (NT-proBNP), urine output (UOP), and plasma creatinine. Machine learning approaches including logistic regression (LR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), and deep neural networks (DNN) were used in this study. The AI/ML algorithm helped predict AKI 61.8 (32.5) hours faster than the Kidney Disease and Improving Global Disease Outcomes (KDIGO) criteria for burn and non-burned trauma patients. NGAL was analytically superior to traditional AKI biomarkers such as creatinine and UOP. With ML, the AKI predictive capability of NGAL was further enhanced when combined with NT-proBNP or creatinine. The use of AI/ML could be employed with NGAL to accelerate detection of AKI in at-risk burn and non-burned trauma patients.

BRAF protein is a serine/threonine kinase with 766 amino acids. Approximately 15% of human cancers harbor BRAF mutations as well as other BRAF anomalies (amplifications, fusions). Somatic mutations mainly occur in the catalytic kinase domain (CR3), and the predominant mutation is p.V600E which is the substitution of glutamic acid (E) for valine (V) as result of a mutation at codon 600 of the kinase domain. To our knowledge, the vast majority of the cancers have non-germline BRAF mutations. Here we describe a case of a 60-year-old female with a history of hairy cell leukemia (HCL) who presented with aphasia and forgetfulness. A follow-up Brain CT scan showed three distinct brain lesions which were found to be diagnostic of melanoma (confirmed by immunohistochemistry) with no evidence of a concurrent brain involvement by a B-cell neoplasm. Molecular studies confirmed the same BRAF p.V600E mutation in both malignancies (hairy cell leukemia and melanoma). Thereafter the patient was started on BRAF inhibitor treatment and is now symptom-free after one year of follow up. Having two concurrent malignancies with a shared BRAF mutation is extremely rare and makes this an excellent example of a genomic marker-driven treatment in two histologically and immunophenotypically distinct tumors.

Increased interest in the opportunities provided by artificial intelligence and machine learning has spawned a new field of health-care research. The new tools under development are targeting many aspects of medical practice, including changes to the practice of pathology and laboratory medicine. Optimal design in these powerful tools requires cross-disciplinary literacy, including basic knowledge and understanding of critical concepts that have traditionally been unfamiliar to pathologists and laboratorians. This review provides definitions and basic knowledge of machine learning categories (supervised, unsupervised, and reinforcement learning), introduces the underlying concept of the bias-variance trade-off as an important foundation in supervised machine learning, and discusses approaches to the supervised machine learning study design along with an overview and description of common supervised machine learning algorithms (linear regression, logistic regression, Naive Bayes, k -nearest neighbor, support vector machine, random forest, convolutional neural networks).

AIMS Machine learning (ML) binary classification in diagnostic histopathology is an area of intense investigation. Several assumptions, including training image quality/format and the number of training images required, appear to be similar in many studies irrespective of the paucity of supporting evidence. We empirically compared training image file type, training set size, and two common convolutional neural networks (CNNs) using transfer learning (ResNet50 and SqueezeNet). METHODS AND RESULTS Thirty haematoxylin and eosin (H&E)-stained slides with carcinoma or normal tissue from three tissue types (breast, colon, and prostate) were photographed, generating 3000 partially overlapping images (1000 per tissue type). These lossless Portable Networks Graphics (PNGs) images were converted to lossy Joint Photographic Experts Group (JPG) images. Tissue type-specific binary classification ML models were developed by the use of all PNG or JPG images, and repeated with a subset of 500, 200, 100, 50, 30 and 10 images. Eleven models were generated for each tissue type, at each quantity of training images, for each file type, and for each CNN, resulting in 924 models. Internal accuracies and generalisation accuracies were compared. There was no meaningful significant difference in accuracies between PNG and JPG models. Models trained with more images did not invariably perform better. ResNet50 typically outperformed SqueezeNet. Models were generalisable within a tissue type but not across tissue types. CONCLUSIONS Lossy JPG images were not inferior to lossless PNG images in our models. Large numbers of unique H&E-stained slides were not required for training optimal ML models. This reinforces the need for an evidence-based approach to best practices for histopathological ML.

Background Burn critical care represents a high impact population that may benefit from artificial intelligence and machine learning (ML). Acute kidney injury (AKI) recognition in burn patients could be enhanced by ML. The goal of this study was to determine the theoretical performance of ML in augmenting AKI recognition. Methods We developed ML models using the k -nearest neighbor ( k -NN) algorithm. The ML models were trained-tested with clinical laboratory data for 50 adult burn patients that had neutrophil gelatinase associated lipocalin (NGAL), urine output (UOP), creatinine, and N-terminal B-type natriuretic peptide (NT-proBNP) measured within the first 24 h of admission. Results Half of patients (50%) in the dataset experienced AKI within the first week following admission. ML models containing NGAL, creatinine, UOP, and NT-proBNP achieved 90–100% accuracy for identifying AKI. ML models containing only NT-proBNP and creatinine achieved 80–90% accuracy. Mean time-to-AKI recognition using UOP and/or creatinine alone was achieved within 42.7 ± 23.2 h post-admission vs. within 18.8 ± 8.1 h via the ML-algorithm. Conclusions The performance of UOP and creatinine for predicting AKI could be enhanced by with a ML algorithm using a k -NN approach when NGAL is not available. Additional studies are needed to verify performance of ML for burn-related AKI.

Anemia is a public health problem in Mexico. This study sought to determine the prevalence and correlates of anemia among women and children residing in a rural farming region of Baja California, Mexico. An existing partnership between universities, non-governmental organizations, and an underserved Mexican community was utilized to perform cross-sectional data collection in 2004-2005 (Wave 1) and in 2011-2012 (Wave 2) among women (15-49 years) and their children (6-59 months). All participants completed a survey and underwent anemia testing. Blood smears were obtained to identify etiology. Nutrition education interventions and clinical health evaluations were offered between waves. Participants included 201 women and 99 children in Wave 1, and 146 women and 77 children in Wave 2. Prevalence of anemia significantly decreased from 42.3 to 23.3 % between Waves 1 and 2 in women (p

Background: Little is known about the effect of a minimum number of slides required in generating image datasets used to build generalizable machine-learning (ML) models. In addition, the assumption within deep learning is that the increased number of training images will always enhance accuracy and that the initial validation accuracy of the models correlates well with their generalizability. In this pilot study, we have been able to test the above assumptions to gain a better understanding of such platforms, especially when data resources are limited. Methods: Using 10 colon histology slides (5 carcinoma and 5 benign), we were able to acquire 1000 partially overlapping images (Dataset A) that were then trained and tested on three convolutional neural networks (CNNs), ResNet50, AlexNet, and SqueezeNet, to build a large number of unique models for a simple task of classifying colon histopathology into benign and malignant. Different quantities of images (10–1000) from Dataset A were used to construct >200 unique CNN models whose performances were individually assessed. The performance of these models was initially assessed using 20% of Dataset A's images (not included in the training phase) to acquire their initial validation accuracy (internal accuracy) followed by their generalization accuracy on Dataset B (a very distinct secondary test set acquired from public domain online sources). Results: All CNNs showed similar peak internal accuracies (>97%) from the Dataset A test set. Peak accuracies for the external novel test set (Dataset B), an assessment of the ability to generalize, showed marked variation (ResNet50: 98%; AlexNet: 92%; and SqueezeNet: 80%). The models with the highest accuracy were not generated using the largest training sets. Further, a model's internal accuracy did not always correlate with its generalization accuracy. The results were obtained using an optimized number of cases and controls. Conclusions: Increasing the number of images in a training set does not always improve model accuracy, and significant numbers of cases may not always be needed for generalization, especially for simple tasks. Different CNNs reach peak accuracy with different training set sizes. Further studies are required to evaluate the above findings in more complex ML models prior to using such ancillary tools in clinical settings.

[Figure][1] A 70-year-old woman presented with a past medical history of essential thrombocythemia (ET) that progressed to post-ET myelofibrosis (MF). Complete blood count showed normocytic anemia (8.2 g/dL), leukopenia (2.2 × 109/L), and normal platelet count (345 × 109/L). The blood

Author(s): Moor, Molly A; Fraga, Miguel A; Garfein, Richard S; Rashidi, Hooman H; Alcaraz, John; Kritz-Silverstein, Donna; Elder, John P; Brodine, Stephanie K | Abstract: IntroductionAnemia is a public health concern among women in rural Baja California, Mexico. The purpose of this study was to identify the individual and community factors contributing to the disproportionately high prevalence of anemia among women in this region.MethodsA cross-sectional study of 118 women (15-49 years) was performed in a rural colonia (small settlement) in Baja California, Mexico in 2012. Participants completed a survey comprised of demographic, socioeconomic, health, and dietary questions and provided a capillary blood sample. A portable HemoCue was used to measure hemoglobin and diagnose anemia. Anemic participants provided a venous blood sample for laboratory testing to elucidate the etiology of anemia. Anemic participants received vitamin supplements and nutritional counseling. Assessments of six local tiendas (community grocery stores) were performed to ascertain the types of food available for purchase within the community.ResultsPrevalence of anemia was 22% among women; laboratory tests revealed iron deficiency was the primary etiology in 80.8% of anemia cases. Other causes of anemia in women included vitamin B-12 deficiency (11.5%) and combined iron and vitamin B-12 deficiency (7.7%). Women from low SES households and women enrolled in the government assistance program Prospera were significantly more likely to be anemic (OR = 3.48, 95% CI 1.35-8.98 and OR = 2.49, 95% CI 1.02-6.09, respectively). Vitamin supplementation was significantly more common among non-anemic women (OR = 0.12, 95% CI 0.02-0.94). Dietary assessments showed limited consumption of iron absorption enhancing foods such as fruits and vegetables. Assessments of local tiendas revealed at least one type of meat and citrus fruit available for purchase at each store; however, leafy green vegetables were only available for purchase at one store.ConclusionAll cases of anemia were due to nutritional deficiencies. While vitamin supplementation is a temporary solution, improved individual nutrition knowledge and community access to iron absorption enhancing foods, particularly produce, is needed. Promoting government assistance programs like Prospera and implementing additional programs designed to improve nutrition and health literacy, in conjunction with ensuring access to nutritious foods, might reduce the high prevalence nutritional anemia within the community.

Classical Hodgkin lymphoma (CHL) is recognized as a B-cell neoplasm arising from germinal center or postgerminal center B-cells. The hallmark of CHL is the presence of CD30 (+) Hodgkin and Reed-Sternberg (HRS) cells with dim expression of PAX5. Nearly all of the HRS cells are positive for PAX5. However, a small minority of HRS cells may lack PAX5 expression, which can cause a diagnostic dilemma. Herein we describe two cases of PAX5-negative CHL and review of the English literature on this very rare entity. It is crucial to be aware of this phenomenon, which in some cases may lead to misdiagnosis and may ultimately adversely affect patient’s management.

Diffuse large B-cell lymphoma (DLBCL) is a neoplasm of large B-lymphocytes with a diffuse growth pattern. The neoplastic cells express B-cell markers such as CD20 and PAX-5 and there may be coexpression of BCL-2, BCL-6, CD10, and MUM-1. With the exception of CD5, other T-cell markers are not commonly expressed in this neoplasm. Here, we describe the first reported case of a DLBCL with abnormal expression CD7 arising in a background of follicular lymphoma in an 81-year-old male who presented with a nontender left axillary mass. Additionally, no other T-cell antigens were expressed in this B-cell lymphoma. Expression of CD7 in DLBCL is exceptionally rare and its prognostic significance is unknown. Here, we describe this rare case with review of literature of known DLBCLs with expression of T-cell antigens.