Faculty Bibliography

PURPOSE/OBJECTIVE:Increasingly complex MRI studies and variable series naming conventions reveal limitations of rule-based image routing, especially in health systems with multiple scanners and sites. Accurate methods to identify series based on image content would aid post-processing and PACS viewing. Recent deep/machine learning efforts classify 5-8 basic brain MR sequences. We present an ensemble model combining a convolutional neural network and a random forest classifier to differentiate 25 brain sequences and image orientation. METHODS:Series were grouped by descriptions into 25 sequences and 4 orientations. Dataset A, obtained from our institution, was divided into training (16,828 studies; 48,512 series; 112,028 images), validation (4746 studies; 16,612 series; 26,222 images) and test sets (6348 studies; 58,705 series; 3,314,018 images). Dataset B, obtained from a separate hospital, was used for out-of-domain external validation (1252 studies; 2150 series; 234,944 images). We developed an ensemble model combining a 2D convolutional neural network with a custom multi-task learning architecture and random forest classifier trained on DICOM metadata to classify sequence and orientation by series. RESULTS:The neural network, random forest, and ensemble achieved 95%, 97%, and 98% overall sequence accuracy on dataset A, and 98%, 99%, and 99% accuracy on dataset B, respectively. All models achieved > 99% orientation accuracy on both datasets. CONCLUSION/CONCLUSIONS:The ensemble model for series identification accommodates the complexity of brain MRI studies in state-of-the-art clinical practice. Expanding on previous work demonstrating proof-of-concept, our approach is more comprehensive with greater sequence diversity and orientation classification.

Image-based analysis as a method for mutation detection can be advantageous in settings when tumor tissue is limited or unavailable for direct testing. Here, we utilize two distinct and complementary machine learning methods of analyzing whole slide images (WSI) for predicting mutated BRAF. In the first method, WSI of melanomas from 256 patients were used to train a deep convolutional neural network (CNN) in order to develop a fully automated model that first selects for tumor-rich areas (Area Under the Curve AUC=0.96) then predicts for mutated BRAF (AUC=0.71). Saliency mapping was performed and revealed that pixels corresponding to nuclei were the most relevant to network learning. In the second method, WSI were analyzed using a pathomics pipeline that first annotates nuclei and then quantifies nuclear features, demonstrating that mutated BRAF nuclei were significantly larger and rounder nuclei compared to BRAF WT nuclei. Lastly, we developed a model that combines clinical information, deep learning, and pathomics that improves the predictive performance for mutated BRAF to AUC=0.89. Not only does this provide additional insights on how BRAF mutations affect tumor structural characteristics, machine learning-based analysis of WSI has the potential to be integrated into higher order models for understanding tumor biology.

BACKGROUND: We previously developed and validated a predictive model to help clinicians identify hospitalized adults with coronavirus disease 2019 (COVID-19) who may be ready for discharge given their low risk of adverse events. Whether this algorithm can prompt more timely discharge for stable patients in practice is unknown. OBJECTIVES/OBJECTIVE: The aim of the study is to estimate the effect of displaying risk scores on length of stay (LOS). METHODS: We integrated model output into the electronic health record (EHR) at four hospitals in one health system by displaying a green/orange/red score indicating low/moderate/high-risk in a patient list column and a larger COVID-19 summary report visible for each patient. Display of the score was pseudo-randomized 1:1 into intervention and control arms using a patient identifier passed to the model execution code. Intervention effect was assessed by comparing LOS between intervention and control groups. Adverse safety outcomes of death, hospice, and re-presentation were tested separately and as a composite indicator. We tracked adoption and sustained use through daily counts of score displays. RESULTS: Enrolling 1,010 patients from May 15, 2020 to December 7, 2020, the trial found no detectable difference in LOS. The intervention had no impact on safety indicators of death, hospice or re-presentation after discharge. The scores were displayed consistently throughout the study period but the study lacks a causally linked process measure of provider actions based on the score. Secondary analysis revealed complex dynamics in LOS temporally, by primary symptom, and hospital location. CONCLUSION/CONCLUSIONS: An AI-based COVID-19 risk score displayed passively to clinicians during routine care of hospitalized adults with COVID-19 was safe but had no detectable impact on LOS. Health technology challenges such as insufficient adoption, nonuniform use, and provider trust compounded with temporal factors of the COVID-19 pandemic may have contributed to the null result. TRIAL REGISTRATION/BACKGROUND: ClinicalTrials.gov identifier: NCT04570488.

Biopsies of inflammatory tissue contain a complex network of interacting cells, orchestrating the immune or autoimmune response. While standard histological examination can identify relationships, it is clear that a great amount of data on each slide is not quantitated or categorized in standard microscopic examinations. To deal with the huge amount of data present in biopsy tissue in an unbiased and comprehensive way, we have developed a deep learning algorithm to identify immune cells in biopsies of inflammatory lesions. We focused on T follicular helper (Tfh) cell subsets and B cells in dermatomyositis biopsy images. We achieved strong performance on detection and classification of cells, including the rare Tfh cell subsets present in the tissue. This algorithm could be used to perform distance mapping between cell types in tissue, and could be easily adapted to other disease states.

BACKGROUND:It is estimated that up to 40% of Alzheimer's Disease and Related Dementias cases can be prevented or delayed by addressing modifiable factors including those that influence vascular risk (hypertension, obesity, smoking, physical activity, diabetes). Prevention may be particularly important in the vascular dementia subtypes. Despite the supporting evidence, the rates of medical therapy to reduce vascular risk are not well described. METHOD/METHODS:We assessed the utilization of statins, aspirin, and blood pressure (BP) medications in adults age ≥65 years cared for at NYU Langone Health, as recorded in the electronic health record. We included two cohorts: cohort 1 included patients who were diagnosed with vascular dementia (VaD) at NYU Langone Barlow Center for Memory Evaluation between January 1, 2015 and June 24, 2019. Cohort 2 extended the inclusion to seniors with VD diagnosis by any NYU Langone physician. Definitions for vascular dementia, the covariates assessed, and medications that we included in each category are shown in Tables 1-3. RESULT/RESULTS:We included 419 and 3745 patients in cohort 1 and cohort 2, respectively. Table 4 shows the characteristics and medication adherence in cohorts 1 and 2. In cohort 1, the prescription rates for statins, aspirin, and BP medications were 66%, 66%, 70%. In cohort 2, the rates for statin, aspirin, and BP medications were 56%, 46%, and 65%, respectively. The differences between prescription rates in cohort 1 and 2 for the three medication groups were statistically significant (p<0.05). CONCLUSION/CONCLUSIONS:Our analysis of the utilization of cardiovascular medications among patients with vascular dementia illuminates potential gaps both among patients who receive care at specialty clinics, as well as the overall population with vascular dementia. The rates of medication utilization are higher for patients under the care of cognitive neurologists. Electronic health records can help identify large cohorts of patients who may benefit from improved access to preventative measures including cardiovascular medications.

Introduction: Early detection of pancreatic cancer (PC) remains challenging largely due to the low population incidence and few known risk factors. However, screening in at-risk populations and detection of early cancer has the potential to significantly alter survival. We used an Electronic Health Records (EHR) based large-scale machine learning algorithm to identify disease codes that are associated with the development of PC at least 3 years before diagnosis and developed a predictive model to identify patients at risk for PC 27-33 months later.
Method(s): EHR data was analyzed between 2000 and 2021 and individuals with at least 3 years of continuous presence in the database were included. A 1:4 case-control matching based on age, sex, length of medical history to all diagnosed with PC was performed. In one model, all patients meeting database presence were included, whereas in a second model only those without known prior pancreatic disease were evaluated. Among demographic and 19,304 disease variables 27-33 months prior to PC diagnosis, we used the P-value of associations to select significant variables (cut-off P-value < 0.01), and trained a logistic regression model. Final predictive performance was tested on a held-out validation cohort.
Result(s): 544,000 patients were analyzed. 2091 patients with PC were matched to 8364 cancer-free patients. We identified 73 variables with significant association of development of PC, including pancreatic cysts, diabetes, family or personal history of breast cancer, and chronic pancreatitis (ranked results and statistical analysis are shown in Table 1). These variables were selected for the regression model, which we trained in over 541,602 patients. In our second model, in patients without prior pancreatic diseases, 541,377 patients were included. The area under the receiver operating characteristic curve (AUROC) were 0.790 [0.772, 0.809] and 0.779 [0.759, 0.789] in the two models respectively.
Conclusion(s): In a robust EHR-based analysis, we identified a list of diagnostic variables associated with pancreatic cancer development in a 3-year time frame and developed a model to identify patients at risk. Although the inclusion of additional variables such as laboratory results and radiomics will likely improve the accuracy of the model, the current algorithm will allow us to develop an EHR-based identification of patients at risk for PC. (Table Presented)

The determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is critical for the diagnostic process, and directly affects patients' prognosis and treatment. Sequencing, albeit slower and more expensive, can provide additional information on molecular subtypes and mutations that can be used to better select treatments. Here, we implement a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes but also the molecular subtypes and 18 common gene mutations based on digitized H&E-stained pathological images. The model achieves high accuracy and generalizes well on independent datasets. Our results suggest that Panoptes, with further refinement, has the potential for clinical application to help pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing.

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.