Deep Learning to Estimate Cardiovascular Risk From Chest Radiographs : A Risk Prediction Study.

BACKGROUND: Guidelines for primary prevention of atherosclerotic cardiovascular disease (ASCVD) recommend a risk calculator (ASCVD risk score) to estimate 10-year risk for major adverse cardiovascular events (MACE). Because the necessary inputs are often missing, complementary approaches for opportunistic risk assessment are desirable. OBJECTIVE: To develop and test a deep-learning model (CXR CVD-Risk) that estimates 10-year risk for MACE from a routine chest radiograph (CXR) and compare its performance with that of the traditional ASCVD risk score for implications for statin eligibility. DESIGN: Risk prediction study. SETTING: Outpatients potentially eligible for primary cardiovascular prevention. PARTICIPANTS: The CXR CVD-Risk model was developed using data from a cancer screening trial. It was externally validated in 8869 outpatients with unknown ASCVD risk because of missing inputs to calculate the ASCVD risk score and in 2132 outpatients with known risk whose ASCVD risk score could be calculated. MEASUREMENTS: 10-year MACE predicted by CXR CVD-Risk versus the ASCVD risk score. RESULTS: Among 8869 outpatients with unknown ASCVD risk, those with a risk of 7.5% or higher as predicted by CXR CVD-Risk had higher 10-year risk for MACE after adjustment for risk factors (adjusted hazard ratio [HR], 1.73 [95% CI, 1.47 to 2.03]). In the additional 2132 outpatients with known ASCVD risk, CXR CVD-Risk predicted MACE beyond the traditional ASCVD risk score (adjusted HR, 1.88 [CI, 1.24 to 2.85]). LIMITATION: Retrospective study design using electronic medical records. CONCLUSION: On the basis of a single CXR, CXR CVD-Risk predicts 10-year MACE beyond the clinical standard and may help identify individuals at high risk whose ASCVD risk score cannot be calculated because of missing data. PRIMARY FUNDING SOURCE: None.

Congenitally Fused Cervical Spine Is Associated With Adjacent-Level Degeneration in the Absence of Cervical Spine Surgery.

BACKGROUND: Cervical fusion surgery is associated with adjacent-level degeneration, but surgical and technical factors are difficult to dissociate from the mechanical effects of the fusion itself. OBJECTIVE: To determine the effect of fusion on adjacent-level degeneration in unoperated patients using a cohort of patients with congenitally fused cervical vertebrae. METHODS: We identified 96 patients with incidental single-level cervical congenital fusion on computed tomography imaging. We compared these patients to an age-matched control cohort of 80 patients without congenital fusion. We quantified adjacent-level degeneration through direct measurements of intervertebral disk parameters as well as the validated Kellgren & Lawrence classification scale for cervical disk degeneration. Ordinal logistic regression and 2-way analysis of variance testing were performed to correlate extent of degeneration with the congenitally fused segment. RESULTS: Nine hundred fifty-five motion segments were analyzed. The numbers of patients with C2-3, C3-4, C4-5, C5-6, and C6-7 congenitally fused segments were 47, 11, 11, 17, and 9, respectively. We found that patients with congenital fusion at C4-C5 and C5-C6 had a significantly greater extent of degeneration at adjacent levels compared with the degree of degeneration at the same levels in control patients and in patients with congenital fusion at other cervical levels, even while controlling for expected degeneration and age. CONCLUSION: Taken together, our data suggest that congenitally fused cervical spinal segments at C4-C5 and C5-C6 are associated with adjacent-level degeneration independent of fixation instrumentation. This study design removes surgical factors that might contribute to adjacent-level degeneration.

Validation of a Deep Learning-Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data.

Importance: Lung cancer screening with chest computed tomography (CT) prevents lung cancer death; however, fewer than 5% of eligible Americans are screened. CXR-LC, an open-source deep learning tool that estimates lung cancer risk from existing chest radiograph images and commonly available electronic medical record (EMR) data, may enable automated identification of high-risk patients as a step toward improving lung cancer screening participation. Objective: To validate CXR-LC using EMR data to identify individuals at high-risk for lung cancer to complement 2022 US Centers for Medicare & Medicaid Services (CMS) lung cancer screening eligibility guidelines. Design, Setting, and Participants: This prognostic study compared CXR-LC estimates with CMS screening guidelines using patient data from a large US hospital system. Included participants were persons who currently or formerly smoked cigarettes with an outpatient posterior-anterior chest radiograph between January 1, 2013, and December 31, 2014, with no history of lung cancer or screening CT. Data analysis was performed between May 2021 and June 2022. Exposures: CXR-LC lung cancer screening eligibility (previously defined as having a 3.297% or greater 12-year risk) based on inputs (chest radiograph image, age, sex, and whether currently smoking) extracted from the EMR. Main Outcomes and Measures: 6-year incident lung cancer. Results: A total of 14 737 persons were included in the study population (mean [SD] age, 62.6 [6.8] years; 7154 [48.5%] male; 204 [1.4%] Asian, 1051 [7.3%] Black, 432 [2.9%] Hispanic, 12 330 [85.2%] White) with a 2.4% rate of incident lung cancer over 6 years (361 patients with cancer). CMS eligibility could be determined in 6277 patients (42.6%) using smoking pack-year and quit-date from the EMR. Patients eligible by both CXR-LC and 2022 CMS criteria had a high rate of lung cancer (83 of 974 patients [8.5%]), higher than those eligible by 2022 CMS criteria alone (5 of 177 patients [2.8%]; P < .001). Patients eligible by CXR-LC but not 2022 CMS criteria also had a high 6-year incidence of lung cancer (121 of 3703 [3.3%]). In the 8460 cases (57.4%) where CMS eligibility was unknown, CXR-LC eligible patients had a 5-fold higher rate of lung cancer than ineligible (127 of 5177 [2.5%] vs 18 of 2283 [0.5%]; P < .001). Similar results were found in subgroups, including female patients and Black persons. Conclusions and Relevance: Using routine chest radiographs and other data automatically extracted from the EMR, CXR-LC identified high-risk individuals who may benefit from lung cancer screening CT.

Outcomes of a Student-Led Telemedicine Clinic in Response to COVID-19.

In response to the coronavirus disease-2019 (COVID-19) pandemic, we developed and launched a student-led telemedicine program in Chelsea. From April to November 2020, over 200 student volunteers contacted over 1000 patients to assess COVID-19 symptoms, provide counseling, and triage patients. Through a retrospective cohort study, we determined that student triage decision was associated with patient outcomes, including hospitalization status, COVID-19 test administration, and COVID-19 test result. These results quantify the outcomes of a student-led telemedicine clinic to combat the ongoing pandemic and may serve as a model for implementation of similar clinics to alleviate mounting health care system burden.

Predicting Discharge Disposition Following Meningioma Resection Using a Multi-Institutional Natural Language Processing Model.

BACKGROUND: Machine learning (ML)-based predictive models are increasingly common in neurosurgery, but typically require large databases of discrete variables for training. Natural language processing (NLP) can extract meaningful data from unstructured text. OBJECTIVE: To present an NLP model that predicts nonhome discharge and a point-of-care implementation. METHODS: We retrospectively collected age, preoperative notes, and radiology reports from 595 adults who underwent meningioma resection in an academic center from 1995 to 2015. A total of 32 algorithms were trained with the data; the 3 best performing algorithms were combined to form an ensemble. Predictive ability, assessed by area under the receiver operating characteristic curve (AUC) and calibration, was compared to a previously published model utilizing 52 neurosurgeon-selected variables. We then built a multi-institutional model by incorporating notes from 693 patients at another center into algorithm training. Permutation importance was used to analyze the relative importance of each input to model performance. Word clouds and non-negative matrix factorization were used to analyze predictive features of text. RESULTS: The single-institution NLP model predicted nonhome discharge with AUC of 0.80 (95% CI = 0.74-0.86) on internal and 0.76 on holdout validation compared to AUC of 0.77 (95% CI = 0.73-0.81) and 0.74 for the 52-variable ensemble. The multi-institutional model performed similarly well with AUC = 0.78 (95% CI = 0.74-0.81) on internal and 0.76 on holdout validation. Preoperative notes most influenced predictions. The model is available at http://nlp-home.insds.org. CONCLUSION: ML and NLP are underutilized in neurosurgery. Here, we construct a multi-institutional NLP model that predicts nonhome discharge.

Ezh2 does not mediate retinal ganglion cell homeostasis or their susceptibility to injury.

Epigenetic predisposition is thought to critically contribute to adult-onset disorders, such as retinal neurodegeneration. The histone methyltransferase, enhancer of zeste homolog 2 (Ezh2), is transiently expressed in the perinatal retina, particularly enriched in retinal ganglion cells (RGCs). We previously showed that embryonic deletion of Ezh2 from retinal progenitors led to progressive photoreceptor degeneration throughout life, demonstrating a role for embryonic predisposition of Ezh2-mediated repressive mark in maintaining the survival and function of photoreceptors in the adult. Enrichment of Ezh2 in RGCs leads to the question if Ezh2 also mediates gene expression and function in postnatal RGCs, and if its deficiency changes RGC susceptibility to cell death under injury or disease in the adult. To test this, we generated mice carrying targeted deletion of Ezh2 from RGC progenitors driven by Math5-Cre (mKO). mKO mice showed no detectable defect in RGC development, survival, or cell homeostasis as determined by physiological analysis, live imaging, histology, and immunohistochemistry. Moreover, RGCs of Ezh2 deficient mice revealed similar susceptibility against glaucomatous and acute optic nerve trauma-induced neurodegeneration compared to littermate floxed or wild-type control mice. In agreement with the above findings, analysis of RNA sequencing of RGCs purified from Ezh2 deficient mice revealed few gene changes that were related to RGC development, survival and function. These results, together with our previous report, support a cell lineage-specific mechanism of Ezh2-mediated gene repression, especially those critically involved in cellular function and homeostasis.