A5026950052- Lung Cancer Research Studies
- Cancer therapeutics and mechanisms
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare and Education
- Spine and Intervertebral Disc Pathology
- Hip and Femur Fractures
- RNA modifications and cancer
- Peptidase Inhibition and Analysis
- Machine Learning in Healthcare
- COVID-19 diagnosis using AI
- Hospital Admissions and Outcomes
- Glaucoma and retinal disorders
- Retinal and Optic Conditions
- Dental Radiography and Imaging
- Digital Imaging in Medicine
- Patient Satisfaction in Healthcare
- Acute Ischemic Stroke Management
- AI in cancer detection
- Glycosylation and Glycoproteins Research
- Pelvic and Acetabular Injuries
- Enhanced Recovery After Surgery
- Retinal Imaging and Analysis
- RNA and protein synthesis mechanisms
- Cardiac, Anesthesia and Surgical Outcomes
- Brain Tumor Detection and Classification
NYU Langone Health
2025
Icahn School of Medicine at Mount Sinai
2019-2023
Mount Sinai Health System
2019-2022
New York Proton Center
2020-2022
Neurological Surgery
2019
The University of Texas MD Anderson Cancer Center
2015-2017
Swarthmore College
2017
Effective targeted therapies for small-cell lung cancer (SCLC), the most aggressive form of cancer, remain urgently needed. Here we report evidence preclinical efficacy evoked by targeting overexpressed cell-cycle checkpoint kinase CHK1 in SCLC. Our studies employed RNAi-mediated attenuation or pharmacologic blockade with novel second-generation inhibitor prexasertib (LY2606368), currently clinical trials. In SCLC models vitro and vivo, LY2606368 exhibited strong single-agent efficacy,...
The adoption of large language models (LLMs) in healthcare demands a careful analysis their potential to spread false medical knowledge. Because LLMs ingest massive volumes data from the open Internet during training, they are potentially exposed unverified knowledge that may include deliberately planted misinformation. Here, we perform threat assessment simulates data-poisoning attack against Pile, popular dataset used for LLM development. We find replacement just 0.001% training tokens...
Cross sectional database study.To develop a fully automated artificial intelligence and computer vision pipeline for assisted evaluation of lumbar lordosis.Lateral radiographs were used to segmentation neural network (n = 629). After synthetic augmentation, 70% these training, while the remaining 30% hyperparameter optimization. A algorithm was deployed on segmented calculate lordosis angles. test set evaluate validity entire 151).The U-Net achieved dataset dice score 0.821, an area under...
We propose a framework that leverages deep residual CNNs pretrained on large, non-biomedical image data sets. These networks learn cross-domain features improve low-level interpretation of images. evaluate our model brain imaging and show pretraining the use are crucial to seeing large improvements in Alzheimer's Disease diagnosis from MRIs.
Extended postoperative hospital stays are associated with numerous clinical risks and increased economic cost. Accurate preoperative prediction of extended length stay (LOS) can facilitate targeted interventions to mitigate harm resource utilization.To develop a machine learning algorithm aimed at predicting LOS after cervical spine surgery on national level elucidate drivers prediction.Electronic medical records from large, urban academic center were retrospectively examined identify...
Real-time seizure detection is a resource intensive process as it requires continuous monitoring of patients on stereoelectroencephalography. This study improves real-time in drug resistant epilepsy (DRE) by developing patient-specific deep learning models that utilize novel self-supervised dynamic thresholding approach. Deep neural networks were constructed over 2000 h high-resolution, multichannel SEEG and video recordings from 14 DRE patients. Consensus labels panel epileptologists used...
The fundamental challenge in machine learning is ensuring that trained models generalize well to unseen data. We developed a general technique for ameliorating the effect of dataset shift using generative adversarial networks (GANs) on 149,298 handwritten digits and 868,549 chest radiographs obtained from four academic medical centers. Efficacy was assessed by comparing area under curve (AUC) pre- post-adaptation. On digit recognition task, baseline CNN achieved an average internal test AUC...
Study Design Retrospective database study. Objectives The goal of this study was to assess the influence weekend admission on patients undergoing elective thoracolumbar spinal fusion by investigating hospital readmission outcomes and analyzing differences in demographics, comorbidities, postoperative factors. Methods 2016-2018 Nationwide Readmission Database used identify adult who underwent fusion. sample divided into weekday patients. Demographics, complications, discharge status data were...
Purpose: We developed an accelerated virtual reality (VR) suprathreshold hemifield perimetry algorithm, the median cut test (MCHT). This study examines ability of MCHT to determine ptosis severity and its reversibility with artificial improvement by eyelid taping on HTC Vive Pro Eye VR headset Humphrey visual field analyzer (HVFA) assess capabilities emerging technologies in evaluating ptosis. Methods: In a single visit, was administered along HVFA 30-2 ptotic untaped taped eyelids...
Cross-sectional study.The purpose of this study is to develop and validate a machine learning algorithm for the automated identification anterior cervical discectomy fusion (ACDF) plates from smartphone images anterior-posterior (AP) spine radiographs.Identification existing instrumentation critical step in planning revision surgery ACDF. Machine algorithms that are known be adept at image classification may applied problem ACDF plate identification.A total 402 containing 15 different types...
Study Design: A retrospective cohort study. Objective: The purpose of this study is to develop a machine learning algorithm predict nonhome discharge after cervical spine surgery that validated and usable on national scale ensure generalizability elucidate candidate drivers for prediction. Summary Background Data: Excessive length hospital stay can be attributed delays in postoperative referrals intermediate care rehabilitation centers or skilled nursing facilities. Accurate preoperative...
Abstract Background: Small cell lung cancer (SCLC) is the most aggressive form of cancer, accounting for 14% cancers. It associated with poor outcomes and few effective treatments. Identification novel therapeutic targets imperative improving treatment outcomes. In our previous work we identified several DNA repair proteins including check point kinase 1 (Chk1) poly (ADP-ribose) polymerase (PARP1) that are overexpressed in SCLC high priority candidate targets. TP53-mutant cells (a hallmark...
The "weekend effect" occurs when patients cared for during weekends versus weekdays experience worse outcomes. But reasons this effect are unclear, especially amongst undergoing elective cervical spinal fusion (ECSF). Our aim was to analyze whether index weekend admission affects 30- and 90-day readmission rates post-ECSF.All ECSF > 18 years were retrospectively identified from the 2016-2018 Healthcare Cost Utilization Project Nationwide Readmissions Database (NRD), using unique patient...
Abstract Background: Given global population growth and aging, it is imperative to prioritize early eye disease detection treatment. However, the current specialist workforce capacity not bridging growing gap, making important consider alternative solutions for increasing screening capabilities. This study compared virtual reality (VR) vision exams that help evaluate retinal health, such as 24-2 perimetry, Ishihara color blindness, Amsler grid tests, against their in-clinic counterparts....