A5033786348- Radiomics and Machine Learning in Medical Imaging
- Palliative Care and End-of-Life Issues
- Lung Cancer Diagnosis and Treatment
- Cancer survivorship and care
- Artificial Intelligence in Healthcare and Education
- Pancreatic and Hepatic Oncology Research
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Lung Cancer Treatments and Mutations
- Gene expression and cancer classification
- Neuroendocrine Tumor Research Advances
- Biomedical Text Mining and Ontologies
- Family Support in Illness
- Advanced Radiotherapy Techniques
- Glioma Diagnosis and Treatment
- Topic Modeling
- Chronic Disease Management Strategies
- Advanced Data Storage Technologies
- Natural Language Processing Techniques
- Cancer Genomics and Diagnostics
- IoT and Edge/Fog Computing
- Cancer Treatment and Pharmacology
- Ethics in Clinical Research
- Breast Cancer Treatment Studies
- Cloud Computing and Resource Management
Stanford University
2019-2025
Stanford Cancer Institute
2020
Using routine preradiation treatment CT simulation scans and tumor segmentation data, a deep learning model was developed to detect segment lung tumors, good performance achieved on diverse datasets.
Despite growing interest in using large language models (LLMs) healthcare, current explorations do not assess the real-world utility and safety of LLMs clinical settings. Our objective was to determine whether two can serve information needs submitted by physicians as questions an informatics consultation service a safe concordant manner. Sixty six from consult were GPT-3.5 GPT-4 via simple prompts. 12 assessed LLM responses' possibility patient harm concordance with existing reports...
Abstract Objective Accurate electronic phenotyping is essential to support collaborative observational research. Supervised machine learning methods can be used train phenotype classifiers in a high-throughput manner using imperfectly labeled data. We developed 10 this approach and evaluated performance across multiple sites within the Observational Health Data Sciences Informatics (OHDSI) network. Materials Methods constructed Automated PHenotype Routine for Definition, Identification,...
Live migration is an essential feature in virtualization technology where a running Virtual Machine (VM) from one physical host migrated to another without any service disruptions. Indisputably the benefits reaped VM are high availability, load balancing, energy saving and disaster recovery which desired data centre attributes. The initiated by administrator part of procedure make informed decision isolate identify appropriate be migrated, lest impressive performance may not achieved....
Patients with cancer are at high risk for having mental disorders, resulting in widespread psychosocial screening efforts. However, there is a need population-based and longitudinal studies of disorders among patients who have gastrointestinal particular elderly patients.We used the SEER-Medicare database to identify aged ≥65 years colorectal, pancreatic, gastric, hepatic/biliary, esophageal, or anal cancer. Earlier (12 months before up 6 after diagnosis) subsequent disorder diagnoses were...
Abstract Background We evaluated whether pre- and mid-treatment metabolic tumor volume (MTV) predicts per lesion local recurrence (LR) in patients treated with definitive radiation therapy (RT, dose≥60 Gy) for locally advanced non-small cell lung cancer (NSCLC). Methods retrospectively reviewed records of stage III NSCLC from 2006 to 2018 mid-RT PET-CT. measured the MTV lesions on pre-RT (MTV pre ) mid LR was defined as within planning target volume. Receiver operating characteristic (ROC)...
Abstract The clinical and financial effects of mental disorders are largely unknown among gastrointestinal (GI) cancer patients. Using the Surveillance, Epidemiology, End Results (SEER)‐Medicare linked database, we identified patients whose first was a primary colorectal, pancreatic, gastric, hepatic/biliary, esophageal, or anal as well those with coexisting depression, anxiety, psychotic, bipolar disorder. Survival, chemotherapy use, total healthcare expenditures, patient out‐of‐pocket...
Abstract Background Elderly patients with gastrointestinal cancer and mental illness have significant comorbidities that can impact the quality of their care. We investigated relationship between frequent emergency department (ED) use in last month life, an indicator for poor end‐of‐life care quality, among elderly cancers. Methods used SEER‐Medicare data to identify decedents cancers who were diagnosed 2004 2013 at least 66 years old time diagnosis (median age: 80 years, range: 66–117...
Verifying factual claims is critical for using large language models (LLMs) in healthcare. Recent work has proposed fact decomposition, which uses LLMs to rewrite source text into concise sentences conveying a single piece of information, as an approach fine-grained verification. Clinical documentation poses unique challenges decomposition due dense terminology and diverse note types. To explore these challenges, we present FactEHR, dataset consisting full document decompositions 2,168...
ABSTRACT Objective Accurate electronic phenotyping is essential to support collaborative observational research. Supervised machine learning methods can be used train phenotype classifiers in a high-throughput manner using imperfectly labeled data. We developed ten this approach and evaluated performance across multiple sites within the Observational Health Sciences Informatics (OHDSI) network. Materials Methods constructed Automated PHenotype Routine for Definition, Identification, Training...
811 Background: Aggressive care at the end-of-life can contradict patients’ wishes, negatively impact patient quality of life, and contribute to overall health expenditures. Patients with mental disorders (MD) often experience disparities in medical have poorer clinical outcomes. We investigated on emergency department (ED) use end life among elderly patients gastrointestinal (GI) malignancies. Methods: conducted a retrospective cohort study using SEER-Medicare database. identified aged 66...