52426 research outputs found
Sort by
Absence of Medical Record Documentation of Advance Care Planning Status in At-Risk Emergency Department Patients.
No full textBackground The majority of those aged 65 and older will visit the emergency department (ED) in the last six months of life. Knowing a patient\u27s goals of care is important, and existing medical records do not always represent them well. We set out to determine the baseline availability of advance directives and goals of treatment in those ED patients at increased risk for mortality. Methods This prospective cohort study included a sample of adult ED patients who had a mortality predictor by an End-of-Life (EOL) Deterioration Index-guided electronic best practice advisory (BPA) or admission to any of the network\u27s intensive care units (ICU). Electronic medical record (EMR) abstraction was used to evaluate for documentation of healthcare proxy, healthcare power of attorney (POA), living will, advance care plans, or physician orders for life-sustaining treatment (POLST). Results A total of 9,321 patient encounters, representing 7,204 unique patients, were included in the analyzed sample. Most patients\u27 charts lacked advance care planning documentation such as healthcare proxy (98.7%, N=9200), healthcare POA (93.0%, N=8665), living will (94.6%, N=8816), advance care planning status (66.8%, N=6226), and POLST (95.8%, N=8928). Overall, urban sites had a larger percentage of encounters in which a high-risk patient might benefit from advance care planning discussions than rural sites. Females had a higher percentage of documentation across all variables of goals of care, with significant differences in healthcare POA (p \u3c 0.001), advance directives (p \u3c 0.001), and POLST (p = 0.008). Conclusions The majority of patients with a higher risk for mortality, as indicated by an EOL Deterioration Index-guided BPA or hospital ICU admission, do not have documentation in the EMR across all variables of goals of care
Refractory methemoglobinemia complicated by serotonin syndrome and anticholinergic toxidrome: successful management with manual exchange blood transfusion
No full textCorrigendum to Surgical resection of diffuse pulmonary arteriovenous malformations (PAVMs) [JTCVS Open Volume 23, February 2025, Pages 309-317].
No full text[This corrects the article DOI: 10.1016/j.xjon.2024.11.002.]
Code-Free Machine Learning for the Detection of Common Ophthalmic Diseases.
No full textPURPOSE: We explore a code-free method enabling physicians without programming experience to develop machine learning (ML) models for detecting diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma from fundus photographs.
METHODS: Two classification models were developed using Google Vertex AI\u27s no-code AutoML Vision platform: a binary model detecting any pathology and a multi-class model classifying specific diseases. The development dataset consisted of 800 fundus photography images (200 each of DR, AMD, glaucoma, and normal) from the publicly available Fundus Image dataset for Vessel Segmentation. Ten percent of the dataset was saved for testing and 10% for internal validation. External validation was performed using the Eye Disease Diagnosis and Fundus Synthesis dataset, from which 100 single-diagnosis images per class were randomly selected (total N = 400). Model performances were evaluated using area under the precision-recall curve (AUPRC), precision, recall, accuracy, F1 score, and confidence score analysis.
RESULTS: Internally, the binary model yielded an AUPRC of 0.967, with 95.0% precision and recall. The multi-class model had an AUPRC of 0.906, with 91.0% precision and 90.0% recall. On external validation, the binary model reached 92.3% accuracy, whereas the multi-class model achieved 90% overall accuracy.
CONCLUSIONS: Code-free ML approaches can enable physicians to create ML models for retinal disease detection without requiring programming expertise, supporting early detection of eye diseases.
TRANSLATIONAL RELEVANCE: This work bridges the gap between AI research and clinical deployment by demonstrating that physicians can independently build ML models using accessible, no-code tools
Bridging to Heart Transplantation With Intraaortic Balloon Pump Versus Impella 5.5.
No full textIn this study, we compare the clinical characteristics and courses of patients directly bridged to heart transplant with intraaortic balloon pump (IABP) versus Impella 5.5. We performed a retrospective cohort study of single-center institutional data including all adult patients at our institution bridged to transplant with either IABP or Impella 5.5 support between October 18, 2018, and May 31, 2023. Ninety-one heart transplant recipients were included in this study, of whom 54 (59%) were bridged on IABP and 37 (41%) were bridged on Impella 5.5. Patients supported with Impella 5.5 had comparable baseline characteristics compared to those bridged on IABP (all p \u3e 0.05). However, Impella 5.5 patients had lower vasoactive inotropic scores during their temporary mechanical circulatory support (MCS) period than those bridged on IABP (all p \u3c 0.05). Duration of MCS and post-transplant intensive care unit (ICU) length of stay were longer for Impella 5.5 patients (all p \u3c 0.05), but rates of complications after transplant were comparable (all p \u3e 0.05). Survival at 1 year post-transplant was significantly greater for the Impella 5.5 group (100% vs. 87%; p = 0.039). Given the increased use of MCS as a bridge to transplant, this project has important implications for preoperative management of waitlist patients
A retrospective analysis of the association of obesity with anthracycline- and trastuzumab-induced cardiotoxicity in the treatment of breast cancer and lymphoma.
No full textINTRODUCTION: Trastuzumab and anthracyclines are mainstays of chemotherapy in breast cancer and lymphoma patients but may cause significant cardiotoxicity, which may result in alterations to chemotherapy dose, schedule, or agent. Obesity is increasingly prevalent in the United States and is a significant risk factor for both cardiovascular disease and certain cancers. We aimed to assess the relationship between obesity and the risk of developing chemotherapy-associated cardiotoxicity.
MATERIAL AND METHODS: A retrospective chart review was conducted of all patients who received trastuzumab or anthracyclines over a 5-year period from January 1, 2008, to December 31, 2012 at our tertiary care center in the Northeastern United States. Obesity was defined as a body mass index (BMI) ≥ 30 kg/m
RESULTS: Of the 368 patients receiving either trastuzumab or anthracyclines, 16 patients developed cardiotoxicity. Demographically, age, race, BMI, body surface area (BSA), and overall weight did not differ between the patients who developed cardiotoxicity and those who did not. The mean dose of anthracycline and trastuzumab did not differ between the patients who developed cardiotoxicity and those who did not. Obesity was not found to increase the odds of developing cardiotoxicity and was slightly protective. A non-significant decrease in the odds of developing cardiotoxicity was found for every one-unit increase in BMI. In a multivariable model using BMI as a continuous predictor and controlling for BMI, age, hypertension, chemotherapy type, and coronary artery disease, the only significant predictor of cardiotoxicity was a previous history of arrhythmia.
CONCLUSIONS: Obesity was not a significant risk factor for patients developing cardiotoxicity from trastuzumab- or anthracycline-based chemotherapy and may be a protective factor for cardiotoxicity. Additional studies with greater statistical power are needed to further evaluate this effect and independently evaluate obesity as a risk factor for cardiotoxicity
Minimum Pathology Reporting Elements for Melanoma: A Review of Reporting Guidelines and Proposal for Minimum Reporting Elements for a Quality Pathology Report by the Task Force of the American Society of Dermatopathology.
No full textGuidelines have been proposed for the pathology reporting of melanoma to ensure inclusion of data elements important for patient care. Compliance with guidelines has been made a yardstick for quality performance. However, there is controversy about how comprehensive a report must be, which is why the American Society of Dermatopathology has formed a task force with the goal of defining minimum data elements that should be included in a pathology report of a primary cutaneous melanoma. Importantly, additional information can or at times should be documented if a pathologist believes it is valuable to the clinical care team of a particular patient. The proposed minimum reporting guidelines outlined herein largely reflect core reporting elements by various professional organizations. Data elements must be included if they are needed for pathologic staging. Excisions require a margin status, but detailed margin metrics are not required for most cases. Furthermore, histopathologic subtyping of melanoma in situ is not routinely needed. Whether or not invasive melanoma should be subclassified depends on clinical relevance and whether the available evidence permits a definitive melanoma subclassification. When the minimum data elements are included, a pathology report should be considered compliant with quality reporting guidelines
Development and Validation of an Artificial Intelligence Digital Pathology Biomarker to Predict Benefit of Long-Term Hormonal Therapy and Radiotherapy in Men With High-Risk Prostate Cancer Across Multiple Phase III Trials.
No full textPURPOSE: Long-term androgen deprivation therapy (ADT) improves survival in men with high-risk localized prostate cancer (PCa) receiving radiotherapy (RT). Predictive biomarkers are needed to guide ADT duration.
METHODS: A multimodal artificial intelligence (MMAI)-derived predictive biomarker was trained for long-term (LT) versus short-term (ST) ADT using pretreatment digital prostate biopsy images and clinical data (age, prostate-specific antigen, Gleason, and T stage) from six NRG Oncology phase III randomized radiotherapy trials. The novel MMAI-derived biomarker was developed to predict the differential benefit of LT-ADT on the primary end point, distant metastasis (DM). MMAI predictive utility was validated on a seventh randomized trial, RTOG 9202 (N = 1,192), which randomly assigned men to RT + ST-ADT (4 months) versus RT + LT-ADT (28 months). Fine-Gray and cumulative incidence analyses for DM, and secondarily, death with DM, were performed. Deaths without DM were treated as competing risks.
RESULTS: In the validation cohort (median follow-up, 17.2 years), LT-ADT significantly improved DM from 26% to 17% (subdistribution hazard ratio [sHR], 0.64 [95% CI, 0.50 to 0.82],
CONCLUSION: To our knowledge, the MMAI model is the first validated predictive biomarker to guide ADT duration with RT in localized/locally advanced PCa. Approximately one third of men with high-risk PCa could safely be spared the additional 24 months of ADT and the associated morbidity
