Background: Natural language processing models such as ChatGPT can generate text-based content and are poised to become a major information source in medicine and beyond. The accuracy and completeness of ChatGPT for medical queries is not known. Methods: Thirty-three physicians across 17 specialties generated 284 medical questions that they subjectively classified as easy, medium, or hard with either binary (yes/no) or descriptive answers. The physicians then graded ChatGPT-generated answers to these questions for accuracy (6-point Likert scale; range 1 – completely incorrect to 6 – completely correct) and completeness (3-point Likert scale; range 1 – incomplete to 3 - complete plus additional context). Scores were summarized with descriptive statistics and compared using Mann-Whitney U or Kruskal-Wallis testing. Results: Across all questions (n=284), median accuracy score was 5.5 (between almost completely and completely correct) with mean score of 4.8 (between mostly and almost completely correct). Median completeness score was 3 (complete and comprehensive) with mean score of 2.5. For questions rated easy, medium, and hard, median accuracy scores were 6, 5.5, and 5 (mean 5.0, 4.7, and 4.6; p=0.05). Accuracy scores for binary and descriptive questions were similar (median 6 vs. 5; mean 4.9 vs. 4.7; p=0.07). Of 36 questions with scores of 1-2, 34 were re-queried/re-graded 8-17 days later with substantial improvement (median 2 vs. 4; p<0.01). Conclusions: ChatGPT generated largely accurate information to diverse medical queries as judged by academic physician specialists although with important limitations. Further research and model development are needed to correct inaccuracies and for validation.
Background: Based on empirical evidence, a personal history of nonmelanoma skin cancer (NMSC) has been hypothesized to be a risk factor for other cancers. Others hypothesize that NMSC may be a marker of high cutaneous vitamin D synthesis and therefore inversely associated with risk of other malignancies. To reconcile these divergent views, we carried out a systematic review to determine the association between NMSC and subsequent risk of other cancers.Methods: Bibliographic databases were searched through March 2009. Studies were included if sufficient information was presented to estimate the risk of developing other cancers following NMSC. Studies were reviewed and data were abstracted independently in duplicate with disagreements resolved by consensus.Results: Of the 21 included studies, 15 reported the association between NMSC and risk of all other cancers combined. NMSC was significantly associated with increased risk of another malignancy among cohort studies based on cancer registries [summary random-effects relative risk (SRR), 1.12; 95% confidence interval (CI), 1.07-1.17; n = 12 studies) and those with individual-level data (SRR, 1.49; 95% CI, 1.12-1.98; n = 3). In stratified analyses of registry studies, this association held true for both squamous (SRR, 1.17; 95% CI, 1.12-1.23; n = 7) and basal cell carcinoma (SRR, 1.09; 95% CI, 1.01-1.17; n = 7), and both men (SRR, 1.14; 95% CI, 1.09-1.20; n = 12) and women (SRR, 1.10; 95% CI, 1.04-1.15; n = 12).Conclusions: Strong, consistent evidence indicates that a personal history of NMSC is associated with increased risk of developing other malignancies.Impact: For unknown reasons, NMSC may be a risk factor for other cancers. Cancer Epidemiol Biomarkers Prev;
Objective To study systemic lupus erythematosus (SLE) in the electronic health record (EHR), we must accurately identify patients with SLE. Our objective was to develop and validate novel EHR algorithms that use International Classification of Diseases, Ninth Revision Clinical Modification (ICD-9) codes, laboratory testing, and medications to identify SLE patients. Methods We used Vanderbilt's Synthetic Derivative (SD), a de-identified version of the EHR, with 2.5 million subjects. We selected all individuals with at least one SLE ICD-9 code (710.0) yielding 5959 individuals. To create a training set, 200 were randomly selected for chart review. A subject was defined as a case if diagnosed with SLE by a rheumatologist, nephrologist, or dermatologist. Positive predictive values (PPVs) and sensitivity were calculated for combinations of code counts of the SLE ICD-9 code, a positive anti-nuclear antibody (ANA), ever use of medications, and a keyword of “lupus” in the problem list. The algorithms with the highest PPV were each internally validated using a random set of 100 individuals from the remaining 5759 subjects. Results The algorithm with the highest PPV at 95% in the training set and 91% in the validation set was 3 or more counts of the SLE ICD-9 code, ANA positive (≥ 1:40), and ever use of both disease-modifying antirheumatic drugs (DMARDs) and steroids while excluding individuals with systemic sclerosis and dermatomyositis ICD-9 codes. Conclusion We developed and validated the first EHR algorithm that incorporates lab values and medications with the SLE ICD-9 code to identify patients with SLE accurately.
Purpose: Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma. Experimental Design: We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan–Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400). Results: The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400). Conclusions: Histology slides and patients' clinicodemographic characteristics are readily available through standard of care and have the potential to predict ICI treatment outcomes. With prospective validation, we believe our approach has potential for integration into clinical practice.
Organ transplant recipients (OTRs) are at increased risk of developing non-melanoma skin cancers (NMSC). This has long been thought to be due to immunosuppression and viral infection. However, skin cancer risk among individuals with AIDS or iatrogenic immunodeficiency does not approach the levels seen in OTRs, suggesting other factors play a critical role in oncogenesis. In clinical trials of OTRs, switching from calcineurin inhibitors to mammalian Target of Rapamycin (mTOR) inhibitors consistently led to a significant reduction in the risk of developing new skin cancers. New evidence suggests calcineurin inhibitors interfere with p53 signaling and nucleotide excision repair. These two pathways are associated with NMSC, and squamous cell carcinoma (SCC) in particular. This finding may help explain the predominance of SCC over basal cell carcinoma in this population. mTOR inhibitors do not appear to impact these pathways. Immunosuppression, viral infection, and impaired DNA repair and p53 signaling all interact in OTRs to create a phenotype of extreme risk for NMSC.
As a method for sustained drug delivery, subcutaneous administration using Matrigel proved more efficacious than intraperitoneal injection for in vivo delivery of retinoids to cone photoreceptors. These experiments are the first to show a sustained delivery of retinoids in mice and suggest a strategy for potential clinical therapeutic development.
As cone photoreceptors mediate vision in bright light, their photopigments are bleached at a rapid rate and require substantial recycling of the chromophore 11-cis retinal (RAL) for continued function. The retinal pigment epithelium (RPE) supplies 11-cis RAL to both rod and cone photoreceptors; however, stringent demands imposed by the function of cones in bright light exceed the output from this source. Recent evidence has suggested that cones may be able to satisfy this demand through privileged access to an additional source of chromophore located within the inner retina. In this study, we demonstrate that the protein RPE65, previously identified in RPE as the isomerohydrolase of the RPE-retinal visual cycle, is found within cones of the rod-dominant mouse retina, and the level of RPE65 in cones is inversely related to the level in the RPE. The light sensitivity of cone ERGs of BALB/c mice, which had an undetectable level of cone RPE65, was enhanced by ~3-fold with administration of exogenous chromophore, indicating that the cones of these animals are chromophore deficient. This enhancement with chromophore administration was not observed in C57BL6 mice, whose cones contain RPE65. These results demonstrate that RPE65 within cones may be essential for the efficient regeneration of cone photopigments under bright light conditions.
BackgroundSystemic sclerosis (SSc) is a rare disease with studies limited by small sample sizes. Electronic health records (EHRs) represent a powerful tool to study patients with rare diseases such as SSc, but validated methods are needed. We developed and validated EHR-based algorithms that incorporate billing codes and clinical data to identify SSc patients in the EHR.MethodsWe used a de-identified EHR with over 3 million subjects and identified 1899 potential SSc subjects with at least 1 count of the SSc ICD-9 (710.1) or ICD-10-CM (M34*) codes. We randomly selected 200 as a training set for chart review. A subject was a case if diagnosed with SSc by a rheumatologist, dermatologist, or pulmonologist. We selected the following algorithm components based on clinical knowledge and available data: SSc ICD-9 and ICD-10-CM codes, positive antinuclear antibody (ANA) (titer ≥ 1:80), and a keyword of Raynaud’s phenomenon (RP). We performed both rule-based and machine learning techniques for algorithm development. Positive predictive values (PPVs), sensitivities, and F-scores (which account for PPVs and sensitivities) were calculated for the algorithms.ResultsPPVs were low for algorithms using only 1 count of the SSc ICD-9 code. As code counts increased, the PPVs increased. PPVs were higher for algorithms using ICD-10-CM codes versus the ICD-9 code. Adding a positive ANA and RP keyword increased the PPVs of algorithms only using ICD billing codes. Algorithms using ≥ 3 or ≥ 4 counts of the SSc ICD-9 or ICD-10-CM codes and ANA positivity had the highest PPV at 100% but a low sensitivity at 50%. The algorithm with the highest F-score of 91% was ≥ 4 counts of the ICD-9 or ICD-10-CM codes with an internally validated PPV of 90%. A machine learning method using random forests yielded an algorithm with a PPV of 84%, sensitivity of 92%, and F-score of 88%. The most important feature was RP keyword.ConclusionsAlgorithms using only ICD-9 codes did not perform well to identify SSc patients. The highest performing algorithms incorporated clinical data with billing codes. EHR-based algorithms can identify SSc patients across a healthcare system, enabling researchers to examine important outcomes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.