Voriconazole Metabolism is Associated with the Number of Skin Cancers Per Patient.

Voriconazole exposure is associated with skin cancer, but it is unknown how the full spectrum of its metabolizer phenotypes impacts this association. We conducted a retrospective cohort study to determine how variation in metabolism of voriconazole as measured by metabolizer status of CYP2C19 is associated with the total number of skin cancers a patient develops and the rate of development of the first skin cancer after treatment. There were 1,739 organ transplant recipients with data on CYP2C19 phenotype. Of these, 134 were exposed to voriconazole. There was a significant difference in the number of skin cancers after transplant based on exposure to voriconazole, metabolizer phenotype, and the interaction of these two (p < 0.01 for all three). This increase was driven primarily by number of squamous cell carcinomas among rapid metabolizes with voriconazole exposure (p < 0.01 for both). Patients exposed to voriconazole developed skin cancers more rapidly than those without exposure (Fine-Grey hazard ratio 1.78, 95% confidence interval 1.19-2.66). This association was similarly driven by development of SCC (Fine-Grey hazard ratio 1.83, 95% confidence interval 1.14-2.94). Differences in voriconazoles metabolism are associated with an increase in the number of skin cancers developed after transplant, particularly SCC.

Voriconazole metabolism is associated with the number of skin cancers per patient.

Voriconazole exposure is associated with skin cancer, but it is unknown how the full spectrum of its metabolizer phenotypes impacts this association. We conducted a retrospective cohort study to determine how variation in metabolism of voriconazole as measured by metabolizer status of CYP2C19 is associated with the total number of skin cancers a patient develops and the rate of development of the first skin cancer after treatment. There were 1,739 organ transplant recipients with data on CYP2C19 phenotype. Of these, 134 were exposed to voriconazole. There was a significant difference in the number of skin cancers after transplant based on exposure to voriconazole, metabolizer phenotype, and the interaction of these two (p < 0.01 for all three). This increase was driven primarily by number of squamous cell carcinomas among rapid metabolizes with voriconazole exposure (p < 0.01 for both). Patients exposed to voriconazole developed skin cancers more rapidly than those without exposure (Fine-Grey hazard ratio 1.78, 95% confidence interval 1.19-2.66). This association was similarly driven by development of SCC (Fine-Grey hazard ratio 1.83, 95% confidence interval 1.14-2.94). Differences in voriconazoles metabolism are associated with an increase in the number of skin cancers developed after transplant, particularly SCC.

Toward personalized skin cancer care: multiple skin cancer development in five cohorts.

Importance: Many patients will develop more than one skin cancer, however most research to date has examined only case status. Objective: Describe the frequency and timing of the treatment of multiple skin cancers in individual patients over time. Design: Longitudinal claims and electronic health record-based cohort study. Setting: Vanderbilt University Medical Center database called the Synthetic Derivative, VA, Medicare, Optum Clinformatics® Data Mart Database, IBM Marketscan. Participants: All patients with a Current Procedural Terminology code for the surgical management of a skin cancer in each of five cohorts. Exposures: None. Main Outcomes and Measures: The number of CPT codes for skin cancer treatment in each individual occurring on the same day as an ICD code for skin cancer over time. Results: Our cohort included 5,508,374 patients and 13,102,123 total skin cancers treated. Conclusions and Relevance: Nearly half of patients treated for skin cancer were treated for more than one skin cancer. Patients who have not developed a second skin cancer by 2 years after the first are unlikely to develop multiple skin cancers within the following 5 years. Better data formatting will allow for improved granularity in identifying individuals at high risk for multiple skin cancers and those unlikely to benefit from continued annual surveillance. Resource planning should take into account not just the number of skin cancer cases, but the individual burden of disease.

A Report on the Safety of Acitretin Use in Renal Failure Patients on Hemodialysis.

Acitretin, commonly used for severe psoriasis and keratinocyte carcinoma chemoprevention in high-risk patients, is contraindicated in patients with end stage renal disease on hemodialysis. However, these patients often lack medication choices and in certain clinical scenarios, the benefits of acitretin may outweigh the potential risks. We identified 24 end stage renal disease patients on HD taking acitretin from Duke and Vanderbilt University Medical Centers. While adverse effects were common, patients did not frequently discontinue the medication due to them. We also found no association between acitretin with hospital admissions or mortality. We lastly found statistically significant increases in ALP and total bilirubin when on acitretin and dialysis compared to baseline. However, there was no dose-dependency or temporal association with acitretin or hemodialysis initiation. Based off these preliminary findings, we find that acitretin may safely be used in patients receiving HD with close monitoring of ALP and bilirubin.

Interoperability of phenome-wide multimorbidity patterns: a comparative study of two large-scale EHR systems.

Background: Electronic health records (EHR) are increasingly used for studying multimorbidities. However, concerns about accuracy, completeness, and EHRs being primarily designed for billing and administrative purposes raise questions about the consistency and reproducibility of EHR-based multimorbidity research. Methods: Utilizing phecodes to represent the disease phenome, we analyzed pairwise comorbidity strengths using a dual logistic regression approach and constructed multimorbidity as an undirected weighted graph. We assessed the consistency of the multimorbidity networks within and between two major EHR systems at local (nodes and edges), meso (neighboring patterns), and global (network statistics) scales. We present case studies to identify disease clusters and uncover clinically interpretable disease relationships. We provide an interactive web tool and a knowledge base combining data from multiple sources for online multimorbidity analysis. Findings: Analyzing data from 500,000 patients across Vanderbilt University Medical Center and Mass General Brigham health systems, we observed a strong correlation in disease frequencies (Kendall's τ = 0.643) and comorbidity strengths (Pearson ρ = 0.79). Consistent network statistics across EHRs suggest similar structures of multimorbidity networks at various scales. Comorbidity strengths and similarities of multimorbidity connection patterns align with the disease genetic correlations. Graph-theoretic analyses revealed a consistent core-periphery structure, implying efficient network clustering through threshold graph construction. Using hydronephrosis as a case study, we demonstrated the network's ability to uncover clinically relevant disease relationships and provide novel insights. Interpretation: Our findings demonstrate the robustness of large-scale EHR data for studying phenome-wide multimorbidities. The alignment of multimorbidity patterns with genetic data suggests the potential utility for uncovering shared biology of diseases. The consistent core-periphery structure offers analytical insights to discover complex disease interactions. This work also sets the stage for advanced disease modeling, with implications for precision medicine. Funding: VUMC Biostatistics Development Award, the National Institutes of Health, and the VA CSRD.

Comparison of late-onset and non-late-onset systemic lupus erythematosus individuals in a real-world electronic health record cohort.

Objective: Late-onset systemic lupus erythematosus (LO-SLE) is defined as SLE diagnosed at age 50 years or later. Current studies on LO-SLE are small and have conflicting results.Methods: Using a large, electronic health record (EHR)-based cohort of SLE individuals, we compared demographics, disease characteristics, SLE-specific antibodies, and medication prescribing practices in LO (n = 123) vs. NLO-SLE (n = 402) individuals.Results: The median age (interquartile range) at SLE diagnosis was 60 (56-67) years for LO-SLE and 28 (20-38) years for NLO-SLE. Both groups were predominantly female (85% vs. 91%, p = 0.10). LO-SLE individuals were more likely to be White than NLO-SLE individuals (74% vs. 60%, p = 0.005) and less likely to have positive dsDNA (39% vs. 58%, p = 0.001) and RNP (17% vs. 32%, p = 0.02) with no differences in Smith, SSA, and SSB. Autoantibody positivity declined with increasing age at SLE diagnosis. LO-SLE individuals were less likely to develop SLE nephritis (9% vs. 29%, p < 0.001) and less likely to be prescribed multiple classes of SLE medications including antimalarials (90% vs. 95%, p = 0.04), azathioprine (17% vs. 31%, p = 0.002), mycophenolate mofetil (12% vs. 38%, p < 0.001), and belimumab (2% vs. 8%, p = 0.02).Conclusion: LO-SLE individuals may be less likely to fit an expected course for SLE with less frequent positive autoantibodies at diagnosis and lower rates of nephritis, even after adjusting for race. Understanding how age impacts SLE disease presentation could help reduce diagnostic delays in SLE.

Mendelian Randomization Analysis of Genetic Proxies of Thiazide Diuretics and the Reduction of Kidney Stone Risk.

Importance: Clinical trial data have called into question the efficacy of thiazide diuretics for the prevention of kidney stones. Objective: To identify whether there is an association between genetic proxies of thiazide diuretics and the risk of kidney stones. Design, Setting, and Participants: This genetic association study undertook a mendelian randomization analysis of derived exposures and outcomes from genome-wide association study summary statistics. Genetic proxies of thiazide diuretics were derived from the International Consortium for Blood Pressure. Kidney stone cases and controls were derived from the Million Veteran Program, UK Biobank, and the FinnGen study. These cross-sectional designs do not report a duration of follow-up. Data analysis was performed in May 2023. Exposure: Genetic proxies of thiazide diuretics were genetic variants in the thiazide-sensitive sodium chloride cotransporter gene associated with systolic blood pressure. Genetic proxies of ß-blockers and systolic blood pressure served as negative controls. Main Outcomes and Measures: The main outcome was the odds of kidney stones. The secondary outcomes were serum laboratory values relevant to the treatment of kidney stones. Results: The main analysis included up to 1 079 657 individuals, including 50 832 kidney stone cases and 1 028 825 controls. In a meta-analysis of all cohorts, genetic proxies of thiazide diuretics were associated with a lower odds of kidney stones (OR, 0.85; 95% CI, 0.81-0.89; P < .001). Genetic proxies of ß-blockers (OR, 1.02; 95% CI, 0.96-1.07; P = .52) and systolic blood pressure (OR, 1.00; 95% CI, 1.00-1.01; P = .49) were not associated with kidney stones. Genetic proxies of thiazide diuretics were associated with higher serum calcium (ß [SE], 0.051 [0.0092]; P < .001) and total cholesterol (ß [SE], 0.065 [0.015]; P < .001), but lower serum potassium (ß [SE], -0.073 [0.022]; P < .001). Conclusions and Relevance: In this genetic association study, genetic proxies of thiazide diuretics were associated with reduced kidney stone risk. This finding reflects a drug effect over the course of a lifetime, unconstrained by the limited follow-up period of clinical trials.

Next-generation phenotyping: introducing phecodeX for enhanced discovery research in medical phenomics.

MOTIVATION: Phecodes are widely used and easily adapted phenotypes based on International Classification of Diseases codes. The current version of phecodes (v1.2) was designed primarily to study common/complex diseases diagnosed in adults; however, there are numerous limitations in the codes and their structure. RESULTS: Here, we present phecodeX, an expanded version of phecodes with a revised structure and 1,761 new codes. PhecodeX adds granularity to phenotypes in key disease domains that are under-represented in the current phecode structure-including infectious disease, pregnancy, congenital anomalies, and neonatology-and is a more robust representation of the medical phenome for global use in discovery research. AVAILABILITY AND IMPLEMENTATION: phecodeX is available at https://github.com/PheWAS/phecodeX.

Genetic Inhibition of APOL1 Pore-Forming Function Prevents APOL1-Mediated Kidney Disease.

SIGNIFICANCE STATEMENT: African Americans are at increased risk of CKD in part due to high-risk (HR) variants in the apolipoprotein L1 ( APOL1 ) gene, termed G1/G2. A different APOL1 variant, p.N264K , reduced the risk of CKD and ESKD among carriers of APOL1 HR variants to levels comparable with individuals with APOL1 low-risk variants in an analysis of 121,492 participants of African ancestry from the Million Veteran Program (MVP). Functional genetic studies in cell models showed that APOL1 p.N264K blocked APOL1 pore-forming function and ion channel conduction and reduced toxicity of APOL1 HR mutations. Pharmacologic inhibitors that mimic this mutation blocking APOL1 -mediated pore formation may be able to prevent and/or treat APOL1 -associated kidney disease. BACKGROUND: African Americans are at increased risk for nondiabetic CKD in part due to HR variants in the APOL1 gene. METHODS: We tested whether a different APOL1 variant, p.N264K , modified the association between APOL1 HR genotypes (two copies of G1/G2) and CKD in a cross-sectional analysis of 121,492 participants of African ancestry from the MVP. We replicated our findings in the Vanderbilt University Biobank ( n =14,386) and National Institutes of Health All of Us ( n =14,704). Primary outcome was CKD and secondary outcome was ESKD among nondiabetic patients. Primary analysis compared APOL1 HR genotypes with and without p.N264K . Secondary analyses included APOL1 low-risk genotypes and tested for interaction. In MVP, we performed sequential logistic regression models adjusting for demographics, comorbidities, medications, and ten principal components of ancestry. Functional genomic studies expressed APOL1 HR variants with and without APOL1 p.N264K in cell models. RESULTS: In the MVP cohort, 15,604 (12.8%) had two APOL1 HR variants, of which 582 (0.5%) also had APOL1 p.N264K . In MVP, 18,831 (15%) had CKD, 4177 (3%) had ESKD, and 34% had diabetes. MVP APOL1 HR, without p.N264K , was associated with increased odds of CKD (odds ratio [OR], 1.72; 95% confidence interval [CI], 1.60 to 1.85) and ESKD (OR, 3.94; 95% CI, 3.52 to 4.41). In MVP, APOL1 p.N264K mitigated the renal risk of APOL1 HR, in CKD (OR, 0.43; 95% CI, 0.28 to 0.65) and ESKD (OR, 0.19; CI 0.07 to 0.51). In the replication cohorts meta-analysis, APOL1 p.N264K mitigated the renal risk of APOL1 HR in CKD (OR, 0.40; 95% CI, 0.18 to 0.92) and ESKD (OR, 0.19; 95% CI, 0.05 to 0.79). In the mechanistic studies, APOL1 p.N264K blocked APOL1 pore-forming function and ion channel conduction and reduced toxicity of APOL1 HR variants. CONCLUSIONS: APOL1 p.N264K is associated with reduced risk of CKD and ESKD among carriers of APOL1 HR to levels comparable with individuals with APOL1 low-risk genotypes.

Accuracy and Reliability of Chatbot Responses to Physician Questions.

Importance: Natural language processing tools, such as ChatGPT (generative pretrained transformer, hereafter referred to as chatbot), have the potential to radically enhance the accessibility of medical information for health professionals and patients. Assessing the safety and efficacy of these tools in answering physician-generated questions is critical to determining their suitability in clinical settings, facilitating complex decision-making, and optimizing health care efficiency. Objective: To assess the accuracy and comprehensiveness of chatbot-generated responses to physician-developed medical queries, highlighting the reliability and limitations of artificial intelligence-generated medical information. Design, Setting, and Participants: Thirty-three physicians across 17 specialties generated 284 medical questions that they subjectively classified as easy, medium, or hard with either binary (yes or no) or descriptive answers. The physicians then graded the chatbot-generated answers to these questions for accuracy (6-point Likert scale with 1 being completely incorrect and 6 being completely correct) and completeness (3-point Likert scale, with 1 being incomplete and 3 being complete plus additional context). Scores were summarized with descriptive statistics and compared using the Mann-Whitney U test or the Kruskal-Wallis test. The study (including data analysis) was conducted from January to May 2023. Main Outcomes and Measures: Accuracy, completeness, and consistency over time and between 2 different versions (GPT-3.5 and GPT-4) of chatbot-generated medical responses. Results: Across all questions (n = 284) generated by 33 physicians (31 faculty members and 2 recent graduates from residency or fellowship programs) across 17 specialties, the median accuracy score was 5.5 (IQR, 4.0-6.0) (between almost completely and complete correct) with a mean (SD) score of 4.8 (1.6) (between mostly and almost completely correct). The median completeness score was 3.0 (IQR, 2.0-3.0) (complete and comprehensive) with a mean (SD) score of 2.5 (0.7). For questions rated easy, medium, and hard, the median accuracy scores were 6.0 (IQR, 5.0-6.0), 5.5 (IQR, 5.0-6.0), and 5.0 (IQR, 4.0-6.0), respectively (mean [SD] scores were 5.0 [1.5], 4.7 [1.7], and 4.6 [1.6], respectively; P = .05). Accuracy scores for binary and descriptive questions were similar (median score, 6.0 [IQR, 4.0-6.0] vs 5.0 [IQR, 3.4-6.0]; mean [SD] score, 4.9 [1.6] vs 4.7 [1.6]; P = .07). Of 36 questions with scores of 1.0 to 2.0, 34 were requeried or regraded 8 to 17 days later with substantial improvement (median score 2.0 [IQR, 1.0-3.0] vs 4.0 [IQR, 2.0-5.3]; P < .01). A subset of questions, regardless of initial scores (version 3.5), were regenerated and rescored using version 4 with improvement (mean accuracy [SD] score, 5.2 [1.5] vs 5.7 [0.8]; median score, 6.0 [IQR, 5.0-6.0] for original and 6.0 [IQR, 6.0-6.0] for rescored; P = .002). Conclusions and Relevance: In this cross-sectional study, chatbot generated largely accurate information to diverse medical queries as judged by academic physician specialists with improvement over time, although it had important limitations. Further research and model development are needed to correct inaccuracies and for validation.

Novel Biomaterial Containing Gelatin, Manuka Honey, and Hydroxyapatite Enhanced Secondary Intention Healing Versus Standard Secondary Intention Healing in Mohs Surgical Defects on the Head and Distal Lower Extremities-A Randomized Controlled Trial: Pilot Study.

BACKGROUND: Randomized, comparative studies evaluating augmented secondary intention healing (SIH) compared with conventional SIH in dermatologic surgery are limited. This study aimed to evaluate whether the use of a novel biomaterial enhances SIH, particularly in shortening time to complete re-epithelialization. OBJECTIVE: The purpose of this study was to elucidate whether a novel biomaterial containing gelatin, manuka honey, and hydroxyapatite enhances SIH when compared with conventional SIH for surgical defects after Mohs micrographic surgery (MMS) on the head and distal lower extremities. MATERIALS AND METHODS: Thirty-seven patients were enrolled in this randomized controlled trial. Patients undergoing MMS on the head or distal lower extremities were eligible for recruitment. After clear surgical margins were obtained post-MMS, patients were randomized to receive standard SIH or biomaterial enhanced SIH. Patients had regularly scheduled follow-ups with questionnaires at each visit until complete re-epithelialization was achieved. RESULTS: Overall, there was no significant difference in time to re-epithelialization between standard SIH and biomaterial-enhanced SIH. However, there was a significant decrease in pain scores and skin thickness in the biomaterial-enhanced SIH group. CONCLUSION: Biomaterial-enhanced SIH is noninferior to standard SIH and produces less pain and favorable skin thickness compared with standard SIH. ClinicalTrials.gov listing: NCT04545476.

Phenotype Risk Score but Not Genetic Risk Score Aids in Identifying Individuals With Systemic Lupus Erythematosus in the Electronic Health Record.

OBJECTIVE: Systemic lupus erythematosus (SLE) poses diagnostic challenges. We undertook this study to evaluate the utility of a phenotype risk score (PheRS) and a genetic risk score (GRS) to identify SLE individuals in a real-world setting. METHODS: Using a de-identified electronic health record (EHR) database with an associated DNA biobank, we identified 789 SLE cases and 2,261 controls with available MEGAEX genotyping. A PheRS for SLE was developed using billing codes that captured American College of Rheumatology SLE criteria. We developed a GRS with 58 SLE risk single-nucleotide polymorphisms (SNPs). RESULTS: SLE cases had a significantly higher PheRS (mean ± SD 7.7 ± 8.0 versus 0.8 ± 2.0 in controls; P < 0.001) and GRS (mean ± SD 12.2 ± 2.3 versus 11.0 ± 2.0 in controls; P < 0.001). Black individuals with SLE had a higher PheRS compared to White individuals (mean ± SD 10.0 ± 10.1 versus 7.1 ± 7.2, respectively; P = 0.002) but a lower GRS (mean ± SD 9.0 ± 1.4 versus 12.3 ± 1.7, respectively; P < 0.001). Models predicting SLE that used only the PheRS had an area under the curve (AUC) of 0.87. Adding the GRS to the PheRS resulted in a minimal difference with an AUC of 0.89. On chart review, controls with the highest PheRS and GRS had undiagnosed SLE. CONCLUSION: We developed a SLE PheRS to identify established and undiagnosed SLE individuals. A SLE GRS using known risk SNPs did not add value beyond the PheRS and was of limited utility in Black individuals with SLE. More work is needed to understand the genetic risks of SLE in diverse populations.

Assessing the Accuracy and Reliability of AI-Generated Medical Responses: An Evaluation of the Chat-GPT Model.

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.

On the cusp: Considering the impact of artificial intelligence language models in healthcare.

Goodman et al. discuss how AI technologies like the natural language processing model Chat-GPT could potentially transform healthcare through knowledge dissemination and personalized patient education. Before these tools can be safely integrated into healthcare, research and development of robust oversight mechanisms are necessary to ensure their accuracy and reliability.

Recent Advances in Melanoma Diagnosis and Prognosis Using Machine Learning Methods.

PURPOSE OF REVIEW: The purpose was to summarize the current role and state of artificial intelligence and machine learning in the diagnosis and management of melanoma. RECENT FINDINGS: Deep learning algorithms can identify melanoma from clinical, dermoscopic, and whole slide pathology images with increasing accuracy. Efforts to provide more granular annotation to datasets and to identify new predictors are ongoing. There have been many incremental advances in both melanoma diagnostics and prognostic tools using artificial intelligence and machine learning. Higher quality input data will further improve these models' capabilities.

Rates of Pneumocystis jirovecii pneumonia and prophylaxis prescribing patterns in a large electronic health record cohort of patients with systemic lupus erythematosus.

Objective No guidelines exist for Pneumocystis jirovecii pneumonia (PJP) prophylaxis in patients with systemic lupus erythematosus (SLE). Limited data are available on incidence of PJP infection and use of PJP prophylaxis. Using a real-world, electronic health record (EHR) cohort, we investigated the frequency of PJP infections as well as patient and provider factors that impacted use and type of PJP prophylaxis. Methods  In a large, de-identified EHR, we identified possible SLE patients using a previously validated algorithm. PJP ICD-9 or ICD-10-CM billing codes and PJP keywords were used to identify possible PJP cases within this SLE cohort. We assessed for PJP prophylaxis prescribing in all SLE patients using keywords and reviewing medication lists for prophylactic agents. Chart review was used to confirm cases of SLE, PJP, and PJP prophylaxis and to obtain data on demographics, comorbidities, and immunosuppressants. Results Of 977 SLE patients, there were only four with confirmed PJP infection. Two of these patients had concurrent Acquired Immunodeficiency Syndrome, and none were on prophylaxis. Of 977 SLE patients, 132 (14%) were prescribed PJP prophylaxis. Of 617 SLE patients ever prescribed immunosuppressants, 128 (21%) were prescribed PJP prophylaxis. Sulfonamides were the most common prophylaxis prescribed (69%), and possible adverse events were documented in 22 out of 117 instances of being placed on a sulfonamide. Patients of younger age, Black race, nephritis, and renal transplant, and on chronic glucocorticoids were all more likely to have PJP prophylaxis prescribed. Patients who were on transplant induction medications, calcineurin/mTOR inhibitors, cyclophosphamide, and mycophenolate mofetil all were more likely to be prescribed PJP prophylaxis compared to other immunosuppressants. Conclusion PJP is a rare diagnosis among SLE patients, and prior studies may even overestimate its prevalence. PJP prophylaxis was less common in our cohort than previously described. Adverse events related to sulfonamides used for PJP prophylaxis were relatively rare with lower rates than previously reported. Our study demonstrates real-world PJP prophylaxis prescribing patterns in a large cohort of SLE patients.

Multi-modal Learning with Missing Data for Cancer Diagnosis Using Histopathological and Genomic Data.

Multi-modal learning (e.g., integrating pathological images with genomic features) tends to improve the accuracy of cancer diagnosis and prognosis as compared to learning with a single modality. However, missing data is a common problem in clinical practice, i.e., not every patient has all modalities available. Most of the previous works directly discarded samples with missing modalities, which might lose information in these data and increase the likelihood of overfitting. In this work, we generalize the multi-modal learning in cancer diagnosis with the capacity of dealing with missing data using histological images and genomic data. Our integrated model can utilize all available data from patients with both complete and partial modalities. The experiments on the public TCGA-GBM and TCGA-LGG datasets show that the data with missing modalities can contribute to multi-modal learning, which improves the model performance in grade classification of glioma cancer.