Understanding Breast Cancer Surgery Through Tiktok: an Analysis of Video Content and Viewer Engagement.

BACKGROUND: Breast cancer is the most common cancer in adolescents and young adults. Social media, particularly TikTok, has emerged as a crucial platform for sharing health information in this population. This study aims to characterize breast cancer surgery information on TikTok, focusing on content reliability, viewer reception, and areas for improvement. METHODS: We queried the search terms "breast cancer surgery," "mastectomy," and "lumpectomy" on TikTok, evaluating the top 50 videos for each. After watching each video, characteristics were recorded including: creator characteristics, video metrics, viewer reception, and video content. Statistical analysis was performed using Spearman's rank correlations and t-tests. RESULTS: A total of 138 videos were analyzed (excluding 12 duplicates from the initial 150). These videos received 4,895,373 likes and 109,705 comments. The most common content types were storytelling (57%) and education (20%), and the most common creator types were patients (77.3%) and physicians (10.3%). Videos with educational content by physicians were rare (6.5%). Engagement varied on the basis of video length, search terms, and creator characteristics. Overall, viewer comments predominantly expressed support and interest. CONCLUSIONS: Our study reveals that information on breast cancer surgery is widely shared on TikTok and has high viewer engagement. Factors influencing impact include video length, creator background, and search terms. While social media has democratized information sharing, there is a relative lack of physician creators providing objective and educational content. We highlight opportunities for health professionals to engage in social media as a tool for health education and ensure diverse and reliable healthcare content on these platforms.

An abdominal skin lesion: to lump or split? a case presentation.

Syphilis has many atypical morphologies which can present a diagnostic challenge, especially in patients with HIV/AIDS who may have multiple concurrent conditions. We describe a 41-year-old man with recently diagnosed HIV who was admitted for acute right vision loss and a diffuse rash with involvement of the palms and soles. He received diagnoses of secondary syphilis and Kaposi sarcoma in the setting of AIDS. Examination revealed an unusual dark brown-to-purple umbilicated papule with a necrotic center on the abdomen, raising a diagnostic dilemma. Skin biopsy showed secondary syphilis, despite the concurrent diagnosis of Kaposi sarcoma. The patient was treated with antibiotic and antiretroviral therapy and symptoms resolved. This case aims to share the clinical reasoning behind diagnosing a patient with HIV/AIDS with multiple concurrent conditions and to raise awareness of the many atypical cutaneous manifestations of secondary syphilis.

Patient and general public attitudes towards clinical artificial intelligence: a mixed methods systematic review.

Artificial intelligence (AI) promises to change health care, with some studies showing proof of concept of a provider-level performance in various medical specialties. However, there are many barriers to implementing AI, including patient acceptance and understanding of AI. Patients' attitudes toward AI are not well understood. We systematically reviewed the literature on patient and general public attitudes toward clinical AI (either hypothetical or realised), including quantitative, qualitative, and mixed methods original research articles. We searched biomedical and computational databases from Jan 1, 2000, to Sept 28, 2020, and screened 2590 articles, 23 of which met our inclusion criteria. Studies were heterogeneous regarding the study population, study design, and the field and type of AI under study. Six (26%) studies assessed currently available or soon-to-be available AI tools, whereas 17 (74%) assessed hypothetical or broadly defined AI. The quality of the methods of these studies was mixed, with a frequent issue of selection bias. Overall, patients and the general public conveyed positive attitudes toward AI but had many reservations and preferred human supervision. We summarise our findings in six themes: AI concept, AI acceptability, AI relationship with humans, AI development and implementation, AI strengths and benefits, and AI weaknesses and risks. We suggest guidance for future studies, with the goal of supporting the safe, equitable, and patient-centred implementation of clinical AI.

Idiopathic pure sudomotor failure: A review and two cases.

Idiopathic pure sudomotor failure (IPSF) is a rare disease characterized by acquired impairment in total body sweating despite exposure to heat or exercise. Its etiology is unknown but thought to involve defective cholinergic receptors on eccrine sweat glands. This article reviews the epidemiology, pathophysiology, presentation, and management of IPSF. Additionally, we report two cases of IPSF treated with multimodal therapy, including stacked antihistamine regimens and omalizumab, resulting in symptom improvement. This is the first report of treatment of IPSF with omalizumab, although its benefit is uncertain and requires further study.

Association of Wildfire Air Pollution and Health Care Use for Atopic Dermatitis and Itch.

IMPORTANCE: Air pollution is a worldwide public health issue that has been exacerbated by recent wildfires, but the relationship between wildfire-associated air pollution and inflammatory skin diseases is unknown. OBJECTIVE: To assess the associations between wildfire-associated air pollution and clinic visits for atopic dermatitis (AD) or itch and prescribed medications for AD management. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional time-series study assessed the associations of air pollution resulting from the California Camp Fire in November 2018 and 8049 dermatology clinic visits (4147 patients) at an academic tertiary care hospital system in San Francisco, 175 miles from the wildfire source. Participants included pediatric and adult patients with AD or itch from before, during, and after the time of the fire (October 2018 through February 2019), compared with those with visits in the same time frame of 2015 and 2016, when no large wildfires were near San Francisco. Data analysis was conducted from November 1, 2019, to May 30, 2020. EXPOSURES: Wildfire-associated air pollution was characterized using 3 metrics: fire status, concentration of particulate matter less than 2.5 µm in diameter (PM2.5), and satellite-based smoke plume density scores. MAIN OUTCOMES AND MEASURES: Weekly clinic visit counts for AD or itch were the primary outcomes. Secondary outcomes were weekly numbers of topical and systemic medications prescribed for AD in adults. RESULTS: Visits corresponding to a total of 4147 patients (mean [SD] age, 44.6 [21.1] years; 2322 [56%] female) were analyzed. The rates of visits for AD during the Camp Fire for pediatric patients were 1.49 (95% CI, 1.07-2.07) and for adult patients were 1.15 (95% CI, 1.02-1.30) times the rate for nonfire weeks at lag 0, adjusted for temperature, relative humidity, patient age, and total patient volume at the clinics for pediatric patients. The adjusted rate ratios for itch clinic visits during the wildfire weeks were 1.82 (95% CI, 1.20-2.78) for the pediatric patients and 1.29 (95% CI, 0.96-1.75) for adult patients. A 10-µg/m3 increase in weekly mean PM2.5 concentration was associated with a 7.7% (95% CI, 1.9%-13.7%) increase in weekly pediatric itch clinic visits. The adjusted rate ratio for prescribed systemic medications in adults during the Camp Fire at lag 0 was 1.45 (95% CI, 1.03-2.05). CONCLUSIONS AND RELEVANCE: This cross-sectional study found that short-term exposure to air pollution due to the wildfire was associated with increased health care use for patients with AD and itch. These results may provide a better understanding of the association between poor air quality and skin health and guide health care professionals' counseling of patients with skin disease and public health practice.

Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models.

Artificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational "stress tests". Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5-22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Multi-omic regulatory networks capture downstream effects of kinase inhibition in Mycobacterium tuberculosis.

The ability of Mycobacterium tuberculosis (Mtb) to adapt to diverse stresses in its host environment is crucial for pathogenesis. Two essential Mtb serine/threonine protein kinases, PknA and PknB, regulate cell growth in response to environmental stimuli, but little is known about their downstream effects. By combining RNA-Seq data, following treatment with either an inhibitor of both PknA and PknB or an inactive control, with publicly available ChIP-Seq and protein-protein interaction data for transcription factors, we show that the Mtb transcription factor (TF) regulatory network propagates the effects of kinase inhibition and leads to widespread changes in regulatory programs involved in cell wall integrity, stress response, and energy production, among others. We also observe that changes in TF regulatory activity correlate with kinase-specific phosphorylation of those TFs. In addition to characterizing the downstream regulatory effects of PknA/PknB inhibition, this demonstrates the need for regulatory network approaches that can incorporate signal-driven transcription factor modifications.

The role of technology in melanoma screening and diagnosis.

Melanoma presents challenges for timely and accurate diagnosis. Expert panels have issued risk-based screening guidelines, with recommended screening by visual inspection. To assess how recent technology can impact the risk/benefit considerations for melanoma screening, we comprehensively reviewed non-invasive visual-based technologies. Dermoscopy increases lesional diagnostic accuracy for both dermatologists and primary care providers; total body photography and sequential digital dermoscopic imaging also increase diagnostic accuracy, are supported by automated lesion detection and tracking, and may be best suited to use by dermatologists for longitudinal follow-up. Specialized imaging modalities using non-visible light technology have unproven benefit over dermoscopy and can be limited by cost, access, and training requirements. Mobile apps facilitate image capture and lesion tracking. Teledermatology has good concordance with face-to-face consultation and increases access, with increased accuracy using dermoscopy. Deep learning models can surpass dermatologist accuracy, but their clinical utility has yet to be demonstrated. Technology-aided diagnosis may change the calculus of screening; however, well-designed prospective trials are needed to assess the efficacy of these different technologies, alone and in combination to support refinement of guidelines for melanoma screening.

Machine learning for the prediction of antimicrobial stewardship intervention in hospitalized patients receiving broad-spectrum agents.

OBJECTIVE: A significant proportion of inpatient antimicrobial prescriptions are inappropriate. Post-prescription review with feedback has been shown to be an effective means of reducing inappropriate antimicrobial use. However, implementation is resource intensive. Our aim was to evaluate the performance of traditional statistical models and machine-learning models designed to predict which patients receiving broad-spectrum antibiotics require a stewardship intervention. METHODS: We performed a single-center retrospective cohort study of inpatients who received an antimicrobial tracked by the antimicrobial stewardship program. Data were extracted from the electronic medical record and were used to develop logistic regression and boosted-tree models to predict whether antibiotic therapy required stewardship intervention on any given day as compared to the criterion standard of note left by the antimicrobial stewardship team in the patient's chart. We measured the performance of these models using area under the receiver operating characteristic curves (AUROC), and we evaluated it using a hold-out validation cohort. RESULTS: Both the logistic regression and boosted-tree models demonstrated fair discriminatory power with AUROCs of 0.73 (95% confidence interval [CI], 0.69-0.77) and 0.75 (95% CI, 0.72-0.79), respectively (P = .07). Both models demonstrated good calibration. The number of patients that would need to be reviewed to identify 1 patient who required stewardship intervention was high for both models (41.7-45.5 for models tuned to a sensitivity of 85%). CONCLUSIONS: Complex models can be developed to predict which patients require a stewardship intervention. However, further work is required to develop models with adequate discriminatory power to be applicable to real-world antimicrobial stewardship practice.

Artificial Intelligence in Dermatology: A Primer.

Artificial intelligence is becoming increasingly important in dermatology, with studies reporting accuracy matching or exceeding dermatologists for the diagnosis of skin lesions from clinical and dermoscopic images. However, real-world clinical validation is currently lacking. We review dermatological applications of deep learning, the leading artificial intelligence technology for image analysis, and discuss its current capabilities, potential failure modes, and challenges surrounding performance assessment and interpretability. We address the following three primary applications: (i) teledermatology, including triage for referral to dermatologists; (ii) augmenting clinical assessment during face-to-face visits; and (iii) dermatopathology. We discuss equity and ethical issues related to future clinical adoption and recommend specific standardization of metrics for reporting model performance.

Multisystem Analysis of Mycobacterium tuberculosis Reveals Kinase-Dependent Remodeling of the Pathogen-Environment Interface.

Tuberculosis is the leading killer among infectious diseases worldwide. Increasing multidrug resistance has prompted new approaches for tuberculosis drug development, including targeted inhibition of virulence determinants and of signaling cascades that control many downstream pathways. We used a multisystem approach to determine the effects of a potent small-molecule inhibitor of the essential Mycobacterium tuberculosis Ser/Thr protein kinases PknA and PknB. We observed differential levels of phosphorylation of many proteins and extensive changes in levels of gene expression, protein abundance, cell wall lipids, and intracellular metabolites. The patterns of these changes indicate regulation by PknA and PknB of several pathways required for cell growth, including ATP synthesis, DNA synthesis, and translation. These data also highlight effects on pathways for remodeling of the mycobacterial cell envelope via control of peptidoglycan turnover, lipid content, a SigE-mediated envelope stress response, transmembrane transport systems, and protein secretion systems. Integrated analysis of phosphoproteins, transcripts, proteins, and lipids identified an unexpected pathway whereby threonine phosphorylation of the essential response regulator MtrA decreases its DNA binding activity. Inhibition of this phosphorylation is linked to decreased expression of genes for peptidoglycan turnover, and of genes for mycolyl transferases, with concomitant changes in mycolates and glycolipids in the cell envelope. These findings reveal novel roles for PknA and PknB in regulating multiple essential cell functions and confirm that these kinases are potentially valuable targets for new antituberculosis drugs. In addition, the data from these linked multisystems provide a valuable resource for future targeted investigations into the pathways regulated by these kinases in the M. tuberculosis cell.IMPORTANCE Tuberculosis is the leading killer among infectious diseases worldwide. Increasing drug resistance threatens efforts to control this epidemic; thus, new antitubercular drugs are urgently needed. We performed an integrated, multisystem analysis of Mycobacterium tuberculosis responses to inhibition of its two essential serine/threonine protein kinases. These kinases allow the bacterium to adapt to its environment by phosphorylating cellular proteins in response to extracellular signals. We identified differentially phosphorylated proteins, downstream changes in levels of specific mRNA and protein abundance, and alterations in the metabolite and lipid content of the cell. These results include changes previously linked to growth arrest and also reveal new roles for these kinases in regulating essential processes, including growth, stress responses, transport of proteins and other molecules, and the structure of the mycobacterial cell envelope. Our multisystem data identify PknA and PknB as promising targets for drug development and provide a valuable resource for future investigation of their functions.

Development and Validation of an Electronic Health Record-Based Machine Learning Model to Estimate Delirium Risk in Newly Hospitalized Patients Without Known Cognitive Impairment.

Importance: Current methods for identifying hospitalized patients at increased risk of delirium require nurse-administered questionnaires with moderate accuracy. Objective: To develop and validate a machine learning model that predicts incident delirium risk based on electronic health data available on admission. Design, Setting, and Participants: Retrospective cohort study evaluating 5 machine learning algorithms to predict delirium using 796 clinical variables identified by an expert panel as relevant to delirium prediction and consistently available in electronic health records within 24 hours of admission. The training set comprised 14 227 adult patients with non-intensive care unit hospital stays and no delirium on admission who were discharged between January 1, 2016, and August 31, 2017, from UCSF Health, a large academic health institution. The test set comprised 3996 patients with hospital stays who were discharged between August 1, 2017, and November 30, 2017. Exposures: Patient demographic characteristics, diagnoses, nursing records, laboratory results, and medications available in electronic health records during hospitalization. Main Outcomes and Measures: Delirium was defined as a positive Nursing Delirium Screening Scale or Confusion Assessment Method for the Intensive Care Unit score. Models were assessed using the area under the receiver operating characteristic curve (AUC) and compared against the 4-point scoring system AWOL (age >79 years, failure to spell world backward, disorientation to place, and higher nurse-rated illness severity), a validated delirium risk-assessment tool routinely administered in this cohort. Results: The training set included 14 227 patients (5113 [35.9%] aged >64 years; 7335 [51.6%] female; 687 [4.8%] with delirium), and the test set included 3996 patients (1491 [37.3%] aged >64 years; 1966 [49.2%] female; 191 [4.8%] with delirium). In total, the analysis included 18 223 hospital admissions (6604 [36.2%] aged >64 years; 9301 [51.0%] female; 878 [4.8%] with delirium). The AWOL system achieved a baseline AUC of 0.678. The gradient boosting machine model performed best, with an AUC of 0.855. Setting specificity at 90%, the model had a 59.7% (95% CI, 52.4%-66.7%) sensitivity, 23.1% (95% CI, 20.5%-25.9%) positive predictive value, 97.8% (95% CI, 97.4%-98.1%) negative predictive value, and a number needed to screen of 4.8. Penalized logistic regression and random forest models also performed well, with AUCs of 0.854 and 0.848, respectively. Conclusions and Relevance: Machine learning can be used to estimate hospital-acquired delirium risk using electronic health record data available within 24 hours of hospital admission. Such a model may allow more precise targeting of delirium prevention resources without increasing the burden on health care professionals.