ChatGPT Influence on Medical Decision-Making, Bias, and Equity: A Randomized Study of Clinicians Evaluating Clinical Vignettes.

In a randomized, pre-post intervention study, we evaluated the influence of a large language model (LLM) generative AI system on accuracy of physician decision-making and bias in healthcare. 50 US-licensed physicians reviewed a video clinical vignette, featuring actors representing different demographics (a White male or a Black female) with chest pain. Participants were asked to answer clinical questions around triage, risk, and treatment based on these vignettes, then asked to reconsider after receiving advice generated by ChatGPT+ (GPT4). The primary outcome was the accuracy of clinical decisions based on pre-established evidence-based guidelines. Results showed that physicians are willing to change their initial clinical impressions given AI assistance, and that this led to a significant improvement in clinical decision-making accuracy in a chest pain evaluation scenario without introducing or exacerbating existing race or gender biases. A survey of physician participants indicates that the majority expect LLM tools to play a significant role in clinical decision making.

Improved lateral penumbra for proton ocular treatments on a general-purpose spot scanning beamline.

PURPOSE: An ocular applicator that fits a commercial proton snout with an upstream range shifter to allow for treatments with sharp lateral penumbra is described. MATERIALS AND METHODS: The validation of the ocular applicator consisted of a comparison of range, depth doses (Bragg peaks and spread out Bragg peaks), point doses, and 2-D lateral profiles. Measurements were made for three field sizes, 1.5, 2, and 3 cm, resulting in 15 beams. Distal and lateral penumbras were simulated in the treatment planning system for seven range-modulation combinations for beams typical of ocular treatments and a field size of 1.5 cm, and penumbra values were compared to published literature. RESULTS: All the range errors were within 0.5 mm. The maximum averaged local dose differences for Bragg peaks and SOBPs were 2.6% and 1.1%, respectively. All the 30 measured point doses were within +/-3% of the calculated. The measured lateral profiles, analyzed through gamma index analysis and compared to the simulated, had pass rates greater than 96% for all the planes. The lateral penumbra increased linearly with depth, from 1.4 mm at 1 cm depth to 2.5 mm at 4 cm depth. The distal penumbra ranged from 3.6 to 4.4 mm and increased linearly with the range. The treatment time for a single 10 Gy (RBE) fractional dose ranged from 30 to 120 s, depending on the shape and size of the target. CONCLUSIONS: The ocular applicator's modified design allows lateral penumbra similar to dedicated ocular beamlines while enabling planners to use modern treatment tools such as Monte Carlo and full CT-based planning with increased flexibility in beam placement.

Most privately insured patients do not receive federally recommended abdominal aortic aneurysm screening.

OBJECTIVE: Since 2005, the United States Preventative Services Task Force has recommended abdominal aortic aneurysm (AAA) ultrasound screening for 65- to 75-year-old male ever-smokers. Integrated health systems such as Kaiser Permanente and the Veterans Affairs (VA) health care system report 74% to 79% adherence, but compliance rates in the private sector are unknown. METHODS: The IBM Marketscan Commercial and Medicare Supplemental databases (2006-2017) were queried for male ever-smokers continuously enrolled from age 65 to 75 years. Exclusion criteria were previous history of AAA, connective tissue disorder, and aortic surgery. Patients with abdominal computed tomographic or magnetic resonance imaging from ages 65 to 75 years were also excluded. Screening was defined as a complete abdominal, retroperitoneal, or aortic ultrasound. A logistic mixed-effects model utilizing state as a random intercept was used to identify patient characteristics associated with screening. RESULTS: Of 35,154 eligible patients, 13,612 (38.7%) underwent screening. Compliance varied by state, ranging from 24.4% in Minnesota to 51.6% in Montana (P < .05). Screening activity increased yearly, with 0.7% of screening activity occurring in 2008 vs 22.2% in 2016 (P <.05). In a logistic mixed-effects model adjusting for state as a random intercept, history of hypertension (odds ratio [OR], 1.07; 95% confidence interval [CI], 1.03-1.13), coronary artery disease (OR, 1.17; 95% CI, 1.10-1.22), congestive heart failure (OR, 1.14; 95% CI, 1.01-1.22), diabetes (OR, 1.1; 95% CI, 1.06-1.16), and chronic kidney disease (OR, 1.4; 95% CI, 1.24-1.53) were associated with screening. Living outside of a census-designated metropolitan area was negatively associated with screening (OR, 0.92; 95% CI, 0.87-0.97). CONCLUSIONS: In a private claims database representing 250 million claimants, 38.7% of eligible patients received United States Preventative Services Task Force-recommended AAA screening. Compliance was nearly one-half that of integrated health systems and was significantly lower for patients living outside of metropolitan areas. Efforts to improve early detection of AAA should include targeting non-metropolitan areas and modifying Medicare reimbursement and incentivization strategies to improve guideline adherence.

Using Case Mix Index within Diagnosis-Related Groups to Evaluate Variation in Hospitalization Costs at a Large Academic Medical Center.

In analyzing direct hospitalization cost and clinical data from an academic medical center, commonly used metrics such as diagnosis-related group (DRG) weight explain approximately 37% of cost variability, but a substantial amount of variation remains unaccounted for by case mix index (CMI) alone. Using CMI as a benchmark, we isolate and target individual DRGs with higher than expected average costs for specific quality improvement efforts. While DRGs summarize hospitalization care after discharge, a predictive model using only information known before admission explained up to 60% of cost variability for two DRGs with a high excess cost burden. This level of variability likely reflects underlying patient factors that are not modifiable (e.g., age and prior comorbidities) and therefore less useful for health systems to target for intervention. However, the remaining unexplained variation can be inspected in further studies to discover operational factors that health systems can target to improve quality and value for their patients. Since DRG weights represent the expected resource consumption for a specific hospitalization type relative to the average hospitalization, the data-driven approach we demonstrate can be utilized by any health institution to quantify excess costs and potential savings among DRGs.

User-centred design for machine learning in health care: a case study from care management.

OBJECTIVES: Few machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the data rather than to address a real-world clinical pain point. METHODS: We introduce a practical toolkit for user-centred design consisting of four questions covering: (1) solvable pain points, (2) the unique value of ML (eg, automation and augmentation), (3) the actionability pathway and (4) the model's reward function. This toolkit was implemented in a series of six participatory design workshops with care managers in an academic medical centre. RESULTS: Pain points amenable to ML solutions included outpatient risk stratification and risk factor identification. The endpoint definitions, triggering frequency and evaluation metrics of the proposed risk scoring model were directly influenced by care manager workflows and real-world constraints. CONCLUSIONS: Integrating user-centred design early in the ML life cycle is key for configuring models in a clinically actionable way. This toolkit can guide problem selection and influence choices about the technical setup of the ML problem.

Predicting Unplanned 7-day Intensive Care Unit Readmissions with Machine Learning Models for Improved Discharge Risk Assessment.

Unplanned readmission to the intensive care unit (ICU) confers excess morbidity and mortality. We explore whether machine learning models can outperform the current standard, the Stability and Workload Index for Transfer (SWIFT) score, in assessing 7-day ICU readmission risk at discharge. Logistic regression, random forest, support vector machine, and gradient boosting models were trained and validated on Stanford Hospital data (2009-2019), externally validated on Beth Israel Deaconess Medical Center (BIDMC) data (2008-2019) and benchmarked against SWIFT. The best performing model was gradient boosting, with AUROC of 0.85 and 0.60 and F1-score of 0.43 and 0.14 on internal and external validation, respectively. SWIFT had an AUROC of 0.67 and 0.51 and F1-score of 0.33 and 0.10 on Stanford and BIDMC data, respectively. Machine learning models predicting 7-day ICU readmission risk can improve current ICU discharge risk assessment standards, but performance may be limited without local training.

Treatment of ocular tumors through a novel applicator on a conventional proton pencil beam scanning beamline.

Treatment of ocular tumors on dedicated scattering-based proton therapy systems is standard afforded due to sharp lateral and distal penumbras. However, most newer proton therapy centers provide pencil beam scanning treatments. In this paper, we present a pencil beam scanning (PBS)-based ocular treatment solution. The design, commissioning, and validation of an applicator mount for a conventional PBS snout to allow for ocular treatments are given. In contrast to scattering techniques, PBS-based ocular therapy allows for inverse planning, providing planners with additional flexibility to shape the radiation field, potentially sparing healthy tissues. PBS enables the use of commercial Monte Carlo algorithms resulting in accurate dose calculations in the presence of heterogeneities and fiducials. The validation consisted of small field dosimetry measurements of point doses, depth doses, and lateral profiles relevant to ocular therapy. A comparison of beam properties achieved through the applicator against published literature is presented. We successfully showed the feasibility of PBS-based ocular treatments.

Childhood maltreatment, subjective social status, and health disparities in bereavement.

BACKGROUND: Spousal bereavement can lead to adverse health outcomes; however, not all widow(er)s experience the same degree of health problems. Thus, it is important to understand the contribution of disparities (e.g., childhood maltreatment and subjective social status) that may underlie adverse health outcomes that arise following bereavement. METHODS: We collected data from 130 spousally bereaved individuals at 3-time points (3 months post-loss, 4 months post-loss, and 6 months post-loss). Using mixed models, we assessed the interaction of childhood maltreatment, subjective social status, and time to predict changes in proinflammatory cytokine production, depressive symptoms, grief symptoms. RESULTS: We found a significant interaction between childhood maltreatment, subjective social status, and time predicting proinflammatory cytokine production (beta > -0.01, p = 0.048), depressive symptoms (beta = 0.008, p = .010), and grief symptoms (beta = 0.001 p = .001). CONCLUSION: This study highlights the role of disparities related to childhood maltreatment and subjective social status on adverse health outcomes following spousal bereavement.

Assessment of Prevalence of Adolescent Patient Portal Account Access by Guardians.

Importance: Patient portals can be configured to allow confidential communication for adolescents' sensitive health care information. Guardian access of adolescent patient portal accounts could compromise adolescents' confidentiality. Objective: To estimate the prevalence of guardian access to adolescent patient portals at 3 academic children's hospitals. Design, Setting, and Participants: A cross-sectional study to estimate the prevalence of guardian access to adolescent patient portal accounts was conducted at 3 academic children's hospitals. Adolescent patients (aged 13-18 years) with access to their patient portal account with at least 1 outbound message from their portal during the study period were included. A rule-based natural language processing algorithm was used to analyze all portal messages from June 1, 2014, to February 28, 2020, and identify any message sent by guardians. The sensitivity and specificity of the algorithm at each institution was estimated through manual review of a stratified subsample of patient accounts. The overall proportion of accounts with guardian access was estimated after correcting for the sensitivity and specificity of the natural language processing algorithm. Exposures: Use of patient portal. Main Outcome and Measures: Percentage of adolescent portal accounts indicating guardian access. Results: A total of 3429 eligible adolescent accounts containing 25 642 messages across 3 institutions were analyzed. A total of 1797 adolescents (52%) were female and mean (SD) age was 15.6 (1.6) years. The percentage of adolescent portal accounts with apparent guardian access ranged from 52% to 57% across the 3 institutions. After correcting for the sensitivity and specificity of the algorithm based on manual review of 200 accounts per institution, an estimated 64% (95% CI, 59%-69%) to 76% (95% CI, 73%-88%) of accounts with outbound messages were accessed by guardians across the 3 institutions. Conclusions and Relevance: In this study, more than half of adolescent accounts with outbound messages were estimated to have been accessed by guardians at least once. These findings have implications for health systems intending to rely on separate adolescent accounts to protect adolescent confidentiality.

Health Equity in Artificial Intelligence and Primary Care Research: Protocol for a Scoping Review.

BACKGROUND: Though artificial intelligence (AI) has the potential to augment the patient-physician relationship in primary care, bias in intelligent health care systems has the potential to differentially impact vulnerable patient populations. OBJECTIVE: The purpose of this scoping review is to summarize the extent to which AI systems in primary care examine the inherent bias toward or against vulnerable populations and appraise how these systems have mitigated the impact of such biases during their development. METHODS: We will conduct a search update from an existing scoping review to identify studies on AI and primary care in the following databases: Medline-OVID, Embase, CINAHL, Cochrane Library, Web of Science, Scopus, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI, and arXiv. Two screeners will independently review all abstracts, titles, and full-text articles. The team will extract data using a structured data extraction form and synthesize the results in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. RESULTS: This review will provide an assessment of the current state of health care equity within AI for primary care. Specifically, we will identify the degree to which vulnerable patients have been included, assess how bias is interpreted and documented, and understand the extent to which harmful biases are addressed. As of October 2020, the scoping review is in the title- and abstract-screening stage. The results are expected to be submitted for publication in fall 2021. CONCLUSIONS: AI applications in primary care are becoming an increasingly common tool in health care delivery and in preventative care efforts for underserved populations. This scoping review would potentially show the extent to which studies on AI in primary care employ a health equity lens and take steps to mitigate bias. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/27799.

The use of multi-pronged screening strategy to understand the epidemiology of carbapenemase-producing Enterobacteriaceae in Hong Kong: transition from epidemic to endemic setting.

A multi-pronged carbapenemase-producing Enterobacteriaceae (CPE) screening strategy was implemented in Hong Kong West healthcare network. Of 199,192 fecal specimens from 77,194 patients screening from 1 July 2011 to 30 June 2019, the incidence of CPE per 1000 patient admission significantly increased from 0.01 (2012) to 1.9 (2018) (p<0.01). With appropriate infection control measures, the incidence of nosocomial CPE per 1000 CPE colonization day decreased from 22.34 (2014) to 10.65 (2018) (p=0.0094). Exposure to wet market for purchasing raw pork (p=0.007), beef (p=0.017), chicken (p=0.026), and vegetable (p=0.034) for >3 times per week significantly associated with community acquisition of CPE. Strategic CPE control measures should be implemented in both the hospital and the community.

Pharmaceutical Machine Learning: Virtual High-Throughput Screens Identifying Promising and Economical Small Molecule Inhibitors of Complement Factor C1s.

When excessively activated, C1 is insufficiently regulated, which results in tissue damage. Such tissue damage causes the complement system to become further activated to remove the resulting tissue damage, and a vicious cycle of activation/tissue damage occurs. Current Food and Drug Administration approved treatments include supplemental recombinant C1 inhibitor, but these are extremely costly and a more economical solution is desired. In our work, we have utilized an existing data set of 136 compounds that have been previously tested for activity against C1. Using these compounds and the activity data, we have created models using principal component analysis, genetic algorithm, and support vector machine approaches to characterize activity. The models were then utilized to virtually screen the 72 million compound PubChem repository. This first round of virtual high-throughput screening identified many economical and promising inhibitor candidates, a subset of which was tested to validate their biological activity. These results were used to retrain the models and rescreen PubChem in a second round vHTS. Hit rates for the first round vHTS were 57%, while hit rates for the second round vHTS were 50%. Additional structure⁻property analysis was performed on the active and inactive compounds to identify interesting scaffolds for further investigation.

Application of a dual target PCR-high resolution melting (HRM) method for rapid nontuberculous mycobacteria identification.

Species differentiation of nontuberculous mycobacteria (NTM) has long been a difficult task in clinical laboratories. This study demonstrated and evaluated a simple and cost-effective method using the real-time PCR with high-resolution melting (PCR-HRM) analysis technique, which could differentiate at least 14 different medically related NTM.

THE TRAINING OF NEXT GENERATION DATA SCIENTISTS IN BIOMEDICINE.

With the booming of new technologies, biomedical science has transformed into digitalized, data intensive science. Massive amount of data need to be analyzed and interpreted, demand a complete pipeline to train next generation data scientists. To meet this need, the transinstitutional Big Data to Knowledge (BD2K) Initiative has been implemented since 2014, complementing other NIH institutional efforts. In this report, we give an overview the BD2K K01 mentored scientist career awards, which have demonstrated early success. We address the specific trainings needed in representative data science areas, in order to make the next generation of data scientists in biomedicine.

Effect of opioid prescribing guidelines in primary care.

Long-term opioid use for noncancer pain is increasingly prevalent yet controversial given the risks of addiction, diversion, and overdose. Prior literature has identified the problem and proposed management guidelines, but limited evidence exists on the actual effectiveness of implementing such guidelines in a primary care setting.A multidisciplinary working group of institutional experts assembled comprehensive guidelines for chronic opioid prescribing, including monitoring and referral recommendations. The guidelines were disseminated in September 2013 to our medical center's primary care clinics via in person and electronic education.We extracted electronic medical records for patients with noncancer pain receiving opioid prescriptions (Rxs) in seasonally matched preintervention (11/1/2012-6/1/2013) and postintervention (11/1/2013-6/1/2014) periods. For patients receiving chronic (3 or more) opioid Rxs, we assessed the rates of drug screening, specialty referrals, clinic visits, emergency room visits, and quantity of opioids prescribed.After disseminating guidelines, the percentage of noncancer clinic patients receiving any opioid Rxs dropped from 3.9% to 3.4% (P = 0.02). The percentage of noncancer patients receiving chronic opioid Rxs decreased from 2.0% to 1.6% (P = 0.03). The rate of urine drug screening increased from 9.2% to 17.3% (P = 0.005) amongst noncancer chronic opioid patients. No significant differences were detected for other metrics or demographics assessed.An educational intervention for primary care opioid prescribing is feasible and was temporally associated with a modest reduction in overall opioid Rx rates. Provider use of routine drug screening increased, but overall rates of screening and specialty referral remained low despite the intervention. Despite national pressures to introduce opioid prescribing guidelines for chronic pain, doing so alone does not necessarily yield substantial changes in clinical practice.

Patient Outcomes when Housestaff Exceed 80 Hours per Week.

BACKGROUND: It has been posited that high workload and long work hours for trainees could affect the quality and efficiency of patient care. Duty hour restrictions seek to balance patient care and resident education by limiting resident work hours. Through a retrospective cohort study, we investigated whether patient care on an inpatient general medicine service at a large academic medical center is impacted when housestaff work more than 80 hours per week. METHODS: We identified all admissions to a housestaff-run general medicine service between June 25, 2013 and June 29, 2014. Each hospitalization was classified by whether the patient was admitted by housestaff who have worked more than 80 hours per week during their hospitalization. Housestaff computer activity and duty hours were calculated by institutional electronic heath record audit, as well as length of stay and a composite of in-hospital mortality, intensive care unit (ICU) transfer rate, and 30-day readmission rate. RESULTS: We identified 4767 hospitalizations by 3450 unique patients; of which 40.9% of hospitalizations were managed by housestaff who worked more than 80 hours that week during their hospitalization. There was a significantly higher rate of the composite outcome (19.2% vs 16.7%, P = .031) for patients admitted by housestaff working more than 80 hours per week during their hospitalization. We found a statistically significant higher length of stay (5.12 vs 4.66 days, P = .048) and rate of ICU transfer (3.53% vs 2.38%, P = .029). There was no statistically significant difference in 30-day readmission rate (13.7% vs 12.8%, P = .395) or in-hospital mortality rate (3.18% vs 2.42%, P = .115). There was no correlation with team census on admission and patient outcomes. CONCLUSIONS: Patients taken care of by housestaff working more than 80 hours per week had increased length of stay and number of ICU transfers. There was no association between resident work-hours and patient in-hospital mortality or 30-day readmission rate.