Faculty Bibliography

BACKGROUND: Clinical reasoning (CR) is a core component of medical training, yet residents often receive little feedback on their CR documentation. Here we describe the process of developing a machine learning (ML) algorithm for feedback on CR documentation to increase the frequency and quality of feedback in this domain.
METHOD(S): To create this algorithm, note quality first had to be rated by gold standard human rating. We selected the IDEA Assessment Tool-a note rating instrument across four domains (I=Interpretive summary, D=Differential diagnosis, E=Explanation of reasoning, A=Alternative diagnoses explained) that uses a 3-point Likert scale without descriptive anchors. To develop descriptive anchors we conducted an iterative process reviewing notes from the EHR written by medicine residents and validated the Revised-IDEA Assessment Tool using Messick's framework- content validity, response process, relation to other variables, internal structure, and consequences. Using the Hofstee standard setting method, cutoffs for high quality clinical reasoning for the IDEA and DEA scores were set. We then created a dataset of expertrated notes to create the ML algorithm. First, a natural language processing software was applied to the set of notes that enabled recognition and automatic encoding of clinical information as a diagnosis or disease (D's), a sign or symptom (E or A), or semantic qualifier (e.g. most likely). Input variables to the ML algorithm included counts of D's, E/A's, semantic qualifiers, and proximity of semantic qualifiers to disease/ diagnosis. ML output focused on DEA quality and was binarized to low or high quality CR. Finally, 200 notes were randomly selected for human validation review comparing ML output to human rated DEA score.
RESULT(S): The IDEA and DEA scores ranged from 0-10 and 0-6, respectively. IDEA score of >= 6.5 and a DEA score of >= 3 was deemed high quality. 252 notes were rated to create the dataset and 20% were rated by 3 raters with high intraclass correlation 0.84 (95% CI 0.74-0.90). 120 of these notes comprised the testing set for ML model development. The logistic regression model was the best performing model with an AUC 0.87 and a positive predictive value (PPV) of 0.65. 48 (40%) of the notes were high quality. There was substantial interrater reliability between ML output and human rating on the 200 note validation set with a Cohen's Kappa 0.64.
CONCLUSION(S): We have developed a ML algorithm for feedback on CR documentation that we hypothesize will increase the frequency and quality of feedback in this domain. We have subsequently developed a dashboard that will display the output of the ML model. Next steps will be to provide internal medicine residents' feedback on their CR documentation using this dashboard and assess the impact this has on their documentation quality. LEARNING OBJECTIVE #1: Describe the importance of high quality documentation of clinical reasoning. LEARNING OBJECTIVE #2: Identify machine learning as a novel assessment tool for feedback on clinical reasoning documentation

Psychosocial stressors are prevalent and linked to worse health outcomes, but are less frequently addressed than physically apparent medical conditions at primary care visits. Through a community-academic partnership between an art museum and a federally qualified health center, we developed an innovative museum-based intervention and evaluated its feasibility and acceptability among diverse, underserved patients and its perceived effects on psychosocial stressors. Guided by experiential learning and constructivist approaches, the intervention consisted of a single, three-hour session that incorporated group discussions and interactive components, including art-viewing, sketching, and object-handling. We used post-intervention focus groups to elicit feedback qualitatively. From July 2017 to January 2018, 25 patients participated. Focus groups revealed that the intervention exhibited therapeutic qualities, fostered self-reflection, catalyzed social connectivity, and functioned as a gateway to community resources. These findings can guide future research and development of community-based interventions to target the growing burden of psychosocial stressors among the underserved.

Background While there is overwhelming evidence for the beneficial role of hydroxychloroquine (HCQ) in SLE, little is known about its economic impact. We estimated annual direct, indirect, and total costs (DC, IC, TC) associated with HCQ use. Methods A subset of patients from the Systemic Lupus Erythematosus International Collaborating Clinics (SLICC) inception cohort were assessed annually between 2014 and 2019 for health resource use, lost work-force/non-work-force productivity and concurrent HCQ use. Resource use was costed using 2021 Canadian prices and lost productivity using Statistics Canada age-and-sex specific wages. At each assessment, HCQ dose over the past year and weight were documented and patients were stratified into 1 of 3 HCQ dosage groups: nonusers (0 mg/kg/day), low-intensity users (<= 5 mg/kg/day), or high-intensity users (>5 mg/kg/day). Costs associated with HCQ dose were calculated by averaging all observations within each dosage group. Multiple random effects linear regressions adjusted for the possible confounding of age at diagnosis, sex, race/ethnicity, disease duration, geographic region, education, alcohol use, and smoking on the association between annual DC and IC and HCQ dose. A possible mediating effect of disease damage (SLICC/ACR DI) on these associations was also investigated. Results 661 patients (89.4% female, 59.3% non-Caucasian race/ethnicity, mean age and mean disease duration at the start of economic assessments was 42.1 years and 9.5 years, respectively) were followed over a mean of 2.8 years. Across 1536 annual assessments, 36.1% of observations were provided by HCQ non-users, 43.1% by low-intensity users (mean dosage 3.4 mg/kg/day), and 20.8% by high-intensity users (mean dosage 5.9 mg/kg/day). Annual adjusted DC were higher in nonusers ($9599) versus low-intensity users ($6344) and highintensity users ($6333) (table 1). When disease damage was included in the regression, there were no significant differences in DC between dosage groups. While unadjusted IC were higher in non-users ($37,610) versus low-intensity users ($32,480) and high-intensity users ($31,418), adjusted IC did not differ. Adjusted TC were higher in non-users ($46,157) versus low-intensity users ($39,257) and high-intensity users ($37,634). Conclusion SLE patients reported higher adjusted annual DC and TC during periods of HCQ non-use versus periods of use, regardless of the intensity of use. There was no additional cost savings in those using high intensity dosages. The cost-savings effect of HCQ could potentially be partially mediated through reduced damage. In addition to its well-established therapeutic potential, there may be an economic imperative for HCQ use in SLE patients

Bacterial infections represent a major cause of mortality and morbidity in patients with cirrhosis that can alter the clinical course of compensated cirrhosis. The most common infections are spontaneous bacterial peritonitis by gram-negative organisms, urinary-tract infection, and pneumonia. In this case report, we raise the question of considering infections in the prognosis scoring in this patient group.

Background/UNASSIGNED:Cardiovascular disease (CVD) is a growing burden in low- and middle-income countries. Ghana seeks to address this problem by task-shifting CVD diagnosis and management to nurses. The Community-Based Health Planning and Services (CHPS) initiative offers maternal and pediatric health care throughout Ghana but faces barriers to providing CVD care. We employed in-depth interviews to identify solutions to constraints in CVD care to develop a nurse-led CVD intervention in two districts of Ghana's Upper East Region. Objective/UNASSIGNED:This study sought to identify non-physician-led interventions for the screening and treatment of cardiovascular disease to incorporate into Ghana's current primary health care structure. Methods/UNASSIGNED:Using a qualitative descriptive design, we conducted 31 semistructured interviews of community health officers (CHOs) and supervising subdistrict officers (SDOs) at CHPS community facilities. Summative content analysis revealed the most common intervention ideas and endorsements by the participants. Findings/UNASSIGNED:Providers endorsed three interventions: increasing community CVD knowledge and engagement, increasing nonphysician prescribing abilities, and ensuring provider access to medical and transportation equipment. Providers suggested community leaders and volunteers should convey CVD knowledge, marshaling established gathering practices to educate communities and formulate action plans. Providers requested lectures paired with experiential learning to improve their prescribing confidence. Providers recommended revising reimbursement and equipment procurement processes for expediting access to necessary supplies. Conclusions/UNASSIGNED:Frontline CHPS primary care providers believe CVD care is feasible. They recommended a three-pronged intervention that combines community outreach, provider training, and logistical support, thereby expanding task-shifting beyond hypertension to include other CVD risk factors. This model could be replicable elsewhere.

LEARNING OBJECTIVES 1: Describe a longitudinal curriculum to train internal medicine (IM) residents in point-of-care ultrasound (POCUS). LEARNING OBJECTIVES 2: Recognize the impact of decreased patient contact on residents' retention of POCUS skills. SETTINGAND PARTICIPANTS:Despite thewell-documented benefits of POCUS, internal medicine residents receive little formal training. We implemented a curriculumin the 2019 academic year to train 55 PGY-2 IMresidents in POCUS across four urban teaching hospitals and a method to evaluate its efficacy. As the COVID pandemic hit, we additionally sought to understand the impact of COVID on the efficacy of our curriculum and to ascertain from IM residents their barriers to using POCUS during the COVID pandemic. DESCRIPTION: The curriculum was composed of three workshops, consisting of lectures and hands-on practice covering lung, cardiac, abdominal, and lower extremity vascular views. Following the workshops, we sought to consolidate learners' knowledge with a subsequent year-long skill building phase. The skill-building phase was truncated due to the pandemic.A hands-on assessment was performed prior to the course and not repeated at course conclusion due to social distancing concerns. An online knowledge test was administered before the course, immediately following the course, and at one year. A survey assessing attitudes and barriers to POCUS was administered before the course and at one year. EVALUATION: No resident passed the pre-course hands-on assessment. Prior to the course, the average resident score was 54% on the online knowledge quiz; directly after the workshop series, the average rose to 78%. At one year, the average score on the online knowledge quiz was 74%, a statistically significant decrease (p=0.04). Ninety-one percent of residents reported performing POCUS at least once/month prior to the pandemic. During the pandemic, scanning activity decreased; 67% residents reported they scanned rarely or never. DISCUSSION/ REFLECTION / LESSONS LEARNED: Our course led to significant improvement of knowledge regarding ultrasound technology and image interpretation, however this decayed at one year, likely due to lack of skill reinforcement. Though POCUS was widely used prior to the pandemic, usage dropped at the pandemic's peak, despite its utility as both a diagnostic and therapeutic tool. The most commonly cited reason for lack of use was concern regarding contamination and infectious exposure. While the COVID pandemic disrupted our curriculum, it also highlighted opportunities to incorporate POCUS into clinical practice and reinforced the importance of continued longitudinal practice to retain learned skills