BACKGROUND: Accessing professional medical interpreters for brief, low risk exchanges can be challenging. Machine translation (MT) for verbal communication has the potential to be a useful clinical tool, but few evaluations exist. OBJECTIVE: We evaluated the quality of three MT applications for English-Spanish and English-Mandarin two-way interpretation of low complexity brief clinical communication compared with human interpretation. DESIGN: Audio-taped phrases were interpreted via human and 3 MT applications. Bilingual assessors evaluated the quality of MT interpretation on four assessment categories (accuracy, fluency, meaning, and clinical risk) using 5-point Likert scales. We used a non-inferiority design with 15% inferiority margin to evaluate the quality of three MT applications with professional medical interpreters serving as gold standards. MAIN MEASURES: Proportion of interpretation exchanges deemed acceptable, defined as a composite score of 16 or greater out of 20 based on the four assessment categories. KEY RESULTS: For English to Spanish, the proportion of MT-interpreted phrases scored as acceptable ranged from 0.68 to 0.84, while for English to Mandarin, the range was from 0.62 to 0.76. Both Spanish/Mandarin to English MT interpretation had low acceptable scores (range 0.36 to 0.41). No MT interpretation met the non-inferiority threshold. CONCLUSION: While MT interpretation was better for English to Spanish or Mandarin than the reverse, the overall quality of MT interpretation was poor for two-way clinical communication. Clinicians should advocate for easier access to professional interpretation in all clinical spaces and defer use of MT until these applications improve.

Background

The COVID-19 pandemic triggered unprecedented expansion of outpatient telemedicine in the United States in all types of health systems, including safety-net health systems. These systems generally serve low-income, racially/ethnically/linguistically diverse patients, many of whom face barriers to digital health access. These patients' perspectives are vital to inform ongoing, equitable implementation efforts.

Methods

Twenty-five semi-structured interviews exploring a theoretical framework of technology acceptability were conducted from March through July 2020. Participants had preferred languages of English, Spanish, or Cantonese and were recruited from three clinics (general medicine, obstetrics, and pulmonary) within the San Francisco Health Network. Both deductive and inductive coding were performed. In a secondary analysis, qualitative data were merged with survey data to relate perspectives to demographic factors and technology access/use.

Results

Participants were diverse with respect to language (52% non-English-speaking), age (range 23-71), race/ethnicity (24% Asian, 20% Black, 44% Hispanic/Latinx, 12% White), & smartphone use (80% daily, 20% weekly or less). All but 2 had a recent telemedicine visit (83% telephone). Qualitative results revealed that most participants felt telemedicine visits fulfilled their medical needs, were convenient, and were satisfied with their telemedicine care. However, most still preferred in-person visits, expressing concern that tele-visits relied on patients' abilities to access telemedicine, as well as monitor and manage their own health without in-person physical evaluation.

Conclusions

High satisfaction with telemedicine can co-exist with patient-expressed hesitations surrounding the perceived effectiveness, self-efficacy, and digital access barriers associated with a new model of care. More research is needed to guide how healthcare systems and clinicians make decisions and communicate about visit modalities to support high-quality care that responds to patients' needs and circumstances.

Alzheimer's Disease (AD) is a neurodegenerative disorder that is still not fully understood. Sex modifies AD vulnerability, but the reasons for this are largely unknown. We utilize two independent electronic medical record (EMR) systems across 44,288 patients to perform deep clinical phenotyping and network analysis to gain insight into clinical characteristics and sex-specific clinical associations in AD. Embeddings and network representation of patient diagnoses demonstrate greater comorbidity interactions in AD in comparison to matched controls. Enrichment analysis identifies multiple known and new diagnostic, medication, and lab result associations across the whole cohort and in a sex-stratified analysis. With this data-driven method of phenotyping, we can represent AD complexity and generate hypotheses of clinical factors that can be followed-up for further diagnostic and predictive analyses, mechanistic understanding, or drug repurposing and therapeutic approaches.

Identification of Alzheimer's disease (AD) onset risk can facilitate interventions before irreversible disease progression. We demonstrate that electronic health records from the University of California, San Francisco, followed by knowledge networks (for example, SPOKE) allow for (1) prediction of AD onset and (2) prioritization of biological hypotheses, and (3) contextualization of sex dimorphism. We trained random forest models and predicted AD onset on a cohort of 749 individuals with AD and 250,545 controls with a mean area under the receiver operating characteristic of 0.72 (7 years prior) to 0.81 (1 day prior). We further harnessed matched cohort models to identify conditions with predictive power before AD onset. Knowledge networks highlight shared genes between multiple top predictors and AD (for example, APOE, ACTB, IL6 and INS). Genetic colocalization analysis supports AD association with hyperlipidemia at the APOE locus, as well as a stronger female AD association with osteoporosis at a locus near MS4A6A. We therefore show how clinical data can be utilized for early AD prediction and identification of personalized biological hypotheses.