Telehealth drastically reduces the time burden of appointments and increases access to care for homebound patients. During the COVID-19 pandemic, many outpatient practices closed, requiring an expansion of telemedicine capabilities. However, a significant number of patients remain unconnected to telehealth-capable patient portals. Currently, no literature exists on the success of and barriers to remote enrollment in telehealth patient portals. From March 26 to May 8, 2020, a total of 324 patients were discharged from Mount Sinai Beth Israel (MSBI), a teaching hospital in New York City. Study volunteers attempted to contact and enroll patients in the MyChart patient portal to allow the completion of a post-discharge video visit. If patients were unable to enroll, barriers were documented and coded for themes. Of the 324 patients discharged from MSBI during the study period, 277 (85%) were not yet enrolled in MyChart. Volunteers successfully contacted 136 patients (49% of those eligible), and 39 (14%) were successfully enrolled. Inability to contact patients was the most significant barrier. For those successfully contacted but not enrolled, the most frequent barrier was becoming lost to follow-up (29% of those contacted), followed by lack of interest in remote appointments (21%) and patient technological limitations (9%). Male patients, and those aged 40–59, were significantly less likely to successfully enroll compared to other patients. Telehealth is critical for healthcare delivery. Remote enrollment in a telemedicine-capable patient portal is feasible, yet underperforms compared to reported in-person enrollment rates. Health systems can improve telehealth infrastructure by incorporating patient portal enrollment into in-person workflows, educating on the importance of telehealth, and devising workarounds for technological barriers.

Accurate prediction of SARS-CoV-2 infection based on symptoms can be a cost-efficient tool for remote screening in healthcare settings with limited SARS-CoV-2 testing capacity. We used a machine learning approach to determine self-reported symptoms that best predict a positive SARS-CoV-2 test result in physician trainees from a large healthcare system in New York. We used survey data on symptoms history and SARS-CoV-2 testing results collected retrospectively from 328 physician trainees in the Mount Sinai Health System, over the period 1 February 2020 to 31 July 2020. Prospective data on symptoms reported prior to SARS-CoV-2 test results were available from the employee health service COVID-19 registry for 186 trainees and analyzed to confirm absence of recall bias. We estimated the associations between symptoms and IgG antibody and/or reverse transcriptase polymerase chain reaction test results using Bayesian generalized linear mixed effect regression models adjusted for confounders. We identified symptoms predicting a positive SARS-CoV-2 test result using extreme gradient boosting (XGBoost). Cough, chills, fever, fatigue, myalgia, headache, shortness of breath, diarrhea, nausea/vomiting, loss of smell, loss of taste, malaise and runny nose were associated with a positive SARS-CoV-2 test result. Loss of taste, myalgia, loss of smell, cough and fever were identified as key predictors for a positive SARS-CoV-2 test result in the XGBoost model. Inclusion of sociodemographic and occupational risk factors in the model improved prediction only slightly (from AUC = 0.822 to AUC = 0.838). Loss of taste, myalgia, loss of smell, cough and fever are key predictors for symptom-based screening of SARS-CoV-2 infection in healthcare settings with remote screening and/or limited testing capacity.