Apurv Soni

Apurv Soni

Auto-generated profile, based on publicly available information

Apurv Soni

University of Massachusetts Medical School

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2025 in Frontiers in Psychiatry
Verified
Journal Article
Open access
PDF file
HLHyein S. Lee
Hyein S. Lee
CWColton Wright
Colton Wright
JFJulia Ferranto
Julia Ferranto
JBJessica Buttimer
Jessica Buttimer
CPClare E. Palmer
Clare E. Palmer
ASApurv Soni
Apurv Soni
Background: Digital mental health interventions, such as artificial intelligence (AI) conversational agents, hold promise for improving access to care by innovating therapy and supporting delivery. However, little research exists on patient perspectives regarding AI conversational agents, which is crucial for their successful implementation. This study aimed to fill the gap by exploring patients’ perceptions and acceptability of AI conversational agents in mental healthcare.Methods: Adults with self-reported mild to moderate anxiety were recruited from the UMass Memorial Health system. Participants engaged in semi-structured interviews to discuss their experiences, perceptions, and acceptability of AI conversational agents in mental healthcare. Anxiety levels were assessed using the Generalized Anxiety Disorder scale. Data were collected from December 2022 to February 2023, and three researchers conducted rapid qualitative analysis to identify and synthesize themes.Results: The sample included 29 adults (ages 19-66), predominantly under age 35, non-Hispanic, White, and female. Participants reported a range of positive and negative experiences with AI conversational agents. Most held positive attitudes towards AI conversational agents, appreciating their utility and potential to increase access to care, yet some also expressed cautious optimism. About half endorsed negative opinions, citing AI’s lack of empathy, technical limitations in addressing complex mental health situations, and data privacy concerns. Most participants desired some human involvement in AI-driven therapy and expressed concern about the risk of AI conversational agents being seen as replacements for therapy. A subgroup preferred AI conversational agents for administrative tasks rather than care provision.Conclusions: AI conversational agents were perceived as useful and beneficial for increasing access to care, but concerns about AI’s empathy, capabilities, safety, and human involvement in mental healthcare were prevalent. Future implementation and integration of AI conversational agents should consider patient perspectives to enhance their acceptability and effectiveness.

11 October 2022 in Annals of Internal Medicine
Verified
Journal Article
Open access
ASApurv Soni
Apurv Soni
CHCarly Herbert
Carly Herbert
AFAndreas Filippaios
Andreas Filippaios
JBJohn Broach
John Broach
ACAndres Colubri
Andres Colubri
DMDavid McManus
David McManus
Use of rapid tests for diagnosis of COVID-19 is now commonplace, but questions remain regarding their performance characteristics compared with those of polymerase chain reaction testing. The role ... Visual Rapid Antigen Test Performance for Delta vs. Omicron SARS-CoV-2 Variants. Use of rapid tests for diagnosis of COVID-19 is now commonplace, but questions remain regarding their perfo... Background: It is important to document the performance of rapid antigen tests (Ag-RDTs) in detecting SARS-CoV-2 variants. Objective: To compare the performance of Ag-RDTs in detecting the Delta (B...

1 April 2019 in International Journal of Cardiology
Verified
Journal Article
Closed access
ASApurv Soni
Apurv Soni
SKSunil Karna
Sunil Karna
NFNisha Fahey
Nisha Fahey
SSSaket Sanghai
Saket Sanghai
HPHarshil Patel
Harshil Patel
DMDavid D. McManus
David D. McManus

15 May 2019 in JMIR Cardio
Verified
Journal Article
Open access
EDEric Y Ding
Eric Y Ding
DHDong Han
Dong Han
CWCody Whitcomb
Cody Whitcomb
Syed Khairul BasharSyed Khairul Bashar
Syed Khairul Bashar
OAOluwaseun Adaramola
Oluwaseun Adaramola
DMDavid D McManus
David D McManus
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Atrial fibrillation (AF) is often paroxysmal and minimally symptomatic, hindering its diagnosis. Smartwatches may enhance AF care by facilitating long-term, non-invasive monitoring. Objective: We aimed to examine the accuracy and usability of arrhythmia discrimination using a smartwatch. Methods: Forty adults presenting to a cardiology clinic wore a smartwatch and performed scripted movements to simulate activities of daily living (ADLs). Clinical and sociodemographic characteristics of participants were abstracted from medical records. Participants completed a questionnaire assessing usability and different domains of their experience with the device. Pulse recordings were analyzed blindly using a real-time realizable algorithm and compared to gold-standard Holter monitoring. Results: Average age of participants was 71  8 years, most had AF risk factors, and 9 (23%) were in AF. About half of participants owned smartphones but none owned smartwatches. Participants wore the smartwatch for 42  14 minutes while generating motion noise to simulate ADLs. The algorithm determined 53 of 314 30-second noise-free pulse segments as consistent with AF. Compared to the gold-standard, the algorithm demonstrated excellent sensitivity (98.2%), specificity (98.1%), and accuracy (98.1%) for identifying irregular pulse. Two-thirds of participants considered the smartwatch highly usable. Younger age and prior cardioversion were associated with greater overall comfort and comfort with data privacy with using a smartwatch for rhythm monitoring, respectively. Conclusions: A real-time realizable algorithm analyzing smartwatch pulse recordings demonstrated high accuracy for identifying pulse irregularities among older participants simulating ADLs. Despite advanced age, lack of smartwatch familiarity, and high burden of comorbidities, participants found the smartwatch to be highly acceptable.

4 July 2023 in Annals of Internal Medicine
Verified
Journal Article
Closed access
ASApurv Soni
Apurv Soni
CHCarly Herbert
Carly Herbert
HLHonghuang Lin
Honghuang Lin
YYYi Yan
Yi Yan
CPCaitlin Pretz
Caitlin Pretz
DMDavid D. McManus
David D. McManus
The performance of rapid antigen tests (Ag-RDTs) for screening asymptomatic and symptomatic persons for SARS-CoV-2 is not well established. To evaluate the performance of Ag-RDTs for detection of SARS-CoV-2 among symptomatic and asymptomatic participants. This prospective cohort study enrolled participants between October 2021 and January 2022. Participants completed Ag-RDTs and reverse transcriptase polymerase chain reaction (RT-PCR) testing for SARS-CoV-2 every 48 hours for 15 days. Participants were enrolled digitally throughout the mainland United States. They self-collected anterior nasal swabs for Ag-RDTs and RT-PCR testing. Nasal swabs for RT-PCR were shipped to a central laboratory, whereas Ag-RDTs were done at home. Of 7361 participants in the study, 5353 who were asymptomatic and negative for SARS-CoV-2 on study day 1 were eligible. In total, 154 participants had at least 1 positive RT-PCR result. The sensitivity of Ag-RDTs was measured on the basis of testing once (same-day), twice (after 48 hours), and thrice (after a total of 96 hours). The analysis was repeated for different days past index PCR positivity (DPIPPs) to approximate real-world scenarios where testing initiation may not always coincide with DPIPP 0. Results were stratified by symptom status. Among 154 participants who tested positive for SARS-CoV-2, 97 were asymptomatic and 57 had symptoms at infection onset. Serial testing with Ag-RDTs twice 48 hours apart resulted in an aggregated sensitivity of 93.4% (95% CI, 90.4% to 95.9%) among symptomatic participants on DPIPPs 0 to 6. When singleton positive results were excluded, the aggregated sensitivity on DPIPPs 0 to 6 for 2-time serial testing among asymptomatic participants was lower at 62.7% (CI, 57.0% to 70.5%), but it improved to 79.0% (CI, 70.1% to 87.4%) with testing 3 times at 48-hour intervals. Participants tested every 48 hours; therefore, these data cannot support conclusions about serial testing intervals shorter than 48 hours. The performance of Ag-RDTs was optimized when asymptomatic participants tested 3 times at 48-hour intervals and when symptomatic participants tested 2 times separated by 48 hours. National Institutes of Health RADx Tech program.

15 October 2017 in Archives of Women's Mental Health
Verified
Journal Article
Open access
PDF file
JKJasmine Khubchandani
Jasmine Khubchandani
ASApurv Soni
Apurv Soni
NFNisha Fahey
Nisha Fahey
NRNitin Raithatha
Nitin Raithatha
APAnusha Prabhakaran
Anusha Prabhakaran
JAJeroan J. Allison
Jeroan J. Allison
The aim of this study is to examine the relationship of caste and class with perceived discrimination among pregnant women from rural western India. A cross-sectional survey was administered to 170 pregnant women in rural Gujarat, India, who were enrolled in a longitudinal cohort study. The Everyday Discrimination Scale and the Experiences of Discrimination questionnaires were used to assess perceived discrimination and response to discrimination. Based on self-report caste, women were classified into three categories with increasing historical disadvantage: General, Other Backward Castes (OBC), and Scheduled Caste or Tribes (SC/ST). Socioeconomic class was determined using the standardized Kuppuswamy scale. Regression models for count and binomial data were used to examine association of caste and class with experience of discrimination and response to discrimination. Sixty-eight percent of women experienced discrimination. After adjusting for confounders, there was a consistent trend and association of discrimination with caste but not class. In comparison to General Caste, lower caste (OBC, SC/ST) women were more likely to (1) experience discrimination (OBC OR: 2.2, SC/ST: 4.1; p trend: 0.01); (2) have a greater perceived discrimination score (OBC IRR: 1.3, SC/ST: 1.5; p trend: 0.07); (3) accept discrimination (OBC OR: 6.4, SC/ST: 7.6; p trend: < 0.01); and (4) keep to herself about discrimination (OBC OR: 2.7, SC/ST: 3.6; p trend: 0.04). The differential experience of discrimination by lower caste pregnant women in comparison to upper caste pregnant women and their response to such experiences highlight the importance of studying discrimination to understand the root causes of existing caste-based disparities.