nutch_noindex
CANCEL
COVID-2019 Alert

Information about the 2019 Novel Coronavirus. Read the latest >

Información sobre el coronavirus 2019 (COVID-19). Aprenda más >

/nutch_noindex

Amit Singh, MD

  • Amit Tej Singh

Work and Education

Professional Education

Baylor College of Medicine Registrar, Houston, TX, 06/30/2008

Residency

Children's Hospital at Oakland, Oakland, CA, 06/30/2011

Fellowship

The Univ of San Diego School of Medicine, San Diego, CA, 06/30/2013

Board Certifications

Pediatrics, American Board of Pediatrics

All Publications

Automatic detection of hand hygiene using computer vision technology. Journal of the American Medical Informatics Association : JAMIA Singh, A., Haque, A., Alahi, A., Yeung, S., Guo, M., Glassman, J. R., Beninati, W., Platchek, T., Fei-Fei, L., Milstein, A. 2020

Abstract

Hand hygiene is essential for preventing hospital-acquired infections but is difficult to accurately track. The gold-standard (human auditors) is insufficient for assessing true overall compliance. Computer vision technology has the ability to perform more accurate appraisals. Our primary objective was to evaluate if a computer vision algorithm could accurately observe hand hygiene dispenser use in images captured by depth sensors.Sixteen depth sensors were installed on one hospital unit. Images were collected continuously from March to August 2017. Utilizing a convolutional neural network, a machine learning algorithm was trained to detect hand hygiene dispenser use in the images. The algorithm's accuracy was then compared with simultaneous in-person observations of hand hygiene dispenser usage. Concordance rate between human observation and algorithm's assessment was calculated. Ground truth was established by blinded annotation of the entire image set. Sensitivity and specificity were calculated for both human and machine-level observation.A concordance rate of 96.8% was observed between human and algorithm (kappa = 0.85). Concordance among the 3 independent auditors to establish ground truth was 95.4% (Fleiss's kappa = 0.87). Sensitivity and specificity of the machine learning algorithm were 92.1% and 98.3%, respectively. Human observations showed sensitivity and specificity of 85.2% and 99.4%, respectively.A computer vision algorithm was equivalent to human observation in detecting hand hygiene dispenser use. Computer vision monitoring has the potential to provide a more complete appraisal of hand hygiene activity in hospitals than the current gold-standard given its ability for continuous coverage of a unit in space and time.

View details for DOI 10.1093/jamia/ocaa115

View details for PubMedID 32712656

Current Practices and Perspectives on Peer Observation and Feedback: A National Survey. Academic pediatrics McDaniel, C. E., Singh, A. T., Beck, J. B., Birnie, K., Fromme, H. B., Ginwalla, C. F., Griego, E., King, M., Maniscalco, J., Nazif, J., Patra, K. P., Seelbach, E., Walker, J. M., Bhansali, P. 2019

Abstract

OBJECTIVE: Peer observation and feedback (POF) is the direct observation of an activity performed by a colleague followed by feedback with the goal of improved performance and professional development. Although well described in the education literature, the use of POF as a tool for development beyond teaching skills has not been explored. We aimed to characterize the practice of POF among pediatric hospitalists, to explore the perceived benefits and barriers, and to identify preferences regarding POF.METHODS: We developed a 14-item cross-sectional survey regarding divisional expectations, personal practice, perceived benefits and barriers, and preferences related to POF. We refined the survey based on expert feedback, cognitive interviews, and pilot testing, distributing the final survey to pediatric hospitalists at twelve institutions across the United States.RESULTS: Of 357 eligible participants, 198 (56%) responded with 115 (58%) practicing in a freestanding children's hospital. While 61% had participated in POF, less than half (42%) reported divisional POF expectation. The most common perceived benefits of POF were identifying areas for improvement (94%) and learning about colleagues' teaching and clinical styles (94%). The greatest perceived barriers were time (51%) and discomfort with receiving feedback from peers (38%), although participation within a POF program reduced perceived barriers. Most (76%) desired formal POF programs focused on improving teaching skills (85%), clinical management (83%), and family-centered rounds (82%).CONCLUSION: Though the majority of faculty desired POF, developing a supportive environment and feasible program is challenging. This study provides considerations for improving and designing POF programs.

View details for PubMedID 30910598

Secure Text Messaging in Healthcare: Latent Threats and Opportunities to Improve Patient Safety. Journal of hospital medicine Hagedorn, P. A., Singh, A., Luo, B., Bonafide, C. P., Simmons, J. M. 2019; 14: E1E3

View details for DOI 10.12788/jhm.3305

View details for PubMedID 31532741

Working to Make the Hospital Smarter. Hospital pediatrics Singh, A. T. 2017; 7 (2): 12224

View details for DOI 10.1542/hpeds.2016-0092

View details for PubMedID 28049133

Who's My Doctor? Using an Electronic Tool to Improve Team Member Identification on an Inpatient Pediatrics Team. Hospital pediatrics Singh, A., Rhee, K. E., Brennan, J. J., Kuelbs, C., El-Kareh, R., Fisher, E. S. 2016; 6 (3): 157-165

Abstract

Increase parent/caregiver ability to correctly identify the attending in charge and define terminology of treatment team members (TTMs). We hypothesized that correct TTM identification would increase with use of an electronic communication tool. Secondary aims included assessing subjects' satisfaction with and trust of TTM and interest in computer activities during hospitalization.Two similar groups of parents/legal guardians/primary caregivers of children admitted to the Pediatric Hospital Medicine teaching service with an unplanned first admission were surveyed before (Phase 1) and after (Phase 2) implementation of a novel electronic medical record (EMR)-based tool with names, photos, and definitions of TTMs. Physicians were also surveyed only during Phase 1. Surveys assessed TTM identification, satisfaction, trust, and computer use.More subjects in Phase 2 correctly identified attending physicians by name (71% vs. 28%, P < .001) and correctly defined terms intern, resident, and attending (P .03) compared with Phase 1. Almost all subjects (>79%) and TTMs (>87%) reported that subjects' ability to identify TTMs moderately or strongly impacted satisfaction and trust. The majority of subjects expressed interest in using computers to understand TTMs in each phase.Subjects' ability to correctly identify attending physicians and define TTMs was significantly greater for those who used our tool. In our study, subjects reported that TTM identification impacted aspects of the TTM relationship, yet few could correctly identify TTMs before tool use. This pilot study showed early success in engaging subjects with the EMR in the hospital and suggests that families would engage in computer-based activities in this setting.

View details for DOI 10.1542/hpeds.2015-0164

View details for PubMedID 26920366

Mom, Im going to be an INPATIENT doctor (A Graduating PHM Fellows Musings on the Past, Present, and Future) Hospital Pediatrics Singh, A. T. 2013; 3: 2

View details for DOI 10.1542/hpeds.2013-0030

Painful Arthritis and Extremity Rash in an 8-Year-Old Boy CLINICAL INFECTIOUS DISEASES Islam, S., Cooney, T., Singh, A., Petru, A. M., LaBeaud, A. D. 2012; 54 (10): 1473-?

View details for DOI 10.1093/cid/cir1007

View details for Web of Science ID 000304049300019

View details for PubMedID 22527963