11/2023

Happy to announce that we are one of the 16 recipients of INSPIRE Research Challenge grants from WCRF International in partnership with the American Institute for Cancer Research and Wereld Kanker Onderzoek Fonds. We will use our chatbot DAPHNE(c), an intelligent chatbot, to address social and mental health needs in real-time for families of children with cancer. This is a collaborative work by Skeens Lab and Intelligent Futures Research Lab at Nationwide Children's Hospital. Link for more details.

10/2023

We will be presenting two of our latest research from the Intelligent Futures Research Lab at Nationwide Children's Hospital at AMIA 2023: An AI-based Embodied Conversational Agent (DAPHNE) for Social Needs Identification and Resource Allocation in At-risk Neighborhoods and assessment and integration of a clinical conversation summarization (digital scribe) pipeline. For more information, please visit AMIA webpage.

07/2023

My latest viewpoint is about the ongoing discussion on "AI replacing doctors". Main takeaways are (1) AI is not here to replace doctors but to augment their roles and improve healthcare efficiency; (2) With the human-in-the-loop concept, AI and healthcare providers' collaboration for optimal patient outcomes is essential; (3) The successful adoption of AI in healthcare organizations extends beyond personal choice—it requires a systematic, organizational approach. Open access paper available here.

04/2023
I will be joining the Open Voice Network panel talk at the upcoming HIMSS23: "It Speaks, It Listens, It's Your Daily Voice Assistant - Leveraging Voice Technology in Health and Wellness" [Monday, April 17th @ 12:45 PM CT]. Voice technology is transforming the healthcare industry. We will discuss the current use of voice technology, and conversational AI in the healthcare industry, including medical practice, healthcare operations, remote patient monitoring, and health management.

04/2023

Generative pretrained transformer models and large language models are the popular AI/ML solutions in the market. However, questions regarding the implementation and operability in health care, clinical practice, and research remain unanswered. In this lecture, we will review these models and their capabilities and address considerations for the implementation and operationalization in healthcare and clinical practice. 

03/2023

Our team has been selected as one of the 15 Phase 2 winners of HRSA Building Bridges to Better Health: A Primary Health Care Challenge! We are thrilled to be recognized for our innovative solution to address social needs by an intelligent conversational agent designed for screening and resource sharing.

02/2023

Unstructured PGHD provides a new and untapped layer in patient health records which can inform decision-making and support remote monitoring and self-care. In this paper, we share the new research findings and preliminary results for the customizable information extraction (IE) NLP model focused on extracting a broad range of clinical information from unstructured PGHD in low-resource settings, especially as it relates to chronic disease management. The full paper (open-access) is available at JMIR.

12/2022

There is a significant increase in research, development, and commercial implementations & interest in designing and evaluating CAs. In our study, we identify key design, development, and evaluation challenges of CAs in healthcare and well-being research. The focus is on the very recent projects with their emerging challenges. The full paper (open-access) is available at JMIR.

11/2022

 I will be participating health data science symposium at Harvard (Nov 3-5), having a chance to learn more about digital phenotyping, using active and passive data in research, hands-on data analysis practice, and listening/networking with brilliant researchers in this field. I will present our work on unstructured PGHD and voice, which is positioned uniquely as having features of active and passive data. 

10/2022

 I will be at the Voice Summit 2022 this October, speaking about the evidence and future of voice technologies and conversational AI in self-management, RPM, and healthcare at the Open Voice Network healthcare track (Oct 12th).

09/2022

The use of artificial intelligence (AI) in child health research and clinical practice has steadily increased. In this paper, we propose three considerations to orient pediatric teams with diverse stakeholders leveraging AI solutions to advance child health equity. It is available at The Lancet Child and Adolescent Health. An author copy is available here.

08/2022

We aimed to understand the current state of hospital-owned mobile apps provided by large pediatric hospitals via a systematic search on Google Play and Apple App Store platforms. Based on the most common features, these apps were designed to help improve accessibility for patients and families in terms of finding providers, scheduling appointments, and accessing patient resources. Open-access available at JMIR Pediatrics and Parenting

06/2022

Isn't it nice to have Google or Microsoft predicting our next words and suggestions while typing our emails?  What if healthcare providers can use similar predictive models while taking clinical notes? In our study, we evaluated generative pre-trained transformer models (GPT) with more than 370,000 free-text electronic medical records to understand the performance of GPT models in text prediction with the medical notes taken. The paper is available at Methods of Information in Medicine. Open access author's copy is here.

05/2022

With the increased sharing of electronic health information as required by the 21st Century Cures Act, there is an increased risk of breaching patient or parent/guardian confidentiality. The prevalence of sensitive terms in clinical notes is not known.  The aim of our study is to define sensitive terms that represent documentation of content that may be private and determine the prevalence and characteristics of provider notes that contain sensitive terms. Open access available at JMIR Med Informatics.

04/2022

This May, I will be presenting our study “Remote patient monitoring (RPM) through the narratives: Leveraging speech and free - text patient-generated health data in shared clinical decision making and telehealth practice” at ATA 2022 conference in Boston. Here is the link for the agenda and details about the conference.

04/2022

Despite the rapid increase in using DHTs for clinical and healthcare research, BYOD use in clinical trials is limited, and regulatory guidance is still evolving. In this article, we offer recommendations for the design and deployment of BYOD models in clinical research. Open access available at the Journal of Digital Biomarkers.

04/2022

This year at SBM 2022, our team is presenting 2 of our studies: “It’s a hustle” Can we use digital health interventions for stress management among low-income families with young children"  & "Personal medical diaries meet AI: Feasibility of using medical notes to improve remote care during the pandemic".  The abstracts will be available in the Annals of Behavioral Medicine.

04/2022

mHealth tools have been promising healthcare technology that may contribute to cost savings, better access to care, and enhanced clinical outcomes; however, it is important to ensure their acceptance and adoption in order to harness this potential. Patient adoption has been recognized as a key challenge that requires further exploration. This review systematically investigates the literature to understand the factors impacting patients’ adoption of mHealth tools, by considering socio-technical factors (from technical, social, and health perspectives). Open access is available at JMIR mHealth uHealth.

02/2022

We conducted a pre-post study with a voice-enabled medical note-taking app in a real world setting with caregivers (parents, family members) of children with special healthcare needs (CSHCN) to understand feasibility and effectiveness of voice interaction and automatic speech recognition (ASR) for medical note-taking at home. Our paper is available open-access at Frontiers in Public Health.

02/2022 

We investigated one of the most popular AI tools (GPT-3) and discussed its use in clinical practice as-a-service model. One of the most popular AI or NLP models have been GPT-3, which has been utilized widely in the industry, such as, to build QnA mechanisms, chatbots, writing essays or translations. Their implementation in clinical practice could be challenging. We summarized considerations for implementation and operations in clinical practice. We illustrated our case with an example of triage chatbot and note summarization mechanism. Available at JMIR Medical Informatics.

01/2022

"Rapid Development of a Telehealth Patient Satisfaction Survey Using a Multi-Stakeholder Approach" and "Identifying the Factors Influencing Patients’ Telehealth Visit Satisfaction: Survey Validation Through a Structural Equation Modeling Approach" are available at the journal of Telemedicine and eHealth. (author copy available at RG)

In these studies, we explained our proposed telehealth patient satisfaction survey, and assessed factors influencing satisfaction through the proposed conceptual model of TPSM.