Dhaval Save

Dhaval Save

Auto-generated profile, based on publicly available information

Dhaval Save

Department of Gastroenterology, Carle Health Methodist Hospital, Peoria, IL, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
22 May 2024 in Mayo Clinic Proceedings: Digital Health
Verified
Journal Article
Open access
ABArchana Reddy Bongurala
Archana Reddy Bongurala
DSDhaval Save
Dhaval Save
AVAnkit Virmani
Ankit Virmani
Rahul KashyapRahul Kashyap
Rahul Kashyap

25 November 2024 in PLOS Mental Health
Verified
Journal Article
Open access
PDF file
ABArchana Bongurala
Archana Bongurala
DSDhaval Save
Dhaval Save
AVAnkit Virmani
Ankit Virmani
Attention-deficit/hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder affecting millions of individuals worldwide, posing significant challenges in accurate diagnosis and effective management [1]. ADHD impacts 3-10% of children, causing inattention, hyperactivity, and impulsivity that disrupt social, academic, and occupational life, potentially lasting into adulthood [2]. The complex symptomatology and heterogeneous nature of ADHD have long posed difficulties for healthcare professionals, leading to misdiagnosis, delayed management, and suboptimal outcomes. However, the rapid advancements in artificial intelligence (AI) offer a transformative opportunity to revolutionize the diagnosis and management of ADHD, providing a more objective, data-driven approach to improve patient outcomes. Enhancing diagnostic accuracy Traditional methods of diagnosis of ADHD in pediatric and adolescent individuals relies on a comprehensive approach encompassing a detailed clinical history, physical examination, review of information from home and community settings, and application of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) criteria [3]. Reliance on subjective reports can be biased and miss co-existing conditions. The thorough evaluation process can be time-consuming and resource-heavy. Additionally, standardized assessments might not capture cultural nuances, potentially leading to misdiagnosis. These limitations pave the way for AI to potentially improve ADHD diagnosis, accuracy and efficiency [3]. As shown in Fig 1, AI's ability to process and analyze vast amounts of multimodal data, including neuroimaging, genetic, and behavioral information, has the potential to identify complex patterns and biomarkers associated with ADHD. Machine learning algorithms, such as support vector machines and deep neural networks, have shown promising results in classifying ADHD based on functional magnetic resonance imaging (fMRI) data, achieving high accuracy rates [4]. These AI-based approaches can detect subtle abnormalities in brain connectivity patterns that may be overlooked by human observers, providing objective evidence to support clinical decision-making. Moreover, AI can integrate multiple data sources, such as neuropsychological assessments, electronic health records, and even digital phenotyping data from wearable devices, to create comprehensive patient profiles and aid in the differential diagnosis of ADHD [5]. Recent studies have explored innovative AI-based approaches to enhance ADHD screening and diagnosis. For instance, Yoo et al. [2] developed a machine learning model using portable eye tracking data to assist in ADHD screening. The study demonstrated the potential of eye movement patterns as biomarkers for ADHD, with the AI model achieving promising

30 January 2026 in Clinical Endoscopy
Verified
Journal Article
Open access
EAEugene Annor
Eugene Annor
NUNneoma Ubah
Nneoma Ubah
DSDhaval Save
Dhaval Save
Ishaan VohraIshaan Vohra
Ishaan Vohra
RSRitu Raj Singh
Ritu Raj Singh
HGHarishankar Gopakumar
Harishankar Gopakumar
Background/Aims: Biliary cannulation is a critical component of endoscopic retrograde cholangiopancreatography (ERCP). When standard methods fail, needle-knife precut sphincterotomy (NKPS) is commonly employed. This systematic review and meta-analysis evaluated the safety and efficacy of using NKPS as a primary technique.Methods: Electronic databases were searched for studies published between January 2000 and November 2024 that assessed outcomes of primary precut techniques. “Primary precut” was defined as needle-knife sphincterotomy performed as the initial approach without any prior standard cannulation attempts. Pooled proportions were calculated using random-effects models, and heterogeneity was assessed using the Q-test and the I² statistic.Results: The mean patient age was 57.95 years (standard deviation [SD], 7.59), and 53.23% were female. The cannulation success rate was 96.50% (95% confidence interval [CI], 94.90–97.60) with no heterogeneity (Q, 7.10; df, 8; I²=0%; p=0.935). The rates of adverse events were as follows: post-ERCP pancreatitis, 1.90% (95% CI, 1.20–3.10; I²=0; p =0.942); bleeding, 2.60% (95% CI, 1.70–4.00, I²=0; p=0.725); cholangitis, 1.50% (95% CI, 0.60–3.60; I²=45.27; p=0.067); and perforation, 0.90% (95% CI, 0.40–1.90; I²=0; p=0.948). The overall adverse event rate was 9.70% (95% CI, 5.70–16.10; I²=83.39; p<0.001).Conclusions: Primary precut sphincterotomy appears to be an effective and safe technique for biliary cannulation in ERCP. These findings support its consideration as a viable first-line approach in appropriate clinical settings.

1 November 2025 in Annals of Internal Medicine: Clinical Cases
Verified
Journal Article
Closed access
DSDhaval Save
Dhaval Save
PSPraveen Sudhindra
Praveen Sudhindra