Hetal Lad

Ms. Hetal Lad

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
HLHetal Lad
Hetal Lad
EKEmily Kwon
Emily Kwon
ACAyushi Chadha
Ayushi Chadha
SHSean Haimowitz
Sean Haimowitz
BGBrandon S. Gold
Brandon S. Gold
WHWayne D Hsueh
Wayne D Hsueh
Background/Objectives: As patients increasingly rely on large language models (LLMs) for Chronic Rhinosinusitis (CRS) diagnosis, surgical candidacy, and perioperative care, evaluating the accuracy of LLM-generated information against established clinical practice guidelines for surgical management of CRS is essential. Methods: ChatGPT, Google AI, Google Gemini, and Grok were queried using a 21-question guideline-mapped prompt set (long) and a single patient-focused prompt (short). Two physician reviewers independently scored responses using a 3-point rubric across 21 fields. Primary outcomes were guideline-concordant scores; secondary outcomes included readability measured with the Flesch Reading Ease (FRE) and Flesch-Kincaid Grade Level (FKGL). Inter-rater reliability (IRR) was assessed using the intraclass correlation coefficient (ICC). Analyses were performed in SPSSv31. Results: Guideline concordance ranged from 55.36% to 77.98% (p > 0.05), highest for Grok (77.98%, 95% CI 63.67–92.28), followed by Google Gemini (66.67%, 95% CI 35.42–97.91), ChatGPT (55.95%, 95% CI 29.25–82.65), and Google AI (55.36%, 95% CI 29.97–80.75), with Grok significantly outperforming both ChatGPT and Google AI. Prompt structure significantly affected scores. Long-form prompting resulted in higher guideline concordance scores than short-form prompting (+26.19, p < 0.001). The CPG demonstrated a more readable structure, with a higher FRE (44.1), exceeding scores generated by Grok (31.7), ChatGPT (39.9), Gemini (39.2), and Google AI (32.5). In contrast, the CPG was a higher reading grade level (FKGL score of 11.7) than Grok (11.4), Gemini (10.5), and ChatGPT (10.3), but was lower in reading grade compared to Google AI, which produced the highest FKGL score (12.5). IRR was high (ICC = 0.961). Conclusions: LLMs demonstrated similar guideline concordance, suggesting patients can expect comparable accuracy across platforms. While LLMs generally improved FKGL scores compared to the AAO-HNS CPG, they demonstrated lower FRE scores, indicating mixed results on overall readability. However, longer prompt structure meaningfully influenced output quality, highlighting how a user’s ability to frame precise prompts is critical to obtaining accurate information.

9 March 2026 in The Laryngoscope
Verified
Journal Article
Closed access
HLHetal Lad
Hetal Lad
SDSally Durant
Sally Durant
KYKenneth Yan
Kenneth Yan
RKRachel Kaye
Rachel Kaye

21 September 2026 in Medical Science Educator
Verified
Journal Article
Open access
PDF file
ILIvan Loncar
Ivan Loncar
SSShivani Srivastava
Shivani Srivastava
SASowntharya Ayyappan
Sowntharya Ayyappan
HLHetal Lad
Hetal Lad
AGAmy Gore
Amy Gore
Bergen Barbers is a student-led program at Rutgers New Jersey Medical School, where medical students provide free haircuts and grooming services to hospitalized patients. The program began as a pilot with four student volunteers in its first year and grew to sixteen newly recruited volunteers each academic year. This pilot study was conducted with the Fall 2025 cohort and used pre/post surveys ( n = 15 pre, n = 12 post) to assess changes in empathy, communication, and clinical confidence. Significant improvements were found in five areas: comfort with diverse patients, rapport-building, comfort with physical patient interactions, hospital navigation, and interactions with hospital staff. Students reported high satisfaction and observed visible mood improvements in patients. Bergen Barbers offers a practical model for building humanistic and clinical skills early in medical training.

HLHetal Lad
Hetal Lad
SSShrey Bhavik Shah
Shrey Bhavik Shah
SBShreeya Bahethi
Shreeya Bahethi
SVSudeepti Vedula
Sudeepti Vedula
BMBrian Manzi
Brian Manzi
Background/Objectives: Artificial intelligence (AI) tools are used in clinical education and patient communication. Concordance with American Academy of Otolaryngology–Head and Neck Surgery Foundation clinical practice guidelines (CPG) and overall readability remain poorly defined. Methods: Over 2 months, ChatGPT, Google Gemini, and Google Search AI were queried using a single LF prompt and a layered set of sub-questions. Responses were scored with a 12-point rubric from the CPG plain-language tonsillectomy guideline. Readability was assessed using Flesch Reading Ease (FRE) and Flesch-Kincaid Grade Level (FKGL). Temporal trends and between-group differences were analyzed using regression and repeated-measures methods. Results: Layered prompts demonstrated greater alignment with guideline subtopics than LF (89.5% vs. 71.4%, p < 0.001). For LF queries, mean concordance was 74.5% (95% CI 72.0–77.0) for Google AI, 71.3% (68.9–73.7) for Gemini, and 68.4% (66.0–70.9) for ChatGPT. Overall, Google AI outperformed Gemini and ChatGPT on pairwise comparisons (p = 0.001). Google AI demonstrated improvement in concordance (slope = 0.03, p = 0.003), while Gemini showed no change (p > 0.05) and ChatGPT worsened over time (slope = −0.03, p < 0.001). Readability differed by strategy and model. Layered prompts produced more accessible text (FKGL 44.6, FRE 10.3) compared with LF outputs (FKGL 35.2, FRE 11.3) and the CPG (FKGL 10.6, FRE 41.7). IRR was high (ICC = 0.96). Conclusions: Model type and prompt structure shaped the quality of AI-generated tonsillectomy guidance. Google AI consistently outperformed ChatGPT, with Gemini intermediate, and uniquely showed temporal improvement. Layered prompting produced more CPG-aligned and readable responses across all models. Readability was consistently above a 7th grade level.

19 January 2026 in Journal of Scientific Innovation in Medicine
Verified
Journal Article
Open access
PDF file
MWMarcee Wilder
Marcee Wilder
ADAleksandra Degtyar
Aleksandra Degtyar
LGLauren Gordon
Lauren Gordon
GLGeorge Loo
George Loo
HLHetal Lad
Hetal Lad
KSKimberly Souffront
Kimberly Souffront
Objective: The role of social determinants of health (SDOH) among adult emergency department (ED) patients with hypertension remains largely unexplored. This study aims to address this critical knowledge gap. Methods: Electronic Health Record data from patients visiting six urban EDs between September 1, 2019, and October 21, 2022 with hypertension [Stage 1 hypertension (two blood pressure readings ≥ 130/80 mmHg)] or Stage 2 hypertension (≥140/90 mmHg)] were obtained along with their demographic and social characteristics such as employment, age, sex, insurance status and comorbidities. Bivariate analysis and multivariate regression modeled the odds of hypertension with demographic and social data, reported as odds ratios (OR) with 95% confidence intervals (CI). Results: Among 822,843 encounters, 22.8% (n = 187,664) involved patients with Stage 1 hypertension. These patients were middle-aged (mean age 60 years) and were more likely to have a prior diagnosis of hypertension (OR 3.02, 95% CI 2.96–3.09), be male (OR 1.14, 95% CI 1.12–1.14), African American (OR 1.40, 95% CI 1.37–1.42), and current smokers (OR 1.05, 95% CI 1.03–1.06), and less likely to be publicly insured (OR 0.91, 95% CI 0.89–0.92). Stage 2 hypertension occurred in 13.0% of encounters (n = 109,231). These patients had a similar mean age (63 years) and showed comparable associations, including higher odds of being African American (OR 1.61, 95% CI 1.58–1.64), unemployed (OR 0.50, 95% CI 0.47–0.52), having a prior hypertension diagnosis (OR 3.37, 95% CI 3.30–3.45), and smoking (OR 1.09, 95% CI 1.06–1.11). They were also less likely to be publicly insured (OR 0.91, 95% CI 0.89–0.93) or to present during the COVID period (OR 0.92, 95% CI 0.89–0.95). Conclusions: In this large, multicenter ED-based cohort, elevated blood pressure was consistently associated with key social and demographic factors, including race/ethnicity, insurance status, employment, and smoking. These findings underscore the importance of considering social context when evaluating hypertension in emergency department settings.

5 November 2026 in The Laryngoscope
Verified
Journal Article
Open access
HLHetal Lad
Hetal Lad
ASAvi Shah
Avi Shah
ETEmma R. Thompson
Emma R. Thompson
SJSumayya Javid
Sumayya Javid
RCRuey Horng Chee
Ruey Horng Chee
KYKenneth Yan
Kenneth Yan
Objective: Laryngeal cancer accounts for 40% of head and neck malignancies and 1% of all cancer‐related deaths worldwide. We evaluated the laryngeal cancer microbiome to identify cancer‐specific genera as potential treatment targets. Methods: A prospective study was conducted using 57 laryngeal mucosal samples from 24 treatment‐naive laryngeal cancer patients and 33 patients who were undergoing otolaryngological surgery unrelated to oral or laryngeal diseases (01/2023–09/2025). DNA was extracted and amplified in triplicate, targeting the V3/V4 region of the 16S rRNA gene, followed by paired‐end 2 × 300 bp sequencing on the Illumina NextSeq 2000. Amplicon sequence variants were identified via DADA2 and assigned to genera using a naive Bayes classifier. Two samples with zero classified read pairs were excluded. Results: Most patients were male (87.5% cancer, 66.7% controls) and smokers (83.3% cancer, 54.5% controls). Cancer patients' core laryngeal microbiomes uniquely contained Parvimonas (3.67%; 95% CI: 0.70%–6.64%), and Campylobacter (1.12%; 95% CI: 0.60%–1.63%), while control patients' uniquely contained Corynebacterium (2.97%; 95% CI: 0.00%–7.67%) and Alloprevotella (1.34%; 95% CI: 0.64%–2.04%). Cancer samples were significantly enriched in 19 genera, notably Peptococcus (2.93, q = 0.0003), Campylobacter (1.68, q = 0.009), and Parvimonas (2.02, q = 0.03), compared to controls. Conclusions: Laryngeal cancer patients' samples displayed microbial dysbiosis, with enrichment of microbes present in gastrointestinal cancers, cervical cancer, and inflammatory states; they also exhibited loss of immunoprotective taxa. These findings support that microbiome profiling can distinguish malignant mucosa and guide future studies targeting genera increased in cancer, including Parvimonas and Campylobacter . Level of Evidence: 3.