Nevin Manimala

JMIR Med Inform. 2026 Jul 24;14:e86145. doi: 10.2196/86145.

ABSTRACT

BACKGROUND: Accurate assessment of pulpal status is essential for achieving successful endodontic outcomes. However, direct evaluation remains inherently challenging because the pulp is surrounded by calcified tissue, necessitating reliance on clinical and radiographic examinations for diagnostic and prognostic decision-making. These procedures demand substantial clinical expertise and time, and less-experienced clinicians often face challenges that may lead to errors in diagnosis and treatment planning. Recent advancements in large language models (LLMs) offer promising opportunities to enhance clinical reasoning by facilitating the integration of evidence and supporting methodical diagnostic decision-making.

OBJECTIVE: This study aimed to evaluate the clinical applicability of LLMs by comparing their text-based clinical screening performance and the clinical validity of their treatment plan responses with those of human evaluators.

METHODS: Between January 2011 and December 2022, 100 clinical cases involving primary endodontic disease were randomly selected from the clinical records of outpatients who visited the Department of Conservative Dentistry or Advanced General Dentistry (AGD) at Yonsei University Dental Hospital. Four prompt types, combining 2 variables (language and role), were used as input for 4 LLMs. Both LLMs and human evaluators (AGD specialists, AGD residents, endodontic residents, and senior dental students) assessed the cases using text-based clinical records. Radiographic images were not directly provided. Screening performance was evaluated using a 0-to-2-point concordance scale, and treatment plan validity and relevance were assessed using a 5-point Likert scale.

RESULTS: Among the 4 LLMs evaluated, ChatGPT achieved the highest mean concordance score on Korean-doctor prompts (mean 0.98, SD 0.82). However, this score did not reach the partially correct criterion of 1 on the 0 to 2-point scale. Clova X recorded the lowest mean score on English-patient prompts (mean 0.23, SD 0.63). Across both diagnostic categories, AGD specialists demonstrated the highest diagnostic accuracy (pulpal: 0.70; periapical: 0.65), with higher sensitivity but lower specificity than those exhibited by the other groups. ChatGPT also showed favorable performance among the LLMs, with accuracies of 0.65 (95% CI 0.55-0.74) for pulpal disease and 0.57 (95% CI 0.47-0.69) for periapical disease, which were comparable to those of AGD and endodontic residents.

CONCLUSIONS: Under image-free clinical record review conditions, ChatGPT 4.0 showed relatively higher and more consistent performance in symptom screening and treatment planning compared to the other LLMs evaluated. However, its highest mean score of 0.98 (SD 0.82) did not reach the partially correct criterion of 1 on the 0 to 2-point scale. Hallucinations generated by LLMs and experience-dependent interpretation biases among human evaluators remain key challenges that require attention. Therefore, continuous clinical supervision and comprehensive user training are necessary for the safe and effective clinical application.

PMID:42497401 | DOI:10.2196/86145

Nutr Rev. 2026 Jul 24:nuag105. doi: 10.1093/nutrit/nuag105. Online ahead of print.

ABSTRACT

CONTEXT: Omega-3 polyunsaturated fatty acids (PUFAs) have demonstrated metabolic benefits in several populations; however, their efficacy in type 1 diabetes mellitus (T1D) is not well established.

OBJECTIVE: The aim of this systematic review and meta-analysis was to assess the efficacy of omega-3 PUFAs supplementation on the lipid and glycemic profile in T1D.

DATA SOURCES: A systematic search was conducted in Medline, Scopus, Web of Science, and the Cochrane Library, from inception to June 2026.

DATA EXTRACTION: Studies evaluating the effect of omega-3 PUFA supplementation on total cholesterol (TC), low- and high-density lipoprotein cholesterol (LDL-C and HDL-C), triglycerides, fasting plasma glucose (FPG), and glycated hemoglobin (HbA1c) were included. Random-effects meta-analyses of randomized clinical trials (RCTs) and of the pre-post effect of a single intervention arm were performed separately. Heterogeneity was assessed using the I2 statistic.

DATA ANALYSIS: Eighteen studies were included. In the RCTs, omega-3 PUFA supplementation increased HDL-C by 4.47 mg/dL (95% CI, 0.07 to 8.86) with an I2 of 64.87%, and decreased triglycerides by 9.49 mg/dL (95% CI, 16.60 to -2.38) with an I2 of 29.83%. There was no effect on the other outcomes, including TC, LDL-C, FPG, and HbA1c. Finally, the effect on the meta-analyses of pre-post studies was similar to that found in the RCTs.

CONCLUSIONS: Although omega-3 supplementation has been associated with modest improvements in lipid levels in people with T1D, the results are statistically fragile. No glycemic benefits were observed. Future RCTs focusing on hard cardiovascular outcomes and standardized protocols are necessary to determine the clinical efficacy of omega-3 supplementation beyond surrogate metabolic markers.

SYSTEMATIC REVIEW REGISTRATION: PROSPERO registration No. [CRD420261297164].

PMID:42497400 | DOI:10.1093/nutrit/nuag105

JMIR Mhealth Uhealth. 2026 Jul 24;14:e74207. doi: 10.2196/74207.

ABSTRACT

BACKGROUND: Adolescents living with HIV often experience poor antiretroviral therapy (ART) outcomes due to multiple barriers affecting medication adherence. Effective self-care interventions are needed to address these challenges. Mobile phones are widely used by the adolescent population and therefore present an opportunity to enhance ART adherence using mobile phone-based interventions. However, research on mobile phone access among adolescents living with HIV, usage patterns, and perceptions of mobile phone-based interventions is limited in Eswatini.

OBJECTIVE: This study aimed to explore these aspects to inform effective mobile health strategies for enhancing ART adherence among adolescents living with HIV.

METHODS: We conducted a qualitative study using in-depth interviews in December 2023. A total of 29 adolescents living with HIV aged 10 to 19 years and enrolled on ART were purposively sampled and interviewed from 5 Teen Clubs in the Hhohho region of Eswatini. Interviews were audio-recorded and transcribed verbatim. Topic areas covered were mobile phone accessibility, usage patterns, and perceptions on the use of mobile phones to facilitate ART adherence. The data were analyzed using the deductive-inductive coding approach.

RESULTS: Of the 29 participants, 15 (52%) were female, and 19 (65.5%) were aged between 15 and 19 years. The study findings indicated high mobile phone access among participants, with primary usage focused on making and receiving calls, as well as engaging with social media. Three themes emerged regarding the use of gamified interventions to support ART adherence. First, the use of gamified interventions aimed at ART adherence among adolescents living with HIV was deemed feasible based on mobile phone access and past experiences with mobile games. Second, 3 main qualities of successful gamified interventions were identified as being supportive, being educational, and ensuring secure and confidential connections with other players. Finally, confidentiality and mobile phone access factors were highlighted as potential concerns when designing gamified ART adherence interventions.

CONCLUSIONS: The findings suggest potentially high access and usage of mobile phones among adolescents living with HIV on ART in Eswatini. This provides an opportunity to leverage mobile technology to enhance ART adherence through gamified interventions. However, it is essential to carefully consider the specific needs and concerns of adolescents living with HIV in the design of these interventions to ensure their successful uptake and sustainability.

PMID:42497375 | DOI:10.2196/74207

JMIR Res Protoc. 2026 Jul 24;15:e93439. doi: 10.2196/93439.

ABSTRACT

BACKGROUND: High-quality neonatal resuscitation (NR) depends on timely execution of technical and nontechnical skills. Simulation-based training improves NR performance, but it is resource-intensive and difficult to deliver at sufficient frequency. Immersive virtual reality (VR) simulation may provide a scalable supplement to traditional mannequin-based training; however, evidence from European neonatal training settings is limited.

OBJECTIVE: The aim of this study is to evaluate whether immersive VR-based simulation training used as a supplement to traditional mannequin-based simulation training improves NR performance among doctors and nurses in Denmark.

METHODS: NEONATAL is a multicenter, individually randomized, 2-arm controlled superiority trial with a parallel-group pretest-posttest design (trial registration number ISRCTN 43822066). Resident doctors and neonatal nurses from 4 hospitals in Eastern Denmark will be randomized to either traditional mannequin-based NR training alone or traditional mannequin-based simulation training supplemented with immersive VR simulation training. Outcomes will be assessed at baseline and endline at 6 to 8 weeks using standardized neonatal simulation scenarios, validated assessment tools, and questionnaires.

RESULTS: The study was funded in July and October 2025, as well as in January 2026. Participant recruitment began in October 2025 and was completed in December 2025, with 66 participants enrolled. Data collection was completed in February 2026. Data cleaning and analysis will take place from March to July 2026, and the results are expected to be published in autumn 2026. This study will provide data on the effectiveness, feasibility, and usability of immersive VR simulation training as a supplement to traditional mannequin-based NR training in routine clinical education.

CONCLUSIONS: The NEONATAL study addresses an important gap in NR education by evaluating immersive VR simulation training as a supplement to traditional mannequin-based training.

PMID:42497368 | DOI:10.2196/93439

JMIR Form Res. 2026 Jul 24;10:e80597. doi: 10.2196/80597.

ABSTRACT

BACKGROUND: Electrocardiograms (ECGs) are commonly stored in PDF, particularly as vector-based files generated by ECG management systems. Previous studies have demonstrated that ECG signals can be extracted through PDF-to-Scalable Vector Graphics (SVG) conversion, highlighting the potential to reconstruct waveform signals from vector graphics. These reconstructed signals further enable the derivation and prediction of clinically relevant ECG parameters.

OBJECTIVE: This study aimed to develop an integrated framework for direct reconstruction of high-fidelity ECG signals from vector-based PDF files and for simultaneous estimation of multiple clinically relevant ECG parameters using deep learning.

METHODS: In this retrospective methodological study, 50,000 twelve-lead ECG PDFs generated by a MUSE system (2015-2024) were analyzed. A direct PDF parsing pipeline was developed to extract vector path objects and reconstruct time-series signals without intermediate format conversion. Reconstruction accuracy was evaluated against the original system-exported signals. Two deep learning models, DualECGFormer and DualResNetECG, were developed to estimate 8 specific ECG parameters. The reference standards for these parameters-including ventricular rate; PR interval; QRS duration; QT interval; corrected QT interval (QTc); and the electrical axes of the P wave, QRS complex, and T wave-were derived from machine-generated values within the MUSE system database. Performance was compared with a rule-based approach (NeuroKit2).

RESULTS: The proposed method achieved high reconstruction fidelity, with mean absolute errors (MAEs) below 1×10-3 mV across all leads. Compared with an SVG-based workflow, the direct parsing approach reduced processing time by approximately 4.6-fold. For parameter estimation, deep learning models outperformed the rule-based method for most parameters. DualResNetECG achieved the best overall performance, with MAEs of 1.11 bpm for ventricular rate, 7.27 milliseconds for PR interval, 9.89 milliseconds for QRS duration, 11.87 milliseconds for QT, and 13.71 milliseconds for QTc. For electrical axis estimation, MAEs ranged from 8.0° to 16.31°. The model also demonstrated reliable detection of physiologically undefined parameters (PR interval and P-wave axis), achieving an area under the receiver operating characteristic curve of up to 0.978.

CONCLUSIONS: This study presents an efficient and scalable framework for direct extraction of ECG signals from MUSE-generated vector-based PDFs and integrated multiparameter estimation using deep learning. The approach achieves high reconstruction accuracy and competitive predictive performance, supporting its potential utility for large-scale retrospective MUSE ECG analysis.

PMID:42497366 | DOI:10.2196/80597

J Med Internet Res. 2026 Jul 24;28:e97802. doi: 10.2196/97802.

ABSTRACT

BACKGROUND: Large language models (LLMs) are increasingly used in health care, with emerging applications in clinical decision support and nursing education. However, evidence on their performance in nursing contexts, particularly in oncology nursing, remains limited. Given the complexity and high-risk nature of oncology care, it is important to evaluate the performance and clinical relevance of LLM-generated responses in oncology nursing contexts.

OBJECTIVE: This study aimed to compare the performance of LLMs in oncology nursing decision support tasks using standardized examination questions and case-based clinical scenarios and explore LLMs’ potential applicability and current limitations in oncology nursing practice.

METHODS: A total of 33 case-based questions derived from 10 oncology nursing clinical scenarios in a nationally used training manual, along with standardized examination-oriented questions from a commercially published preparation book for the Chinese Nursing (Intermediate) Qualification Examination, were used to evaluate the performance of 5 LLMs (DeepSeek, Qwen, Spark-Desk, WiseDiag, and ChatGPT). All models generated responses using a standardized prompt. Two oncology nurses with more than 5 years of clinical experience independently rated the case-based responses using 3 evaluation dimensions: correctness, clarity, and conciseness. Interrater reliability was assessed using the quadratic weighted Cohen κ, intraclass correlation coefficient, and Spearman rank correlation coefficient. Differences among models were analyzed using the Kruskal-Wallis test with the Dunn post hoc test. In addition, examination performance was evaluated based on total score, accuracy rate, and completion efficiency.

RESULTS: Interrater reliability analyses indicated moderate agreement between evaluators. The median correctness, clarity, and conciseness scores were as follows: 11.50 (IQR 10.50-12.00) for DeepSeek, 11.00 (IQR 10.50-12.00) for Qwen, 10.50 (IQR 9.50-11.50) for Spark-Desk, 10.00 (IQR 9.50-11.50) for WiseDiag, and 10.00 (IQR 9.00-11.50) for ChatGPT. The Kruskal-Wallis test indicated statistically significant differences among models (H=11.416; P<.05), with post hoc analysis showing a significant difference only between DeepSeek and ChatGPT (P<.05). In examination-based tasks, all models achieved passing performance, with accuracy rates ranging from 77% (77/100) to 93% (93/100). In terms of response completion, DeepSeek and ChatGPT completed all tasks in a single interaction, whereas other models required multiple interactions due to output interruptions.

CONCLUSIONS: LLMs showed relatively strong performance on structured knowledge and examination-based tasks but remained limited in complex oncology nursing scenarios requiring individualized assessment and dynamic clinical judgment. Their potential use may be most relevant to information retrieval, knowledge organization, and patient education. Because the correctness, clarity, and conciseness rubric showed only moderate interrater reliability, the case-based comparisons should be interpreted as preliminary signals rather than definitive evidence of between-model differences. LLM outputs should therefore be used as supportive information and interpreted alongside professional clinical judgment.

PMID:42497362 | DOI:10.2196/97802

JMIR Res Protoc. 2026 Jul 24;15:e86667. doi: 10.2196/86667.

ABSTRACT

BACKGROUND: Heart failure (HF) is a major public health problem associated with frequent hospitalizations, high mortality, and substantial health care costs. Self-care is fundamental to improving health outcomes; yet, self-care is commonly poor among patients with HF. SMS text messaging interventions may provide a simple, scalable, and accessible strategy to support HF self-care, particularly among older adults who may face barriers to using more complex digital health technologies. However, the efficacy of text messaging as a standalone intervention for patients with HF remains underexplored.

OBJECTIVE: This protocol paper describes the rationale and design of a pilot randomized controlled trial examining the feasibility, acceptability, and preliminary efficacy of an individually Tailored Text Messaging Intervention to Improve Self-Care in Adults with HF (Text4HF).

METHODS: This study is a single-site, stage I, parallel-group randomized controlled trial. Participants (n=30) are community-dwelling adults aged 50 years or older with stage C HF and suboptimal self-care, defined as a score of 3 or less on at least 2 items of the Self-Care of Heart Failure Index (SCHFI v7.2). Participants are randomized (1:1) to either a 12-week tailored text messaging intervention (Text4HF) plus usual care or usual care alone. Text messages are triggered based on patient responses to validated instruments assessing evidence-based, modifiable behavioral factors of HF self-care. Feasibility (recruitment and retention) and acceptability of the intervention are assessed as key process outcomes. The main exploratory patient-reported outcome is HF self-care (SCHFI v7.2). Other patient-reported outcomes include medication adherence, adherence to a heart-healthy diet, HF knowledge, health-related quality of life, self-efficacy, and health beliefs.

RESULTS: This study was funded in June 2022, and participant recruitment began in September 2024. A total of 26 participants have been enrolled and randomized to the intervention (n=13) and control (n=13) groups. Participants have a mean age of 60 (SD 6.6) years, 46% (12/26) are female, and 73% (19/26) identify as non-Hispanic Black. Half of the participants are individuals with reduced ejection fraction. Study completion is anticipated in June 2026.

CONCLUSIONS: This protocol describes an important step toward evaluating a scalable, low-cost text messaging intervention designed to improve self-care in patients with HF. Study findings will provide critical data on feasibility and acceptability to guide a future fully powered efficacy trial of Text4HF.

PMID:42497360 | DOI:10.2196/86667

Dent Med Probl. 2026 May-Jun;63(3):825-831. doi: 10.17219/dmp/217233.

ABSTRACT

BACKGROUND: Various parameters are used in cephalometric diagnosis to assess the sagittal discrepancy of the maxillary bases.

OBJECTIVES: The aim of this study was to assess the role of the horizontal and vertical dispersion of anthropometric landmarks used for plotting, and to assess the reliability of the selected cephalometric parameters.

MATERIAL AND METHODS: The material consisted of 24 randomly selected cephalometric radiographs. They were analyzed twice, 7 days apart, by 15 orthodontists. The horizontal and vertical dispersion (x, y) of individual anthropometric landmarks was assessed using the mean reference value, and the reliability of individual landmarks and measurements was assessed using the intraclass correlation coefficient (ICC(2.1)).

RESULTS: The ICC(2.1) for each landmark ranged from 0.9907 to 0.9998. The ICC(2.1) for individual sagittal discrepancy measurements averaged 0.9370 to 0.9842. The highest reliability was achieved for the ANB, W, Sar, Wits, Tau, and Yen measurements, respectively. The obtained results indicate excellent reliability in determining landmarks. The measurements of the selected parameters assessing the sagittal incongruence relationship between the maxilla and the mandible also demonstrated excellent reliability.

CONCLUSION: s The highest reliability in assessing the sagittal relationship between the maxilla and the mandible continues to be demonstrated by the ANB angle. The high and comparable values of the Sar, W, Tau, and Yen angles indicate the possibility of using these parameters interchangeably or complementarily in diagnosis and treatment planning, especially in borderline cases.

PMID:42497350 | DOI:10.17219/dmp/217233

JAMA Netw Open. 2026 Jul 1;9(7):e2622211. doi: 10.1001/jamanetworkopen.2026.22211.

ABSTRACT

IMPORTANCE: Pertussis, or whooping cough, can be life threatening in infants, yet the concept of severe pertussis remains poorly defined in the literature. Lack of standardization may impair research and public health interventions.

OBJECTIVE: To assess the variability in terminology and criteria used to define severe pertussis in the published literature.

EVIDENCE REVIEW: A systematic review of the literature drawn from PubMed and Web of Science databases was performed. Studies involving infants with pertussis that provided a definition for severe pertussis and published from database inception to April 2025 were included without language restrictions. Study characteristics and detailed definitions of severe pertussis were extracted. Variations in terminology and criteria used across definitions were described.

FINDINGS: Of the 914 unique studies identified, 133 underwent full-text review, and 78 were included in the study, encompassing 49 observational studies, 22 case reports, 3 case-control studies, and 4 reviews; no randomized clinical trials were included. Five different terms used to define severe pertussis were identified: severe (44 of 78 studies [56%]), malignant (12 of 78 studies [15%]), critical (9 of 78 studies [12%]), fatal (9 of 78 studies [12%]), and fulminant (4 of 78 studies [5%]). Across studies, 22 different criteria were used to define clinical severity, which were classified into 3 categories (ie, clinical, biological, and outcome). The most commonly reported criteria included respiratory failure (40 of 78 studies [51%]), pulmonary hypertension (30 of 78 studies [38%]), leukocytosis (28 of 78 studies [36%]), death (29 of 78 studies [37%]), and intensive care unit admission (29 of 78 studies [37%]).

CONCLUSIONS AND RELEVANCE: This systematic review revealed substantial heterogeneity in the definition of severe pertussis in the literature. A consensus-based definition of severe pertussis is urgently needed to improve the understanding of its pathophysiology and to enhance clinical management, clinical research, and public health decision-making.

PMID:42496978 | DOI:10.1001/jamanetworkopen.2026.22211

JAMA Netw Open. 2026 Jul 1;9(7):e2624984. doi: 10.1001/jamanetworkopen.2026.24984.

ABSTRACT

IMPORTANCE: Exclusive breastfeeding (EBF) during the postpartum hospital stay is associated with longer breastfeeding duration. Electronic health record (EHR) data can be used to uncover patterns in missed and inequitable breastfeeding care that may be associated with persistent breastfeeding disparities.

OBJECTIVES: To assess the association of documented postpartum in-hospital breastfeeding care with EBF and test differences in documented care by feeding intention and demographic and clinical characteristics.

DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study of EHR data from a single academic hospital network in Minnesota included 22 857 patients who intended to provide breastmilk and delivered singleton infants born at 37 weeks’ or more gestation between January 1, 2018, and December 31, 2022. Data preparation was completed between September 2023 and May 2024; analyses were completed between June and December 2025.

EXPOSURES: Ratio of the number of documented lactation support events per 8-hour nursing shift to the number recommended during the postpartum stay (breastfeeding support ratio [BSR]). Current guidelines recommend a BSR of 1.00 or more.

MAIN OUTCOMES AND MEASURES: Multivariable logistic regression with restricted cubic splines was used to estimate the probability of EBF during the hospital stay and to estimate the relative risk (RR) of a BSR less than 1.00.

RESULTS: The sample included 22 857 dyads (mean [SD] maternal age, 31.0 [5.1] years; mean [SD] gestational age, 39.4 [1.1] weeks), with feeding intentions of 91.1% EBF (n = 20 826) and 8.9% breastmilk and formula (n = 2031). There was a nonlinear positive association between BSR and the probability of EBF, with a probability of 0.49 (95% CI, 0.44-0.54) for a BSR of 0.00, a probability of 0.78 (95% CI, 0.76-0.80) for a BSR of 1.00, and a probability of 0.91 (95% CI, 0.90-0.92), with a plateau in the association above a BSR of 2.00. The positive association of BSR with EBF was weaker, with a higher RR of a BSR less than 1.00, among American Indian or Alaska Native patients (adjusted RR, 1.94; 95% CI, 1.26-2.62); Asian, Native Hawaiian, and Other Pacific Islander patients (adjusted RR, 2.35; 95% CI, 2.08-2.62); and Black or African American patients (adjusted RR, 1.83; 95% CI, 1.60-2.07) than among White patients. There were further disparities in documented breastfeeding support identified, with higher risk of a BSR less than 1.00, by breastfeeding intention (both breastmilk and formula: adjusted RR, 4.65; 95% CI, 4.25-5.05), need for an interpreter (adjusted RR, 1.52; 95% CI, 1.32-1.72), age younger than 25 years (adjusted RR, 1.33; 95% CI, 1.14-1.51), marital status (single: adjusted RR, 1.34; 95% CI, 1.21-1.48), health insurance type (public health insurance: adjusted RR, 1.25; 95% CI, 1.06-1.45), body mass index of 30 or more (adjusted RR, 1.40; 95% CI, 1.25-1.56), current tobacco smoking (adjusted RR, 2.09; 1.72-2.47), cesarean delivery (adjusted RR, 1.16; 95% CI, 1.04-1.28), gestational age of 37 to 38 weeks (adjusted RR, 1.26; 95% CI, 1.14-1.38), and low-birth-weight status (<2500 g; adjusted RR, 1.87; 95% CI, 1.42-2.32).

CONCLUSIONS AND RELEVANCE: This cross-sectional study found that, in a large EHR-based postpartum patient sample, the frequency of documented breastfeeding support was positively associated with EBF during the hospital stay, an early predictor of breastfeeding duration. However, there were numerous disparities in the level of support documented. More frequent in-hospital breastfeeding support, above currently recommended levels, could help reduce gaps in breastfeeding outcomes.

PMID:42496977 | DOI:10.1001/jamanetworkopen.2026.24984