Tag: nevin manimala

JMIR Mhealth Uhealth. 2025 Jun 6;13:e58597. doi: 10.2196/58597.

ABSTRACT

BACKGROUND: Mobile phone apps powered by artificial intelligence (AI) have emerged as powerful tools to address mental health challenges faced by children.

OBJECTIVE: This study aimed to comprehensively review AI-driven apps for child mental health, focusing on their availability, quality, readability, characteristics, and functions.

METHODS: This study systematically analyzed AI-based mobile apps for child mental health. Quality was evaluated using the Mobile Application Rating Scale, which assessed various dimensions of app quality, including subjective quality, engagement, functionality, aesthetics, and information. An automatic readability index calculator was implemented to assess readability by using the count of words, syllables, and sentences to generate a score indicative of the reading difficulty level. Content analysis was conducted to examine the apps’ availability, characteristics, and functionality.

RESULTS: Out of 369 apps initially identified, 27 met the eligibility criteria for inclusion. The quality of the apps was assessed using Mobile Application Rating Scale, with an average score of 3.45 out of 5 (SD 0.5), indicating a need for quality improvement. The readability analysis revealed suboptimal scores, with an average grade level of 6.62 (SD 2.2) for in-app content and 9.93 (SD 2.6) for app store descriptions. These results, combined with a monotonous user interface, suggest that many apps lack a child-friendly design, potentially hindering their usability and engagement for young users. Content analysis categorized the apps into 3 functional groups-chatbot-based apps (15 apps), journal logging apps (9 apps), and psychotherapeutic treatment apps (3 apps). While 20 out of 27 apps (74%) used clinically validated technologies, rigorous clinical tests of the apps were often missing, with only 2 apps undergoing clinical trials. Of the 27 apps analyzed, only 7 (26%) were free to use, while the majority, 20 apps, required a subscription or one-time payment. Among the paid apps, the average cost was US $20.16 per month, which may pose a financial barrier and limit accessibility for some users, particularly those from lower-income households.

CONCLUSIONS: AI-based mental health apps hold significant potential to address the unique challenges of child mental health but face critical limitations in design, accessibility, and validation. To fully realize their benefits, future research and development should focus on integrating child-centric design principles, ensuring affordability, and prioritizing rigorous clinical testing. These efforts are essential to harness the power of AI technologies in creating equitable, effective, and engaging solutions for improving child mental health outcomes.

PMID:40479582 | DOI:10.2196/58597

J Med Internet Res. 2025 Jun 6;27:e73336. doi: 10.2196/73336.

ABSTRACT

BACKGROUND: The proliferation of health-related content on social media platforms has changed the way people access and interpret information about cosmetic medicine. TikTok (ByteDance) has become an important platform for sharing breast enhancement content, yet little is known about the quality, credibility, and impact of such information on user perceptions and decision-making.

OBJECTIVE: This paper aims to analyze the characteristics of breast enhancement videos, including uploader demographics, product details, promotional claims, and user engagements, to better understand the nature of the claims and products encountered by users.

METHODS: We conducted a cross-sectional content analysis of the top 150 most-liked breast enhancement videos via TikTok’s web interface. The videos were coded according to the uploader’s traits (gender expression and account type), product details (type and scientific evidence), and promotional strategies (testimonials and sponsorship disclosures). Engagement metrics (likes and shares) were recorded, and nonparametric tests (Mann-Whitney U test) were used to compare the engagement between licensed physicians and uncertified content creator uploaders. Descriptive statistics were calculated for all the variables.

RESULTS: Overall, 85 videos were included in the final analysis, with most uploaders presenting a feminine gender expression (59/85, 69.4%) and using uncertified content creator accounts (59/85, 69.4%). The most promoted product types were breast enhancement creams or oils (32/85, 37.6%) and breast implants (22/85, 25.9%). Most videos (71/85, 83.5%) depicted the products positively; however, most videos (78/85, 91.8%) provided no scientific evidence of the product’s efficacy. Engagement metrics revealed that videos by licensed physicians received significantly higher thumbs up (median 9761, IQR 4975-19,492) than uncertified content creator uploaders (median 701, IQR 280-2604; P=.002). Only one video (1.2%) of the 85 videos included a “before and after” visual component, and most videos (75/85, 88.2%) omitted product purchasing details. Sponsorship disclosures were absent in most of posts (79/85, 92.9%).

CONCLUSIONS: TikTok’s short video format fosters widespread and rapid dissemination of breast enhancement information, representing a key strength in democratizing health communication. Its user-friendly interface and visual appeal also offer a valuable avenue for medical professionals to engage audiences more dynamically. However, the lack of rigorous content checks can amplify misleading or unverified claims. To address these weaknesses, implementing dual-mode content review could be essential for maximizing TikTok’s capacity to support informed public health decision-making.

PMID:40479581 | DOI:10.2196/73336

Healthc Manage Forum. 2025 Jun 6:8404704251343260. doi: 10.1177/08404704251343260. Online ahead of print.

ABSTRACT

Our Canadian multi-site academic health sciences centre uses a standardized process to review critical patient safety incidents and develop recommendations to prevent incident reoccurrence. We recognized an opportunity to enhance recommendation development by integrating the Hierarchy of Intervention Effectiveness (HIE), a human factors framework, into the incident review process. This project aimed to increase the proportion of system-focused recommendations from critical incident reviews from 16 to 30% over 16 months. A multi-intervention strategy included (1) standardizing the incident analysis review template; (2) earmarking time for recommendation development during reviews; (3) providing participants with just-in-time education and tools; and (4) initiating HIE-based recommendation classification during incident reviews. Statistical process control p-Chart analysis showed an increase in system-focused recommendations from 16 to 30% over 16 months. The HIE promotes system-level change to prevent critical incidents, which other organizations may benefit from incorporating in their patient safety reviews.

PMID:40479578 | DOI:10.1177/08404704251343260

J Am Acad Orthop Surg. 2025 Jun 15;33(12):e657-e664. doi: 10.5435/JAAOS-D-23-01243. Epub 2024 Oct 29.

ABSTRACT

INTRODUCTION: Total hip arthroplasty (THA) is a treatment used for both elective (eg, osteoarthritis) and nonelective (eg, fracture) indications. Patients undergoing nonelective THA may not be able to undergo the same preoperative optimization protocols as those undergoing elective THA. We aimed to determine differences in 30-day, 90-day, and 1-year surgical site infection (SSI) rates; 90-day and 1-year periprosthetic joint infection (PJI)-related revision; and 90-day and 1-year PJI-related surgery (ie, revision or irrigation and débridement) between nonelective and elective THA status.

METHOD: This retrospective cohort study using the Medicare Limited Data Set included fee-for-service Medicare beneficiaries aged 65+ years who underwent inpatient primary THA in 2017 to 2020. Propensity score matching (1:5, nonelective: elective) was used. We assessed differences in surgical site infection (SSI), periprosthetic joint infection (PJI) outcomes by nonelective versus elective surgery status using mixed-effects logistic regression models, reporting adjusted odds ratios (OR) and 95% confidence intervals (CI).

RESULTS: From a total of 433,326 patients, 88,940 (19,094 nonelective; 69,846 elective) were successfully matched. Nonelective surgery status was associated with markedly higher odds of 30-day SSI (OR 1.55, 95% CI 1.25 to 1.92, P < 0.001), 90-day SSI (OR 1.53, 95% CI 1.30 to 1.78, P < 0.001), and 1-year SSI (OR 1.41, 95% CI 1.25 to 1.59, P < 0.001). Nonelective status was also associated with higher odds of 1-year PJI-related revision (OR 1.33, 95% CI 1.08-1.63, P = 0.006) but not 90-day PJI-related revision. Similarly, nonelective status was associated with higher odds of 1-year PJI-related surgery (OR 1.33, 95% CI 1.09 to 1.62, P = 0.004) but not 90-day PJI-related surgery.

CONCLUSION: Nonelective THA status was an independent risk factor for SSI throughout the first postoperative year and for 1-year PJI-related revision and PJI-related surgery. Additional research is necessary to elucidate the etiology of observed differences in infection risk between patients undergoing nonelective and elective THA and to define strategies to mitigate this difference in infection risk.

PMID:40479559 | DOI:10.5435/JAAOS-D-23-01243

J Am Acad Orthop Surg. 2025 May 9;33(12):655-662. doi: 10.5435/JAAOS-D-25-00160.

ABSTRACT

BACKGROUND: Metallic implants are widely used in orthopaedic surgery. These implants may have carcinogenic properties, but the incidence of associated malignancies appears to be low, and to date, only case reports and small case series have been reported. We describe a series of patients with soft-tissue sarcoma adjacent to orthopaedic implant.

METHODS: Cases of soft-tissue sarcomas treated at our institution were reviewed to identify tumors arising next to orthopaedic implant. We collected diagnostic, therapeutic, surgical, and outcome data and conducted genetic testing on the implant-associated tumors and control tumors.

RESULTS: We identified 4 cases, all of which were high-grade sclerosing rhabdomyosarcoma. Median age at diagnosis was 50 years (range: 35 to 58 years). Three tumors were in the lower extremity following internal fixation of the tibia and/or fibula, whereas the fourth was posterior to spinal implant. Mean time from implant placement to diagnosis was 19.0 years (range: 10.9 to 24.3 years). Three patients underwent wide surgical resection, whereas one had metastatic disease at diagnosis and declined surgery. All were treated with chemotherapy and radiation. Genetic testing revealed a MYOD1 mutation in all four tumors. The tumor mutational burden and fraction of genome altered were slightly higher in the control tumors than in the implant-adjacent tumors, although the differences were not statistically significant. Median follow-up was 1.7 years (range: 0.8 to 2.6 years). Of the three patients with localized disease, two had no evidence of disease at latest follow-up and one died of unknown cause at 2.6 years. The patient with metastatic disease died of disease at 0.8 years.

CONCLUSIONS: We found no genetic differences between implant-associated and non-implant-associated rhabdomyosarcomas. Further investigation is needed to understand the contribution of metallic implants to tumorigenesis. Physicians should be aware of this diagnosis when a new mass arises in a patient with long-standing orthopaedic implants.

PMID:40479555 | DOI:10.5435/JAAOS-D-25-00160

ATS Sch. 2025 Jun 6. doi: 10.34197/ats-scholar.2024-0134OC. Online ahead of print.

ABSTRACT

Background: Interprofessional teaching (IPT) has the potential to promote teamwork and collaborative patient care, but few studies have explored physician attitudes about the role of nonphysician clinical teachers in graduate medical education. Objective: This study aimed to elucidate critical care attending physician perspectives about the role of nurses, pharmacists, and respiratory therapists in teaching medical residents. Methods: Using a concurrent mixed methods approach, surveys and focus groups were administered to attendings in an urban tertiary academic medical center. Survey data were analyzed with descriptive statistics; focus group data were analyzed using the Framework method of content analysis. Results: Of attendings surveyed, 23/26 (88%) responded. Attendings reported positive attitudes about IPT; highly cited benefits included capitalizing on the unique expertise held by interprofessional providers (21/22, 95%), modeling respectful interprofessional relationships (21/22, 95%), and promoting collaborative patient care (20/22, 91%). Ten attendings participated in focus groups. Qualitative analysis revealed four major themes: overall low rates of IPT that vary by profession, potential role of attending as facilitator of IPT, multiple interpersonal and environmental characteristics that influence IPT, and impacts of IPT on education, patient care, and teamwork. Conclusion: Study results suggest that attending physicians are enthusiastic about the concept of IPT and their potential role in its promotion.

PMID:40479547 | DOI:10.34197/ats-scholar.2024-0134OC

Cancer. 2025 Jun 15;131(12):e35926. doi: 10.1002/cncr.35926.

ABSTRACT

BACKGROUND: The disproportionate burden of obesity among Black women may contribute to disparities in breast cancer survival; yet, associations of body mass index (BMI), a proxy for total adiposity, are inconsistent.

METHODS: To examine racial/ethnic differences in body composition and evaluate associations with breast cancer-specific and all-cause mortality, this study identified 3898 women 18 to <90 years old, diagnosed in 2005-2019 with stage II-III breast cancer at Kaiser Permanente Northern California. The authors measured subcutaneous, visceral, and intermuscular adipose tissue area from computed tomography scans.

RESULTS: Body composition differed by race: compared to other race/ethnicity groups, Black women had higher skeletal muscle and subcutaneous adipose, but lower visceral adipose tissues, whereas Asian/Pacific Islander women had lower intermuscular and subcutaneous adipose tissue. BMI was not significantly associated with mortality in any group. Among Black women, higher subcutaneous adipose tissue was associated with breast cancer-specific mortality (hazard ratio [HR], 1.24; 95% confidence interval [CI], 1.02-1.52) and all adipose tissue measures were associated with increased all-cause mortality (intermuscular HR, 1.26; 95% CI, 1.09-1.46; subcutaneous HR, 1.25; 95% CI, 1.05-1.48; and visceral HR, 1.32; 95% CI, 1.03-1.68, respectively). By contrast, only increased intermuscular adipose tissue was associated with all-cause mortality among White women (HR, 1.08; 95% CI, 1.00-1.16), with null associations for Hispanic and Asian/Pacific Islander women.

CONCLUSIONS: BMI obscures variation in body composition, particularly for Black women, who have more subcutaneous adipose and skeletal muscle but less visceral adipose tissue at higher BMIs. These findings from routine imaging highlight opportunities for tailored lifestyle interventions to improve survivorship and mitigate disparities.

PMID:40479498 | DOI:10.1002/cncr.35926

Int J Surg. 2025 Jun 5. doi: 10.1097/JS9.0000000000002641. Online ahead of print.

ABSTRACT

INTRODUCTION: Due to the high propensity for occult lymph node metastasis (OLNM) in Early-stage oral tongue squamous cell carcinoma (OTSCC), elective neck dissection has become standard practice for many patients with clinically node-negative (cT1-2 N0) disease, which may lead to overtreatment in some patients. Hence, accurate identification and prediction of OLNM are of great significance.

AIM: This study aimed to develop and validate an explainable machine learning (ML) model to predict OLNM in OTSCC.

METHODS: A total of 678 Early-stage OTSCC patients from multiple centers were enrolled and randomly classified into the derivation and external validation cohorts. The variables considered in this study primarily included clinicopathological characteristics associated with the occurrence of OLNM in OTSCC. Feature selection utilized multivariate logistic regression analysis and Lasso regression analysis. Meanwhile, 6 ML algorithms were employed to develop an OLNM diagnostic model, assessed with area under the curve (AUC), calibration curve, decision curve analysis (DCA), sensitivity, specificity, and validation cohorts. Moreover, the Shapley Additive exPlanations (SHAP) method was applied to rank the feature importance and interpret the final model.

RESULTS: In this study, 192 patients (34.7%) developed OLNM in the derivation cohort, while 38 patients (30.6%) developed OLNM in the external validation cohort. Through feature selection, 9 clinicopathological variables were identified as independent predictive factors for OLNM, and six ML models were developed based on these factors. Among the six evaluated ML models, the Random Forest (RF) model achieved the highest AUC (0.941, 95% CI: 0.907-0.975) for internal validation. External validation further confirmed the RF model’s effectiveness, yielding an AUC of 0.917 (95% CI: 0.868-0.967). The calibration curves also demonstrated a high level of concordance between the anticipated risk and the observed risk of the RF model. Additionally, this study also compared the RF model with the currently accepted traditional statistical methods, including depth of invasion (DOI) and tumor budding (TB), demonstrating superior prediction performance and greater clinical application value. Ultimately, an online computing platform (https://prediction-model-for-olnm.streamlit.app/) for this RF model is freely available to both clinicians and patients.

CONCLUSION: This study innovatively utilized 9 easily obtained clinicopathological features to construct an explainable RF model, providing a practical and reliable tool for predicting OLNM in Early-stage OTSCC. More importantly, it also provided interpretable results, thus overcoming the “impenetrable black box” of conventional ML models.

PMID:40479496 | DOI:10.1097/JS9.0000000000002641

J Med Internet Res. 2025 Jun 6;27:e67201. doi: 10.2196/67201.

ABSTRACT

BACKGROUND: Sepsis is a severe syndrome of organ dysfunction caused by infection; it has high heterogeneity and high in-hospital mortality, representing a grim clinical challenge for precision medicine in critical care.

OBJECTIVE: We aimed to extract reported sepsis biomarkers to provide users with comprehensive biomedical information and integrate retrieval augmented generation (RAG) and prompt engineering to enhance the accuracy, stability, and interpretability of clinical decisions recommended by large language models (LLMs).

METHODS: To address the challenge, we established and updated the first knowledge-enhanced platform, MetaSepsisKnowHub, comprising 427 sepsis biomarkers and 423 studies, aiming to systematically collect and annotate sepsis biomarkers to guide personalized clinical decision-making in the diagnosis and treatment of human sepsis. We curated a tailored LLM framework incorporating RAG and prompt engineering and incorporated 2 performance evaluation scales: the System Usability Scale and the Net Promoter Score.

RESULTS: The overall quantitative ratings of expert-reviewed clinical recommendations based on RAG surpassed baseline responses generated by 4 LLMs and showed a statistically significant improvement in textual questions (GPT-4: mean 75.79, SD 7.11 vs mean 81.59, SD 9.87; P=.02; GPT-4o: mean 70.36, SD 7.63 vs mean 77.98, SD 13.26; P=.02; Qwen2.5-instruct: mean 77.08 SD 3.75 vs mean 85.46, SD 7.27; P<.001; and DeepSeek-R1: mean 77.67, SD 3.66 vs mean 86.42, SD 8.56; P<.001), but no significant statistical differences could be measured in clinical scenarios. The RAG assessment score comparing RAG-based responses and expert-provided benchmark answers illustrated prominent factual correctness, accuracy, and knowledge recall compared to the baseline responses. After use, the average the System Usability Scale score was 82.20 (SD 14.17) and the Net Promoter Score was 72, demonstrating high user satisfaction and loyalty.

CONCLUSIONS: We highlight the pioneering MetaSepsisKnowHub platform, and we show that combining MetaSepsisKnowHub with RAG can minimize limitations on precision and maximize the breadth of LLMs to shorten the bench-to-bedside distance, serving as a knowledge-enhanced paradigm for future application of artificial intelligence in critical care medicine.

PMID:40478618 | DOI:10.2196/67201

Cogn Sci. 2025 Jun;49(6):e70073. doi: 10.1111/cogs.70073.

ABSTRACT

Previous research suggests that statistical learning enhances memory for self-related information at the individual level and that individuals exhibit better memory for partner-related items than they do for irrelevant items in joint contexts (i.e., the joint memory effect, JME). However, whether statistical learning improves memory for partner-related information in joint contexts remains unclear. This study investigated memory performance for partner-related words when higher level statistical regularities were embedded in word streams during a joint memory task. Participants performed a word categorization task, followed by a surprise free recall task across four experiments. Experiment 1 replicated the JME, revealing improved memory for partner-related items than for irrelevant items when using Chinese words with increased repetition. Experiment 2 embedded semantic regularities within partners’ word streams; Experiment 3a employed regularities based on non-adjacent fixed temporal positions; and Experiment 3b employed regularities based on adjacent fixed temporal positions. Results showed that the JME was enhanced only when semantic regularities were present (Experiment 2) and not with temporal positional rules (Experiments 3a and 3b). These findings suggest a hierarchical structure of co-representation and show that co-represented statistical regularities facilitate the processing of partner-related words, but only when the regularities align with partners’ intentions. This study advances our understanding of co-representation in joint action by highlighting its hierarchical nature, and the top-down interaction between structural levels.

PMID:40478612 | DOI:10.1111/cogs.70073