Background: Young adults' extensive use of smartphones has resulted in several health concerns and one of which is Text Neck Syndrome. Prolonged neck flexion during smartphone use can lead to neck pain, disability and functional limitations. The study focused on determining the prevalence and knowledge regarding Text Neck Syndrome and identify predicting factors associated with the condition. Methods: A cross-sectional study was carried out among 240 undergraduate students selected using convenience method of sampling from four colleges in East Khasi Hills, Meghalaya. A standardized questionnaire with questions on demographics, participant behaviour and understanding of text neck syndrome was used to gather data. Two standardized tools neck disability index and the smartphone addiction scale-short version were used with prior permission to assess neck disability and smartphone addiction.8,9 Results: The results demonstrated that, prevalence of Text Neck Syndrome among the participants discovered to be 35.8% (95% CI:29.8%–42.3%) and 41.0% participants had smartphone addiction. Majority (71.7%) participants had adequate knowledge regarding Text Neck Syndrome and smartphone addiction was identified as a significant independent predictor of Text Neck Syndrome, with 2.2 times higher odds of developing the condition. Additionally, there was a significant positive correlation found between smartphone addiction and neck disability. Conclusions: Text Neck Syndrome is a prevalent health issue among undergraduate students in Meghalaya, affecting more than one-third of the study population. Although most of the participants had adequate knowledge regarding text neck syndrome, the occurrence of the syndrome suggests the need of targeted educational, ergonomic and behavioural interventions among young adults.
This cross-sectional study aimed to develop and preliminarily validate a machine learning model for preliminary forward head posture (FHP) screening and deploy the final model as an online tool. Among 825 university students, 625 comprised the development dataset (training set, n = 437; test set, n = 188), and 200 the exploratory external validation dataset. FHP was defined as a craniovertebral angle < 50°. Six machine learning models were compared through nested cross-validation. Restricted cubic splines and Shapley additive explanations analysis were used for exploratory association analysis and model interpretation, respectively. Random forest (RF) achieved the highest sensitivity in nested cross-validation (0.748, 95% CI 0.661–0.825) and was therefore selected as the final model based on the prespecified priority of reducing missed cases. In the external validation, RF achieved an AUC of 0.827 (0.751–0.896), sensitivity of 0.745 (0.615–0.865), specificity of 0.784 (0.715–0.845), and Brier score of 0.125 (0.097–0.154). Body mass index contributed most to model output and showed a significant nonlinear association with FHP (adjusted p = 0.017). The model showed moderate-to-good discrimination for FHP among university students and may offer a relatively accessible approach to preliminary FHP screening.
این مطالعه مقطعی با هدف توسعه و اعتبارسنجی اولیه یک مدل یادگیری ماشین برای غربالگری اولیه وضعیت سر به جلو (FHP) و پیاده‌سازی مدل نهایی به عنوان یک ابزار آنلاین انجام شد. از میان ۸۲۵ دانشجوی دانشگاه، ۶۲۵ نفر مجموعه داده توسعه (مجموعه آموزش، n = ۴۳۷؛ مجموعه آزمون، n = ۱۸۸) و ۲۰۰ نفر مجموعه داده اعتبارسنجی اکتشافی خارجی را تشکیل دادند. FHP به عنوان زاویه کرانیوورتبرال کمتر از ۵۰ درجه تعریف شد. شش مدل یادگیری ماشین از طریق اعتبارسنجی متقاطع تو در تو مقایسه شدند. برای تحلیل اکتشافی ارتباط و تفسیر مدل به ترتیب از اسپلاین‌های مکعبی محدود و تحلیل توضیحات افزایشی Shapley استفاده شد. مدل جنگل تصادفی (RF) بالاترین حساسیت را در اعتبارسنجی متقاطع تو در تو (۰.۷۴۸، ۹۵٪ CI: ۰.۶۶۱–۰.۸۲۵) به دست آورد و بر اساس اولویت از پیش تعیین‌شده برای کاهش موارد از دست رفته به عنوان مدل نهایی انتخاب شد. در اعتبارسنجی خارجی، RF به AUC برابر با ۰.۸۲۷ (۰.۷۵۱–۰.۸۹۶)، حساسیت ۰.۷۴۵ (۰.۶۱۵–۰.۸۶۵)، ویژگی ۰.۷۸۴ (۰.۷۱۵–۰.۸۴۵) و امتیاز Brier معادل ۰.۱۲۵ (۰.۰۹۷–۰.۱۵۴) دست یافت. شاخص توده بدنی بیشترین سهم را در خروجی مدل داشت و ارتباط غیرخطی معناداری با FHP نشان داد (p تعدیل‌شده = ۰.۰۱۷). مدل مذکور تمایز متوسط تا خوبی را برای FHP در میان دانشجویان دانشگاه نشان داد و ممکن است رویکردی نسبتاً در دسترس برای غربالگری اولیه FHP ارائه دهد.
