A Machine Learning Prediction Model of Adult Obstructive Sleep Apnea Based on Systematically Evaluated Common Clinical Biochemical Indicators.

Objective: Obstructive sleep apnea (OSA) is a common and potentially fatal sleep disorder. The purpose of this study was to construct an objective and easy-to-promote model based on common clinical biochemical indicators and demographic data for OSA screening. Methods: The study collected the clinical data of patients who were referred to the Sleep Medicine Center of the Second Affiliated Hospital of Fujian Medical University from December 1, 2020, to July 31, 2023, including data for demographics, polysomnography (PSG), and 30 biochemical indicators. Univariate and multivariate analyses were performed to compare the differences between groups, and the Boruta method was used to analyze the importance of the predictors. We selected and compared 10 predictors using 4 machine learning algorithms which were "Gaussian Naive Bayes (GNB)", "Support Vector Machine (SVM)", "K Neighbors Classifier (KNN)", and "Logistic Regression (LR)". Finally, the optimal algorithm was selected to construct the final prediction model. Results: Among all the predictors of OSA, body mass index (BMI) showed the best predictive efficacy with an area under the receiver operating characteristic curve (AUC) = 0.699; among the predictors of biochemical indicators, triglyceride-glucose (TyG) index represented the best predictive performance (AUC = 0.656). The LR algorithm outperformed the 4 established machine learning (ML) algorithms, with an AUC (F1 score) of 0.794 (0.841), 0.777 (0.827), and 0.732 (0.788) in the training, validation, and testing cohorts, respectively. Conclusion: We have constructed an efficient OSA screening tool. The introduction of biochemical indicators in ML-based prediction models can provide a reference for clinicians in determining whether patients with suspected OSA need PSG.

Suicide death, suicidal ideation and suicide attempt in patients with diabetes: A systematic review and meta-analysis.

AIMS: Diabetes has been indicated to be a risk factor for suicide. We aim to estimate the prevalence of suicide in patients with diabetes. DESIGN: A meta-analysis using PRISMA methodology was adopted to examine the incidence of suicide in diabetic patients. DATA SOURCES: From inception to October 2022, three online databases (PubMed, China National Knowledge Infrastructure and Web of Science) were used to search studies. REVIEW METHODS: We used random-effects model to analysis. And our primary outcome was the incidence of suicide death per 100 person-years, and other outcomes were prevalence of suicidal ideation and suicide attempt. To explore the sources of heterogeneity in our study, we performed subgroup and meta-regression analyses. RESULTS: The suicide death rate in diabetic patients was 0.027 per 100 person-years, with a higher rate for Type 1 Diabetes Mellitus compared to Type 2 Diabetes Mellitus. The prevalence of suicidal ideation in diabetes patients was 0.175, with a higher prevalence in Type 1 Diabetes Mellitus compared to Type 2 Diabetes Mellitus. The prevalence of suicide attempts in diabetes patients was 0.033, indicating a higher rate for Type 2 Diabetes Mellitus compared to Type 1 Diabetes Mellitus. CONCLUSIONS: The results indicate a high rate of suicide among people with diabetes, and this study identifies populations and regions at high risk for suicide. Our review emphasizes interventions in mental health and the improvement of suicide prevention programmes. IMPACT: The study investigated suicide death, suicidal ideation and suicide attempt in diabetic individuals. Suicide rates are elevated among diabetic patients, and various patient groups face distinct suicide risks. It is important to prioritize the mental well-being of diabetic individuals and enhance interventions, including personalized approaches, to inform public health efforts aimed at preventing and addressing suicide among diabetic patients. PATIENT OR PUBLIC CONTRIBUTION: No patient or public involvement.

LC-MS/MS platform-based serum untargeted screening reveals the diagnostic biomarker panel and molecular mechanism of breast cancer.

BACKGROUND: Breast cancer (BC), the most common form of malignant cancer affecting women worldwide, was characterized by heterogeneous metabolic disorder and lack of effective biomarkers for diagnosis. The purpose of this study is to search for reliable metabolite biomarkers of BC as well as triple-negative breast cancer (TNBC) using serum metabolomics approach. METHODS: In this study, an untargeted metabolomics technique based on ultra-high performance liquid chromatography combined with mass spectrometry (UHPLC-MS) was utilized to investigate the differences in serum metabolic profile between the BC group (n = 53) and non-BC group (n = 57), as well as between TNBC patients (n = 23) and non-TNBC subjects (n = 30). The multivariate data analysis, determination of the fold change and the Mann-Whitney U test were used to screen out the differential metabolites. Additionally, machine learning methods including receiver operating curve analysis and logistic regression analysis were conducted to establish diagnostic biomarker panels. RESULTS: There were 36 metabolites found to be significantly different between BC and non-BC groups, and 12 metabolites discovered to be significantly different between TNBC and non-TNBC patients. Results also showed that four metabolites, including N-acetyl-D-tryptophan, 2-arachidonoylglycerol, pipecolic acid and oxoglutaric acid, were considered as vital biomarkers for the diagnosis of BC and non-BC with an area under the curve (AUC) of 0.995. Another two-metabolite panel of N-acetyl-D-tryptophan and 2-arachidonoylglycerol was discovered to discriminate TNBC from non-TNBC and produced an AUC of 0.965. CONCLUSION: This study demonstrated that serum metabolomics can be used to identify BC specifically and identified promising serum metabolic markers for TNBC diagnosis.

Prediction Models for Sleep Quality Among College Students During the COVID-19 Outbreak: Cross-sectional Study Based on the Internet New Media.

BACKGROUND: COVID-19 has been reported to affect the sleep quality of Chinese residents; however, the epidemic's effects on the sleep quality of college students during closed-loop management remain unclear, and a screening tool is lacking. OBJECTIVE: This study aimed to understand the sleep quality of college students in Fujian Province during the epidemic and determine sensitive variables, in order to develop an efficient prediction model for the early screening of sleep problems in college students. METHODS: From April 5 to 16, 2022, a cross-sectional internet-based survey was conducted. The Pittsburgh Sleep Quality Index (PSQI) scale, a self-designed general data questionnaire, and the sleep quality influencing factor questionnaire were used to understand the sleep quality of respondents in the previous month. A chi-square test and a multivariate unconditioned logistic regression analysis were performed, and influencing factors obtained were applied to develop prediction models. The data were divided into a training-testing set (n=14,451, 70%) and an independent validation set (n=6194, 30%) by stratified sampling. Four models using logistic regression, an artificial neural network, random forest, and naïve Bayes were developed and validated. RESULTS: In total, 20,645 subjects were included in this survey, with a mean global PSQI score of 6.02 (SD 3.112). The sleep disturbance rate was 28.9% (n=5972, defined as a global PSQI score >7 points). A total of 11 variables related to sleep quality were taken as parameters of the prediction models, including age, gender, residence, specialty, respiratory history, coffee consumption, stay up, long hours on the internet, sudden changes, fears of infection, and impatient closed-loop management. Among the generated models, the artificial neural network model proved to be the best, with an area under curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 0.713, 73.52%, 25.51%, 92.58%, 57.71%, and 75.79%, respectively. It is noteworthy that the logistic regression, random forest, and naive Bayes models achieved high specificities of 94.41%, 94.77%, and 86.40%, respectively. CONCLUSIONS: The COVID-19 containment measures affected the sleep quality of college students on multiple levels, indicating that it is desiderate to provide targeted university management and social support. The artificial neural network model has presented excellent predictive efficiency and is favorable for implementing measures earlier in order to improve present conditions.

Insulin injection knowledge, attitude and behaviour of nurses: A cross-sectional study in Guangdong Province.

AIM: To understand the insulin injection knowledge, attitude and behaviour of nurses and their influencing factors in Guangdong Province. DESIGN: Cross-sectional study. METHODS: A total of 19,853 nurses from 82 hospitals in 15 cities in Guangdong, China, participated in this study. The scores of the nurses' insulin injection knowledge, attitude and behaviour were determined through a questionnaire, and multivariate regression analysis was used to evaluate the influencing factors of insulin injection in different dimensions. STROBE. RESULTS: Among all nurses involved in this study, 22.3% of nurses had good knowledge, 75.9% of nurses had good attitude and 92.7% of nurses had good behaviour. Pearson's correlation analysis showed that knowledge, attitude scores and behaviour scores were significantly correlated. The influencing factors of knowledge, attitude and behaviour included gender, age, education, nurse level, work experience, type of ward, diabetes nursing certification, position held and most recent insulin administration.

Prevalence and related factors of peripheral arterial disease in diabetes mellitus inpatients: a cross-sectional study in China.

Peripheral arterialdisease (PAD) can result in diabetic foot ulcers, gangrene, and even amputation. Since most cases of PAD in diabetic patients are associated with peripheral neuropathy, the symptoms of vascular disease are easily concealed by the symptoms of neuropathy and are ignored by people, so it is critical for health care providers to screen PAD for the diabetes patients. This study was carried out to identify theprevalence and related factors of PAD in diabetes mellitus inpatients. This was a cross-sectional observational study. A total of 855 patients were enrolled in the study from December 2018 to December 2019. The patients were divided into a non-PAD group (ABI = 0.9-1.3) and a PAD group (ABI <0.9). Logistic multivariate regression analysis showed that age, LDL-C, dorsalis pedis artery pulsation (left foot), and sensory-current threshold (right foot) were related factors for peripheral arterial disease. Patients who are older and have a higher LDL-C level, abnormal dorsal foot pulse, and abnormal sensory-current threshold must be vigilant, and receive early screening for PAD diagnosis and treatment to avoid a malignant outcome. In clinical work, medical staff should actively apply PAD screening to diabetic patients, identify risk factors as early as possible, conduct early interventions, reduce the risk of PAD in patients, and avoid the occurrence of adverse outcomes.

Diagnostic value of autofluorescence laryngoscope in early laryngeal carcinoma and precancerous lesions: A systematic review and meta-analysis.

OBJECTIVE: We aim to evaluate the diagnostic value of autofluorescence laryngoscope (AFL) in early laryngeal carcinoma and precancerous lesions. aWe also assess the value of AFL in diagnosis of early laryngeal carcinoma and precancerous lesions in comparison with that of white light laryngoscope (WL). METHODS: The databases consisting of PubMed, Cochrane Library, Web of science and CNKI were systematically searched to find pertinent literatures of AFL in diagnosing early laryngeal carcinoma and precancerous lesions. We made a quality evaluation of every study we included using the modified Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivities, specificities were calculated using Meta-Disc 1.4. And we estimated the summary receiver operating characteristic curves (SROC) and area under the curves (AUC). RESULTS: We finally included 23 studies. The results of AFL in diagnosing early laryngeal carcinoma and precancerous lesions showed higher sensitivity of 0.91 (95%CI: 0.89-0.93; χ²=43.78, p = 0.0025) and specificity of 0.80 (95%CI: 0.77-0.82; χ²=130.64, p = 0.000), and the weighted AUC of AFL was 0.948 ± 0.013 (95%CI: 0.921-0.974) and the diagnostic accuracy (Q*) was 0.887 ± 0.018. The sensitivity and specificity of WL were 0.74 (95%CI: 0.70-0.77; χ²=52.40, p = 0.000) and 0.89 (95%CI: 0.87-0.90; χ²=299.22, p = 0.000), and the weighted AUC of WL was 0.835 ± 0.029 (95%CI: 0.777-0.892) and the diagnostic accuracy (Q*) was 0.767 ± 0.027. CONCLUSION: The meta-analysis and systematic review suggested that AFL had high diagnostic value in early laryngeal carcinoma and precancerous lesions, and its diagnostic value was higher than that of WL. These results indicated that AFL can provide good guidance for the early detection of laryngeal carcinoma and precancerous lesions.

Effects of a nurse led web-based transitional care program on the glycemic control and quality of life post hospital discharge in patients with type 2 diabetes: A randomized controlled trial.

BACKGROUND: Individuals with type 2 diabetes have a heightened risk of developing serious complications post hospital discharge. Web-based transitional care is a promising intervention to improve the glycemic control and quality of life of this patient group; however, whether web-based transitional care can improve the glycemic control and quality of life of this group remains unknown. Further, the mechanisms underlying the relationships between the intervention and both glycemic control and quality of life have not been fully explored. OBJECTIVES: The aims of this study were to develop a web-based transitional care program and evaluate its effects on the glycemic control and quality of life of Chinese patients with type 2 diabetes and to explore the mediating roles of self-efficacy and treatment adherence. DESIGN: Randomized controlled trial. SETTINGS AND PARTICIPANTS: This study was conducted in a large regional hospital in Guangzhou City, China. Patients diagnosed with type 2 diabetes were included. METHODS: A total of 116 eligible participants were randomly assigned to receive either the 3-month web-based transitional care program or usual care. Assessments of hemoglobin A1c (HbA1c), self-efficacy, treatment adherence, and quality of life were conducted at baseline and at 3 months. Analysis followed the intention-to-treat principle. A generalized estimating equation was used to determine intervention effects on HbA1c and quality of life. Path analysis was used to assess the mediation of these effects by changes in self-efficacy and treatment adherence during the intervention. RESULTS: Participants in the intervention group had significantly greater improvements in HbA1c (ß = 2.87; p < 0.01) and quality of life (ß = 7.69; p < 0.01) compared with the control group. The relationships between the intervention and both glycemic control and quality of life were significantly mediated by improved self-efficacy (indirect effect: ß = 0.18, p < 0.05) and improved treatment adherence (indirect effect: ß = 0.17, p < 0.05); overall, the model explained 52.5% of the variance in HbA1c and 34.2% of the variance in quality of life. CONCLUSIONS: Our study identified beneficial effects of a web-based transitional care program on glycemic control and quality of life post hospital discharge in people with type 2 diabetes, and the underlying mediating mechanisms. The effectiveness and feasibility of this web-based intervention program suggests that its application should be promoted in community settings to reduce poor outcomes in people with type 2 diabetes. Tweetable abstract: The web-based transitional care program can improve patients' glycemic control and quality of life. Registration number: ChiCTR2000035603.

Clinical application analysis of continuing nursing in nursing service for diabetic patients.

The research is to establish a Continuing Nursing Project after discharge which conforming to the actual conditions of our country and explore whether such Continuing Nursing Project could effectively improve therapy compliance and blood glucose control of diabetic patients. METHODS: mainly analyzing pathological mechanisms of diabetic patients and exploring the clinical effect and the complication after implementing Continuing Nursing to patients. RESULTS: after implementing Continuing Nursing, the diabetic patients could be better at controlling their diet, the drug usage rate and exercise rate have been improved significantly, complication rate have been decreased and the clinical effect is remarkable. CONCLUSION: the application of Continuing Nursing in the nursing service for diabetic patients, which could effectively improve living quality and clinical symptoms of patients, deserves to be popularized.

[Dexamethasone acetate microemulsions: formulation and effect on skin permeability].

The present project was designed to optimize the microemulsion (ME) formulation of oil in water (O/W) for dexamethasone acetate (DA), and examine its impact on DA percutaneous permeation. The saturated solubility of DA in different oils, surfactants and co-surfactants was tested. The ratio of surfactant to co-surfactant was selected by constructing pseudo three phase diagrams to investigate the maximal microemulsion area. In vitro permeation studies of DA from microemulsion and suspension were performed to optimize the formulation further. Differential scanning calorimetry(DSC) and attenuated total reflection flourier transformed infrared spectroscopy (ATR-FTIR) were performed to investigate the mechanism of microemulsion action on skin. The optimized formulation was composed of oleic acid/Labrasol/propylene glycol/water with 8/45/15/32 (w/w), and the DA loading was 0.75% (w/w). The permeation enhancement of microemusion was 6.00-fold as that of suspension, and the DA from microemulsion retained in the skin was 4.79-fold as that of suspension. DSC and ATR-FTIR results suggested that microemulsion could affect the intercellular lipid lamellae and keratin of the stratum corneum. The barrier function of stratum corneum was disordered by the microemulsion so that the dermal drug delivery was enhanced. Therefore, the optimized microemulsion enhanced DA percutaneous permeation significantly through the interaction of microemulsion with skin, microemulsion is a promising approach for DA percutaneous delivery.

Web-based telemedicine for management of type 2 diabetes through glucose uploads: a randomized controlled trial.

AIMS: To evaluate the feasibility and effectiveness of a telemedicine system based on internet in the follow-up of patients with type 2 diabetes mellitus (T2DM). METHODS: A prospective randomized telemedicine study with two parallel groups was designed. 114 patients diagnosed T2DM were randomly divided into telemedicine group and traditional face-to-face visit group as control. 57 cases were included for each group. 108 patients completed the trial, in which 53 cases in telemedicine group and 55 cases in control group. Patients in telemedicine group were taught to use telemedicine software to upload their blood glucose and other metabolic information at home at least every 2 weeks, and the researchers gave proper advices according to patients' key behaviors. The telemedicine interval is 3 months. RESULTS: Compared to control group, telemedicine group exhibited better HbA1c and fasting blood glucose controlling (P < 0.05). Moreover, telemedicine intervention decreased hypoglycemia risk (P = 0.044), and contributed to levels of HbA1c less than 7% which is the target of our study (P = 0.049). CONCLUSIONS: Telemedicine system can provide a tighter glycemic control for the treatment of T2DM patients, especially in cases with difficulties to access to the medical centre.