Machine learning for the prediction of atherosclerotic cardiovascular disease during 3-year follow up in Chinese type 2 diabetes mellitus patients.

AIMS/INTRODUCTION: Clinical guidelines for the management of individuals with type 2 diabetes mellitus endorse the systematic assessment of atherosclerotic cardiovascular disease risk for early interventions. In this study, we aimed to develop machine learning models to predict 3-year atherosclerotic cardiovascular disease risk in Chinese type 2 diabetes mellitus patients. MATERIALS AND METHODS: Clinical records of 4,722 individuals with type 2 diabetes mellitus admitted to 94 hospitals were used. The features included demographic information, disease histories, laboratory tests and physical examinations. Logistic regression, support vector machine, gradient boosting decision tree, random forest and adaptive boosting were applied for model construction. The performance of these models was evaluated using the area under the receiver operating characteristic curve. Additionally, we applied SHapley Additive exPlanation values to explain the prediction model. RESULTS: All five models achieved good performance in both internal and external test sets (area under the receiver operating characteristic curve >0.8). Random forest showed the highest discrimination ability, with sensitivity and specificity being 0.838 and 0.814, respectively. The SHapley Additive exPlanation analyses showed that previous history of diabetic peripheral vascular disease, older populations and longer diabetes duration were the three most influential predictors. CONCLUSIONS: The prediction models offer opportunities to personalize treatment and maximize the benefits of these medical interventions.

Prediction of prognosis in COVID-19 patients using machine learning: A systematic review and meta-analysis.

BACKGROUND: Accurate prediction of prognostic outcomes in patients with COVID-19 could facilitate clinical decision-making and medical resource allocation. However, little is known about the ability of machine learning (ML) to predict prognosis in COVID-19 patients. OBJECTIVE: This study aimed to systematically examine the prognostic value of ML in patients with COVID-19. METHODS: A systematic search was conducted in PubMed, Web of Science, Embase, Cochrane Library, and IEEE Xplore up to December 15, 2021. Studies predicting the prognostic outcomes of COVID-19 patients using ML were eligible for inclusion. Risk of bias was evaluated by a tailored checklist based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Pooled sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated to evaluate model performance. RESULTS: A total of 33 studies that described 35 models were eligible for inclusion, with 27 models presenting mortality, four intensive care unit (ICU) admission, and four use of ventilation. For predicting mortality, ML gave a pooled sensitivity of 0.86 (95% CI, 0.79-0.90), a specificity of 0.87 (95% CI, 0.80-0.92), and an AUC of 0.93 (95% CI, 0.90-0.95). For the prediction of ICU admission, ML had a sensitivity of 0.86 (95% CI, 0.78-0.92), a specificity of 0.81 (95% CI, 0.66-0.91), and an AUC of 0.91 (95% CI, 0.88-0.93). For the prediction of ventilation, ML had a sensitivity of 0.81 (95% CI, 0.68-0.90), a specificity of 0.78 (95% CI, 0.66-0.87), and an AUC of 0.87 (95% CI, 0.83-0.89). Meta-regression analyses indicated that algorithm, population, study design, and source of dataset influenced the pooled estimate. CONCLUSION: This meta-analysis demonstrated the satisfactory performance of ML in predicting prognostic outcomes in patients with COVID-19, suggesting the potential value of ML to support clinical decision-making. However, improvements to methodology and validation are still necessary before its application in routine clinical practice.

[Establishment of non-targeted screening database and confirmation method for 18 mycotoxins in grains using ultra performance liquid chromatography-quadrupole-time of flight mass spectrometry].

A mass spectral library of 18 mycotoxins was developed based on ultra performance liquid chromatography-quadrupole-time of flight mass spectrometry (UPLC-Q-TOF/MS), which was used to establish a non-targeted screening method for mycotoxins in rice and wheat matrices. Eighteen mycotoxin standards were separated on an HSS T3 column, and data were collected for both positive and negative ionization under the MSE mode of the UPLC-Q-TOF/MS. Details including formulas, retention times, theoretical exact masses, measured exact masses of the adduct and fragment ions, and ion abundance ratios were recorded to establish the mass spectral library of the 18 mycotoxins in UNIFI Software. Analyte detection was based on a retention time deviation of 0.3 min, and the exact mass deviation of the adduct ions and fragment ions was set to 5×10-6. The screening detection limit (SDL) was used as the main threshold for verifying the screening method. In the validation process, 18 mycotoxins were classified into two types: with maximum levels (MLs) and without MLs. The results showed that the mycotoxins with MLs could be accurately screened at their limited level, and the mycotoxins without MLs had a range of SDL concentration from 2 to 800 µg/kg. The matrix effect results showed that 14 mycotoxins in rice and 11 in wheat had moderate matrix effects. Finally, 25 batches of rice and wheat were purified using QuEChERS and HLB columns after acetonitrile extraction and screening were performed by employing the established method. The results revealed that aflatoxin G1 (AFG1), aflatoxin G2 (AFG2), fumonisins B1 (FB1), and sterigmatocystin (ST) were detected in one batch of rice, FB1 and ST were detected in another batch of rice, FB1 and ochratoxin A (OTA) were detected in two batches of wheat, and no other mycotoxins were detected. This method is characterized by high throughput, simplicity, rapidity, accuracy, and can be applied to accurately screen mycotoxins with concentrations higher than the SDLs and qualitatively screen various mycotoxins in rice and wheat without standards.

Theoretical Approach and Scale Construction of Patient Privacy Protection Behavior of Doctors in Public Medical Institutions in China: Pilot Development Study.

BACKGROUND: Considering the high incidence of medical privacy disclosure, it is of vital importance to study doctors' privacy protection behavior and its influencing factors. OBJECTIVE: We aim to develop a scale for doctors' protection of patients' privacy in Chinese public medical institutions, following construction of a theoretical model framework through grounded theory, and subsequently to validate the scale to measure this protection behavior. METHODS: Combined with the theoretical paradigm of protection motivation theory (PMT) and semistructured interview data, the grounded theory research method, followed by the Delphi expert and group discussion methods, a theoretical framework and initial scale for doctors in Chinese public medical institutions to protect patients' privacy was formed. The adjusted scale was collected online using a WeChat electronic survey measured using a 5-point Likert scale. Exploratory and confirmatory factor analysis (EFA and CFA) and tests to analyze reliability and validity were performed on the sample data. SPSS 19.0 and Amos 26.0 statistical analysis software were used for EFA and CFA of the sample data, respectively. RESULTS: According to the internal logic of PMT, we developed a novel theoretical framework of a "storyline," which was a process from being unaware of patients' privacy to having privacy protection behavior, that affected doctors' cognitive intermediary and changed the development of doctors' awareness, finally affecting actual privacy protection behavior in Chinese public medical institutions. Ultimately, we created a scale to measure 18 variables in the theoretical model, comprising 63 measurement items, with a total of 208 doctors participating in the scaling survey, who were predominantly educated to the master's degree level (n=151, 72.6%). The department distribution was relatively balanced. Prior to EFA, the Kaiser-Meyer-Olkin (KMO) value was 0.702, indicating that the study was suitable for factor analysis. The minimum value of Cronbach α for each study variable was .754, which met the internal consistency requirements of the scale. The standard factor loading value of each potential measurement item in CFA had scores greater than 0.5, which signified that all the items in the scale could effectively converge to the corresponding potential variables. CONCLUSIONS: The theoretical framework and scale to assess doctors' patient protection behavior in public medical institutions in China fills a significant gap in the literature and can be used to further the current knowledge of physicians' thought processes and adoption decisions.

Associations between brain-derived neurotrophic factor and cognitive impairment in panic disorder.

INTRODUCTION: Our study was designed to examine the relationship between Brain-Derived Neurotrophic Factor (BDNF) genotypes (rs6265, Val66Met), BDNF plasma levels, and cognitive impairment in Chinese patients with panic disorder (PD). METHODS: Total 85 patients with PD and 91 healthy controls finally completed all assessments. The severity of panic symptoms and whole anxiety of PD was measured by Panic Disorder Severity Scale-Chinese Version (PDSS-CV) and Hamilton Anxiety Scale (HAMA-14). Montreal Cognitive Assessment (MoCA) and some neurocognitive measures were conducted to evaluate the cognitive performance. All participants were detected for the plasma BDNF levels and BDNF Val66Met polymorphism before assessment and treatment. RESULTS: No significant differences were found in the BDNF allele frequencies and the BDNF genotype distributions between healthy controls and PD patients. BDNF Met/Met genotype was associated with lower BDNF plasma levels in PD patients, and PD patients with BDNF Met/Met genotype had the lower scores in the attention and speed of processing domains compared to those with Val/Val and Met/Val genotype (p's < .05). Among PD patients, the BDNF plasma levels showed moderate positive correlations with Stroop interference (r = .60, p < .001). Using the MoCA data, the BDNF plasma levels were correlated with delayed memory (r = .50, p < .001), verbal learning (r = .45, p < .001), and total scores of MoCA (r = .51, p < .001). CONCLUSIONS: The BDNF Met/Met genotype may be associated with lower BDNF plasma levels and cognitive impairments in PD patients.

Altered brain function and clinical features in patients with first-episode, drug naïve major depressive disorder: A resting-state fMRI study.

Major depressive disorder (MDD) is characterized by heterogeneous clinical performance and neurocognitive impairment. It is important to explore the correlation between global functioning and regional homogeneity (ReHo)/amplitude of low-frequency fluctuation (ALFF) values in MDD patients. 67 first-episode, drug naïve MDD patients and 69 healthy subjects were enrolled in the study. The MATRICS Consensus Cognitive Battery (MCCB) and the Functioning Assessment Short Test (FAST) were used to assess functional impairment in patients. Brain activity was assessed using ReHo and ALFF measurements. The relationship between the clinical features and altered brain function was evaluated using correlation analysis. There were significant differences in the ReHo and ALFF values between MDD patients and healthy subjects. The reduction in ReHo in the left calcarine/lingual gyrus/cuneus was negatively correlated with occupational functioning and the total FAST scores. The reduction in ALFF in the right calcarine/lingual gyrus was positively correlated with the verbal learning aspects of the MCCB. These findings suggest that the altered brain function in the default mode network (DMN) may be related to functional impairments in patients with first-episode, drug naïve major depressive disorder.

Psychometric properties of the MATRICS Consensus Cognitive Battery (MCCB) in Chinese patients with major depressive disorder.

BACKGROUND: Major depression disorder (MDD) is often associated with cognitive impairment. The development of an accurate and effective battery to measure cognitive deficit is necessary for both research and clinical practice in MDD. Our study was designed to test the psychometric properties of the MATRICS Consensus Cognitive Battery (MCCB) in patients with MDD. METHOD: Forty-eight patients with MDD, forty-three euthymic patients with bipolar disorder (BD) and thirty-two remitted patients with schizophrenia (SCH) were recruited from Tianjin Anding Hospital in Tianjin, China. The MCCB, the Montreal Cognitive Assessment (MoCA) and the Hamilton Depression Rating Scale-17 (HDRS-17) were administered to assess cognitive impairment and depressive symptoms at both baseline and one month later. RESULT: Our findings showed that the MCCB had good internal consistency and acceptable reliability in Chinese MDD patients. Our findings revealed a high correlation between the MCCB and the MoCA, indicating good concurrent validity of the MCCB. Furthermore, the MCCB showed high discriminant ability between MDD patients and healthy controls, and a principal component analysis of the MCCB in MDD patients revealed four domains with acceptable internal structure. LIMITATIONS: We did not consider confounding factors, such as the course, severity of symptoms and medication treatments, which might bias the cognitive assessment. In addition, the use of the MoCA as a reference scale for mild cognitive impairment could weaken the concurrent validity of the MCCB in MDD patients. CONCLUSION: Our findings demonstrated that the MCCB may be clinically useful as a cognitive impairment rating battery in Chinese patients with MDD.

[Determination of bis (p-fluorobenzyl) trisulfide and bis (p-fluoro-benzyl) disulfide in lungs of rat by HPLC].

OBJECTIVE: To establish an HPLC method for analysis of bis(p-fluorobenzyl) trisulfide(BFTS) and bis(p-fluorobenzyl)disulfide(BFDS) in the lungs of rat. METHODS: 5.0 ml extract solvent (n-hexane: isopropyl alcohol=95:5, v/v) and 20 microl of 11.50 microg/ml dibenzyl disulfide (internal standard) were added to 0.2 g lung sample followed by homogenization. After centrifugation, 4.0 ml of supernatant was separated and vaporized to dryness, and the residue was reconstituted in mobile phase for HPLC analysis. The HPLC analysis was performed on an SB C18 column using acetonitrile and water (65:35, v/v) as mobile phase with a flow rate of 1.0 ml/min with UV detection at 220 nm. RESULT: The calibration curves for BFTS and BFDS in sample were linear over the concentration ranges of 0.04712-14.78 microg/g(r=0.999) and 0.04831-23.96 microg/g(r=0.999), respectively. The limits of quantification were 0.04712 microg/g and 0.04831 microg/g for BFTS and BFDS, respectively. The assay recoveries for BFTS and BFDS ranged from 95.71%-107.2% and 90.00%-110.5%, respectively. The precisions were obtained with RSD of <10%. The developed method was successfully applied to study the content of BFTS and BFDS in the lungs of rats after intravenous injection of 12.5 mg/kg BFTS. CONCLUSION: The method developed is simple, selective, repeatable and accurate, which can be applied to study the tissue distribution of BFTS and BFDS.

Intestinal absorption of luteolin from peanut hull extract is more efficient than that from individual pure luteolin.

Luteoin is one of the main flavones and the crucial effective component of peanut hull extract (PHE). The present paper aims to elucidate the absorption mechanism of luteolin and clarify whether its absorption occurs primarily at a specific site of the intestine by an in situ single-pass intestinal perfusion (SPIP) model. Moreover, the paper investigates the difference in absorption of luteolin when it is administered in PHE form and as pure luteolin by the SPIP model and in vivo pharmacokinetics studies. Results showed that the effective permeability ( P eff) and absorption rate constant ( k a) of pure luteolin(5.0 microg/mL) in duodenum and jejunum were not significantly different, but markedly higher than that in the colon and ileum. The P eff and k a of luteolin in jejunum were concentration-independent, and the ATP inhibitor (DNP) did not influence P eff and k a of pure luteolin. However, the P eff and k a of luteolin in PHE were significantly greater than that of pure luteolin. The pharmacokinetics study showed that following oral administration of a single dose of pure luteolin (14.3 mg/kg) or PHE (= 14.3 mg/kg of luteolin) in rats, the peak concentration of luteolin in plasma ( C max) and the area under the concentration curve (AUC) for pure luteolin were 1.97 +/- 0.15 microg/mL and 10.7 +/- 2.2 microg/mL.h, respectively. These parameters were significantly lower than those of the PHE group ( P < 0.05), C max = 8.34 +/- 0.98 microg/mL and AUC = 20.3 +/- 1.3 microg/mL.h, respectively. It can be concluded that luteolin is absorbed passively in the intestine of rats and that its absorption is more efficient in the jejunum and duodenum than in the colon and ileum. The bioavailability of luteolin in PHE form is significantly greater than that of pure luteolin.

[A clinical and pathological analysis on laryngeal contact granuloma among 18 cases].

OBJECTIVE: To summarize the clinicopathologic feature and diagnostic and therapeutic experience of laryngeal contact granuloma. METHOD: A retrospective study was carried out among 18 cases with this disease through careful analysis on their clinical and pathological data. RESULT: All of 18 cases were male, aged 34 to 78 years,The most common symptoms were hoarseness. In general the granuloma located on the posterior of the larynx unilaterally. The histological appearances of the lesions were typical inflammatory granuloma. Little allotype cell were found in one histologic sample. Fifteen cases received surgical excision and the recurrence rate was 60% after operation. Recidivist received operation again,4 cases among these cases received antireflux therapy after operation but 3 cases recurrences again. Among those follow-up cases(3 cases), 1 case was self-cure and other 2 cases appeared no marked change during observation period. CONCLUSION: Laryngeal contact granuloma predilected the middle-aged male. The localization and appearance of the granuloma is very characteristic. The correct diagnosis can be established by clinical examination alone, but the histological examination is necessary in order to avoid missed diagnosis. There is a high recurrence rate after operation and the effect of antireflux therapy need further research.