Lower GDNF Serum Level Is a Possible Risk Factor for Constipation in Patients With Parkinson Disease: A Case–Control Study

Background: Constipation is a significant symptom of Parkinson's disease (PD). Glial-derived neurotrophic factor (GDNF) is important for the morphogenesis of the enteric nervous system and plays a critical role in the preservation of mucosal integrity under enteric glia surveillance. The aim of this work was to evaluate the serum levels of GDNF in patients with PD with and without constipation.Methods: This work included 128 patients with PD. The patients were classified into three groups: those with PD but no constipation (nCons-PD) (n = 49), those with prodromal stage constipation (Cons-Pro-PD) (n = 48), and those with clinical stage constipation (Cons-Clinic-PD) (n = 31). The association between serum GDNF concentration and constipation was explored using logical regression.Results: The nCons-PD group's mean GDNF levels were 528.44 pg/ml, which was higher than the Cons-Pro-PD group's 360.72 pg/ml and the Cons-Clinic-PD group's 331.36 pg/ml. The results of binary logistic regression indicated that GDNF was a protective factor in the prevention of constipation. Cons-Clinic-PD group had a higher score of MDS-UPDRS-II, MDS-UPDRS-III, MDS-UPDRS-IV, and a higher H-Y staging as compared with nCons-PD group. Relative to the nCons-PD group, Cons-Clinic-PD had higher NMSS scores, lower MoCA and PDSS scores, and were more likely to have RBD.Conclusions: GDNF serum levels are lower in patients with PD who are constipated. A low GDNF level is a potential risk factor for constipation in patients with PD.

Development and Validation of Predictors for the Survival of Patients With COVID-19 Based on Machine Learning

Background: The outbreak of COVID-19 attracted the attention of the whole world. Our study aimed to explore the predictors for the survival of patients with COVID-19 by machine learning.Methods: We conducted a retrospective analysis and used the idea of machine learning to train the data of COVID-19 patients in Leishenshan Hospital through the logical regression algorithm provided by scikit-learn.Results: Of 2010 patients, 42 deaths were recorded until March 29, 2020. The mortality rate was 2.09%. There were 6,812 records after data features combination and data arrangement, 3,025 records with high-quality after deleting incomplete data by manual checking, and 5,738 records after data balancing finally by the method of Borderline-1 Smote. The results of 10 times of data training by logistic regression model showed that albumin, saturation of pulse oxygen at admission, alanine aminotransferase, and percentage of neutrophils were possibly associated with the survival of patients. The results of 10 times of data training including age, sex, and height beyond the laboratory measurements showed that percentage of neutrophils, saturation of pulse oxygen at admission, alanine aminotransferase, sex, and albumin were possibly associated with the survival of patients. The rates of precision, recall, and f1-score of the two training models were all higher than 0.9 and relatively stable.Conclusions: We demonstrated that percentage of neutrophils, saturation of pulse oxygen at admission, alanine aminotransferase, sex, and albumin were possibly associated with the survival of patients with COVID-19.

The Association between Dietary Inflammation Index and Rheumatoid Arthritis in Americans: a cross-sectional study

Background Studies have shown that personal diet has a certain impact on the development and treatment of rheumatoid arthritis (RA). However, the effect of overall dietary structure on RA is still an exploratory issue at present. Dietary inflammation index (DII) is an index that evaluates the inflammatory potential of the total nutrients consumed by human body. Therefore, we studied the correlation between DII and RA in Americans to explore whether the pro-inflammatory or anti-inflammatory effects of diet contribute to the risk of RA. Methods We used data from the 2005–2017 NHANES database for analysis, including 1819 individuals with RA and 8602 individuals without RA. Among them, DII was calculated by collecting the relevant data of Total Nutrient Intakes, First Day in the database. The analysis was carried out through the comparison between the two groups, including logical regression, multiple regression analysis, smooth curve fitting, recursive algorithm, and independent sample T-test. Results After adjusting for other confounding factors, we found that there was a positive correlation between DII and RA in Americans (β = 1.068, 95% CI = 1.026 to 1.111, P = 0.00121). In the subgroup analysis, it was found that characteristics of the participants were younger than 50 years old, female, Other Hispanic, BMI≥25 or federal poverty rate > 185%, there was still a positive association between DII and RA. Compared with non-smokers, the effect between DII and RA of smokers was greater than that of non-smokers. In Other Hispanic, there was an inflection point (K = 1.195). When K > 1.195, the curve gradient increases rapidly. In addition, the intake of energy, protein, dietary fiber, total saturated fatty acids, vitamin E, vitamin B6, magnesium, zinc, Niacin, Selenium, iron, and alcohol in individuals with RA was significantly lower than that in those without RA. Conclusions The inflammatory potential of diet may increase the risk of onset and development of RA. The risk may be different in different individuals, but it may be a feasible way to prevent and alleviate RA by improving dietary structure, reducing pro-inflammatory food, and increasing anti-inflammatory food intake.

Prediction of Cardiovascular Diseases based on Machine Learning

With the rapid development of artificial intelligence, it is very important to find the pattern of the data from the observed data and the functional dependency relationship between the data. By finding the existing functional dependencies, we can classify and predict them. At present, cardiovascular disease has become a major disease harmful to human health. As a disease with high mortality, the prediction problem of cardiovascular disease is becoming more and more urgent. However, some computer methods are mainly used for disease detection rather than prediction. If the computer method can be used to predict cardiovascular disease in advance and treat it as early as possible, then the consequences of the disease can be reduced to a certain extent. Diseases can be predicted by mechanical methods. Support vector machine (SVM) has strict mathematical theory support, and can deal with nonlinear classification after using kernel techniques. Therefore, support vector machine can be used to predict cardiovascular disease. On the other hand, we also use logical regression and random forest to predict cardiovascular disease. This paper mainly uses the method of machine learning to predict whether the population is sick or not. First of all, we preprocess the obtained data to improve the quality of the data, and then use svm and logical regression to predict, so as to provide reference for the prevention and treatment of cardiovascular diseases.

Predictive Model of Postgraduate Student’s Dropout and Delay Using Machine Learning Algorithms

Neural networks and Logical Regression algorithm provide the best ways to classify data, but they are outperformed continuously by the Decision Tree in analyzing student performance. Therefore, many scholars have used the Decision Tree to predict student performance with greater success. This research analyzed postgraduate student degree outcomes using socioeconomic data to develop a prediction model, where Decision Tree recorded the highest accuracy of 92.79%, better than Logical Regression and Neural Network. For brevity, the Decision Tree was used to produce the prediction model. Based on the study findings, postgraduate students who delay or drop out at the university mostly lack sponsors or had decreased income. Besides, male students delay or drop out if they had financial issues more than their female counterparts. Age, money management skills, number of children, and health expenses are the other factors that contribute to higher dropout or delay at the university. Therefore, this study provides a reliable prediction model for degree outcomes, allowing personalized follow-up to improve graduation rates.

IVERMECTIN REPROPOSING FOR COVID-19 TREATMENT OUTPATIENTS IN MILD STAGE IN PRIMARY HEALTH CARE CENTERS

Background: The emergence of COVID-19 requires alternative treatments based on the reuse of drugs as a strategy to prevent the progression of the disease in patients infected with SARS-COV-2. The goal was to evaluate the use of ivermectin in mild stage outpatients to heal and / or reverse the progression of COVID-19 disease towards the development of moderate or severe stages. Methods: Cluster Assigned Clinical Trial (2:1) in outpatients, n = 234. The subjects were divided into experimental (EG: n = 110) and control groups (CG: n = 62). The EG received ivermectin orally 4 drops of 6 mg = 24 mg every 7 days for 4 weeks. All participants were diagnosed by positive RT-PCR for COVID-19 and were evaluated by clinical examination, at the beginning and the end of protocol. Data analyzed were applied the proportion, bivariate, and logical regression tests with level significance p < 0.05. This study was registered at ClinicalTrials.gov Identifier NCT04784481. Findings: Both groups were similar in age, sex, and comorbidities (EG: 56F, median age= 40.0, range: 18.0 - 75.0; CG: 34F, median age = 37.5, range: 18.0 - 71.0). A significant reduction in the symptom numbers was observed in the EG when the medical examination was performed from 5th to 9th days, after starting treatment (p = 0.0026). Although, medical examination from 10th to 14th day, showed a progressive reduction of the percentage symptom numbers, these were not significative in both groups. A higher proportion of medical release was observed in EG (98.2%) vs CG (87.1%) (p = 0.003). EG showed 8 times more chance of receiving medical release than CG (OR 7.99, 95% CI: 1.64 -38.97, p = 0.003). The treatment effect with ivermectin to obtain medical release was analyzed by the logistic regression model based in the following control variables: sex, age, and comorbidities. Then, the chance to obtain medical release was maintained in EG (OR 10.37, 95% CI: 2.05 - 52.04, p = 0.005). Interpretation: Treatment with ivermectin in outpatients with mild stage COVID-19 disease managed to slightly reduce the symptom numbers. Also, this treatment improved the clinical state to obtain medical release, even in the presence of comorbidities. The treatment with ivermectin could significantly prevent the evolution to serious stages since the EG did not present any patient with referral to critical hospitalization.

Nomogram Prediction of Severe Risk in Patients With COVID-19 Pneumonia: A Retrospective Study

Background COVID-19 elicits a range of different responses in patients and can manifest into mild to very severe cases in different individuals, depending on many factors. We aimed to establish a prediction model of severe risk in COVID-19 patients, to help clinicians achieve early prevention, intervention, and aid them in choosing effective therapeutic strategy. Methods We selected confirmed COVID-19 patients who admitted to First Hospital of Changsha city between January 29 and February 15, 2020 and collected their clinical data. Multivariate logical regression was used to identify the risk factors associated with severe risk. These factors were incorporated into the nomogram to establish the model. The ROC curve, calibration plot and decision curve were used to assess the performance of model. Results 239 patients were enrolled and 45 (18.83%) patients developed severe pneumonia. Univariate and multivariate analysis showed that age, COPD, shortness of breath, fatigue, creatine kinase, D-dimer, lymphocytes and h CRP were independent risk factors for severe risk in COVID-19 patients. Incorporating these factors, the nomogram achieved good concordance indexes of 0.873 (95% CI: 0.819–0.927), and well-fitted calibration plot curves. The model provided superior net benefit when clinical decision thresholds were between 10–70% predicted risk. Conclusions Using the model, clinicians can intervene early, improve therapeutic effects and reduce the severity of COVID-19, thus ensuring more targeted and efficient use of medical resources.

Effective Prediction of Diabetes Mellitus using Nine different Machine Learning Techniques and their Performances

Diabetes is a disease where the predominant finding is high blood sugar. The high blood sugar may either be because of deficient insulin production (Type 1) or insulin resistance in peripheral tissue cells (Type 2). Many problems occur if diabetes remains untreated and unidentified. It is additional inventor of various varieties of disorders for example: coronary failure, blindness, urinary organ diseases etc. Nine different machine learning techniques are used in this research work for prediction of diabetes. A dataset of diabetic patient’s is taken and nine different machine learning techniques are applied on the dataset. Positive likelihood ratio, Negative likelihood ratio, Positive predictive value, Negative predictive value, Disease prevalence, Specificity, Precision, Recall, F1-Score ,True positive rate, False positive rate of the applied algorithms is discussed and compared. Diabetes is growing at an increasing in the world and it requires continuous monitoring. To check this we use Logical regression, Random forest, Logical regression CV, Support Vector Machine, Artificial Neural Network (ANN), Decision Tree, k-nearest neighbors (KNN), XGB classifier.

0621 Utilization of the Ares to Predict OSA Among Blacks Using Home-Based Watchpat Recording

Introduction In two waves of data we collected in Brooklyn New York, we observed blacks were at high risk for obstructive sleep apnea (OSA). In the NIH-funded study ‘Metabolic Syndrome Outcome Study (MetSO), blacks enrolled from primary-care settings had a 59% risk of OSA. Similarly, blacks surveyed in churches and barbershops had a 43% risk of OSA. While these studies showed higher than expected risk as noted in the general population (29%), it remains uncertain how many of those blacks would be diagnosed with OSA in that population. The purpose of this study was to explore the rate of OSA using the WatchPat device in a community-based setting. Methods Data were collected from an NIH-funded study ‘Peer-Enhanced Education to Reduce Sleep Ethnic Disparities, designed to navigate blacks at risk of OSA to receive timely diagnosis and treatment using peer-delivered linguistically and culturally tailored sleep health education. Blacks were screened for OSA using the Apnea Risk Evaluation System (ARES) Questionnaire; a score ≥6 denoted moderate-high OSA risk. Individuals were asked to wear the WatchPAT 200 for one night during a week-long sleep assessment. WatchPat 200 measures SaO2 to determine respiratory-related arousals, defined as an Apnea-Hypopnea Index (AHI) ≥5, which is used to identify and diagnose OSA. We used SPSS 25.0 to perform logical regression analysis to assess associations between ARES and WatchPat AHI. Results A sample of 111 blacks provided valid ARES and WatchPat data for the present analyses. Of the sample, the mean age was 62.26 (SD=13.52 years; female = 55%); 49% reported annual income &gt;20K and 79.5% reported a high school education. Moreover, 27% reported high blood pressure, 13%, diabetes, and 65% were overweight/obese. Multivariate-adjusted logical regression analyses indicated that blacks at risk for OSA were 66% more likely to receive an OSA diagnosis based on WatchPat AHI data (OR = 1.662, p &lt; 0.01). The model adjusted for age, sex, income, and education. Conclusion The present study demonstrated that blacks at risk for OSA at the community level have a significant likelihood of receiving an OSA diagnosis using home-based recordings. Support NIH Support (T32HL129953, RO1MD007716, K01HL135452 and K07AG052685).