Assessing the feasibility of statistical inference using synthetic antibody-antigen datasets.

Simulation frameworks are useful to stress-test predictive models when data is scarce, or to assert model sensitivity to specific data distributions. Such frameworks often need to recapitulate several layers of data complexity, including emergent properties that arise implicitly from the interaction between simulation components. Antibody-antigen binding is a complex mechanism by which an antibody sequence wraps itself around an antigen with high affinity. In this study, we use a synthetic simulation framework for antibody-antigen folding and binding on a 3D lattice that include full details on the spatial conformation of both molecules. We investigate how emergent properties arise in this framework, in particular the physical proximity of amino acids, their presence on the binding interface, or the binding status of a sequence, and relate that to the individual and pairwise contributions of amino acids in statistical models for binding prediction. We show that weights learnt from a simple logistic regression model align with some but not all features of amino acids involved in the binding, and that predictive sequence binding patterns can be enriched. In particular, main effects correlated with the capacity of a sequence to bind any antigen, while statistical interactions were related to sequence specificity.

Prevalence and predictors associated with modern contraceptive method utilization among women in the nomadic community of Ethiopia: a cross-sectional study.

BACKGROUND: Ethiopia is one of the countries in sub-Saharan Africa with the lowest prevalence of the use of modern contraceptive methods. On the frequency and determinants of modern contraceptive method in the Ethiopian women who live a nomadic lifestyle, there is, however, scant research. Therefore, the purpose of this study was to evaluate the factors that influence how often women in Ethiopia's nomadic tribes use modern contraceptive method. METHODS: In the nomadic community of Ethiopia, a community-based retrospective cross-sectional study was carried out between January 18 and June 27, 2016. From the 15,683 nationally representative datasets on the 2016 Ethiopian Demography and Health Survey, a sample of 3,415 women from nomadic communities was chosen. To determine factors linked to modern contraceptive method usage within the nomadic group, a multivariable logistic regression model analysis was considered. RESULT: In the nomadic population of Ethiopia, 10% (95% CI (9.10, 11.1)) of respondents reported using modern contraceptive method overall. The most popular way to use modern contraceptive method was through injection (73.5%). In the multivariable logistic regression model analysis, secondary and above-educated husbands (AOR = 1.6, 95% CI (1.01, 2.24)) and primarily educated husbands (AOR = 1.4, 95% CI (1.027, 2.0)), rich (AOR = 1.6, 95% CI (1.03, 2.74)) and middle wealth index (AOR = 1.58, 95% CI (1.25, 2.38)), public health place of delivery (AOR = 2.5, 95% CI (1.55, 3.0)), being a working husband (AOR = 3.8, 95% CI (1.96, 4.22)), and respondents working (AOR = 1.5, 95% CI (1.04, 1.79)) were positively critical risk predictors associated with modern contraceptive method usages. Compared to the Somali region, women living in the Afar (AOR = 2.58, 95% CI (1.68, 3.95)) and Benshangul-Gumuz (AOR = 3.40, 95% CI (2.22, 5.21)) regions had higher use of modern contraceptive method. CONCLUSION: In Ethiopia, modern contraceptive method usage is still quite uncommon among women who live in nomadic communities. Therefore, in order to increase modern contraceptive method service utilization and improve the wealth index of households, two key strategies, government professionals and concerned body service providers should pay special attention to educational opportunities for husbands and give valuable and effective counseling information during child delivery for women.

Residents' Willingness to Pay for Water Pollution Treatment and Its Influencing Factors: a Case Study of Taihu Lake Basin.

This study designs a double-bounded dichotomous questionnaire, and uses the Contingent Valuation Method (CVM) to estimate residents' willingness to pay(WTP) for water pollution control along the Taihu Lake Basin. The results of the returned questionnaire show that 82.76% of the residents are willing to pay. CVM estimation results show that the average WTP of residents for water pollution control is 138.86 yuan/year. In addition, the influencing factors of WTP are explored using a Logistic regression model, and the heterogeneity of WTP among residents of different genders is analyzed. The study found that: (1) The younger the residents, the higher their WTP; (2) The higher the income, the higher the residents' WTP for water pollution control; (3) Residents with higher educational level are more willing to pay; (4) The higher the degree of residents' understanding of water pollution control policies, the higher the WTP; (5) The higher the degree of residents' recognition of pro-environmental behavior, the higher the WTP; (6) Male residents' WTP is mainly affected by cognitive factors such as their understanding of governance policies and their approval of pro-environmental behaviors, while female residents' WTP is mainly affected by personal attributes, such as age, income, and the number of household laborers. Furthermore, this study proposes targeted measures to improve residents' WTP from three aspects: the government enriches the channels for residents to participate in water pollution control, the social media enriches the popularization of water environment knowledge, and the school strengthens the education of environmental protection knowledge, considering the differences in residents' characteristics. Therefore, this study can provide a theoretical reference and decision-making basis for encouraging residents to participate in water pollution control, promote the construction of a beautiful watershed, and provide a reference for other basins.

Classification of Chest CT Lung Nodules Using Collaborative Deep Learning Model.

Background: Early detection of lung cancer through accurate diagnosis of malignant lung nodules using chest CT scans offers patients the highest chance of successful treatment and survival. Despite advancements in computer vision through deep learning algorithms, the detection of malignant nodules faces significant challenges due to insufficient training datasets. Methods: This study introduces a model based on collaborative deep learning (CDL) to differentiate between cancerous and non-cancerous nodules in chest CT scans with limited available data. The model dissects a nodule into its constituent parts using six characteristics, allowing it to learn detailed features of lung nodules. It utilizes a CDL submodel that incorporates six types of feature patches to fine-tune a network previously trained with ResNet-50. An adaptive weighting method learned through error backpropagation enhances the process of identifying lung nodules, incorporating these CDL submodels for improved accuracy. Results: The CDL model demonstrated a high level of performance in classifying lung nodules, achieving an accuracy of 93.24%. This represents a significant improvement over current state-of-the-art methods, indicating the effectiveness of the proposed approach. Conclusion: The findings suggest that the CDL model, with its unique structure and adaptive weighting method, offers a promising solution to the challenge of accurately detecting malignant lung nodules with limited data. This approach not only improves diagnostic accuracy but also contributes to the early detection and treatment of lung cancer, potentially saving lives.

Forest fire vulnerability in Nepal's chure region: Investigating the influencing factors using generalized linear model.

The Chure region, among the world's youngest mountains, stands out as highly susceptible to natural calamities, particularly forest fires. The region has consistently experienced forest fire incidents, resulting in the degradation of valuable natural and anthropogenic resources. Despite its vulnerability, there have been limited studies to understand the relationship of various causative factors for the recurring fire problem. Hence, to comprehend the influencing factors for the recurring forest fire problem and its extent, we utilized generalized linear modeling under binary logistic regression to combine the dependent variable of satellite detected fire points and various independent variables. We conducted a variance inflation factor (VIF) test and correlation matrix to identify the 14 suitable variables for the study. The analysis revealed that forest fires occurred mostly during the three pre-monsoon periods and had a significant positive relation with the area under forest, rangeland, bare-grounds, and Normalized Difference Vegetation Index (NDVI) (P < 0.05). Consequently, our model showed that the probability of fire incidents decreases with elevation, precipitation, and population density (P < 0.05). Among the significant variables, the forest areas emerges as the most influencing factor, followed by precipitation, elevation, area of rangeland, population density, NDVI, and the area of bare ground. The validation of the model was done through the area under the curve (AUC = 0.92) and accuracy (ACC = 0.89) assessments, which showed the model performed excellently in terms of predictive capabilities. The modeling result and the forest fire susceptible map provide valuable insights into the forest fire vulnerability in the region, offering baseline information about forest fires that will be helpful for line agencies to prepare management strategies to further prevent the deterioration of the region.

Are digital technologies an effective inhibitor of depression among middle-aged and older adults? Micro-level evidence from a panel study.

The increased number of middle-aged and older adults leads to depression in this stratum of the population as a topical social and public health issue. However, the new generation of information technologies has exerted a profound impact on the lives of middle-aged and older adults, and offers potential solutions for alleviating their depression. This study utilizes data from the China Health and Retirement Longitudinal Study (CHARLS) collected between 2011 and 2018 and combines them with city-level traits. The results demonstrate that digital technology can reduce depression levels effectively in this group. Mechanism analysis reveals that digital technology could improve life satisfaction and subjective health status levels, which, in turn, reduces depression levels. Heterogeneity analysis shows that the positive effects of digital technology on depression were more pronounced among middle-aged and older adults with urban household registration compared to the rural population. Finally, recommendations are provided for reducing depression levels among middle-aged and older adults.

Contraceptive Utilization and Its Associated Factors Among Married Women in West African Countries: A Population-Based Survey Using Multinomial Logistic Regression.

Background: The international development agenda emphasizes universal access to family planning, as seen in Sustainable Development Goal 3.7. However, the use of modern contraceptive methods remains low in developing countries, specifically in West Africa. This study aimed to assess the current status of contraceptive use in the region, focusing on different methods. Methods: We analyzed Demographic and Health Survey data from 13 West African nations (2012-2022) involving 117,165 married women. Using binary and multiple multinomial logistic regression, we identified key factors associated with contraceptive use. Adjusted odds ratios with 95% confidence intervals were utilized, and significance was determined at p ≤ 0.2 for binary regression and p < 0.05 for multiple multinomial regression. Results: About 80.86% of women did not use any method, while 16.56% of women used modern methods. Maternal age of 35-49 years (RRR=0.77, 95% CI, 0.72,0.82), had given first birth after 20 years (RRR=0.80,95% CI, 0.77,0.83), cohabitation after 20 years old (RRR=1.24,95% CI, 1.18,1.29), being employed (RRR=1.38,95% CI, 1.33,1.43), women who have from 3-5, and more than five living children (RRR=2.06,95% CI,1.97,2.16, and (RRR=2.57, 95% CI, 2.42,2.74), primary(RRR=1.59, 95% CI, 1.52,1.66), secondary/higher education (RRR=2.08, 95% CI, 1.99,2.18), antenatal visit (RRR= 1.38, 95% CI 1.28,1.49), institutional delivery(AOR=1.42, 95% CI, 1.35,1.49), husband working status (RRR=1.39, 95% CI, 1.28,1.51), media exposure(RRR=1.23, 95% CI, 1.19,1.28), visited health facility more than once (RRR=1.09, 95% CI, 1.05,1.13), rural women (RRR=0.89,95% CI,0.85,0.93), female households (RRR=0.79, 95% CI,0.76,0.83), richer (RRR=1.42, 95% CI,1.33,1.51), and richest wealth indexes (RRR=1.69,95% CI,1.58,1.82) were associated. Conclusion: This study revealed a low level of contraceptive use among women in West Africa. Strengthening maternal reproductive health services, such as antenatal care, institutional delivery, and health visits, while also targeting mass media and disadvantaged women, has the potential to significantly increase the adoption of modern contraception techniques.

Association between migraine and exclusive breastfeeding: A cross-sectional study.

BACKGROUND: Medical conditions may preclude a mother from exclusively breastfeeding her infant; however, the association between migraine and the duration of exclusive breastfeeding is not well known. OBJECTIVE: To evaluate the association between migraine and the duration of exclusive breastfeeding in a representative sample of Canadian females. METHODS: We used the Canadian Community Health Survey, a cross-sectional survey, to identify females aged 20-49 years who delivered a baby in the previous 5 years. History of migraine was self-reported. Females reported if they breastfed their baby, and among those who did, they further reported the duration of exclusive breastfeeding. We evaluated the association between migraine and the rate of breastfeeding, and the duration of exclusive breastfeeding adjusting for selected covariates. RESULTS: We included 5282 females, of whom 862 (16.3%) had migraine. Compared to females without migraine, females with migraine were less likely to have high income (annual income >$80,000: 362 [42.0] vs. 2276 [51.6]), and more likely to have comorbid mood (176 [20.5] vs. 378 [8.6%]) and anxiety (196 [22.8%] vs. 406 [9.2%]) disorders. Migraine was not associated with breastfeeding (proportion of females who did not breastfeed, migraine vs. no migraine: 114/862 [13.2%] vs. 498/4420 [11.3%]; adjusted odds ratio 1.03; 0.74-1.27); however, females with migraine had lower odds (≥6 months of exclusive breastfeeding: 216/688 [31.4%] vs. 1325/3561 [37.2%]; adjusted odds ratio from ordinal shift analyses 0.84; 0.71-0.99) of longer duration of exclusive breastfeeding than females without migraine. CONCLUSION: Females with migraine exclusively breastfeed their infants for a shorter duration compared to females without migraine, suggesting the need to better support this population through education on the safety and benefits of exclusive breastfeeding and better access to safe and effective treatment of migraine in lactating females.

Analysing predictors of surgical site infections in patients undergoing emergency surgery for traumatic pulmonary haemorrhage.

Identifying predictors for surgical site infections (SSIs) after emergency surgical treatment for traumatic pulmonary haemorrhage (TPH) is crucial for improving patient outcomes. This study aims to ascertain these predictors. In this comprehensive retrospective study, conducted from January 2020 to December 2023 at our institution, 75 patients were analysed, including a case group of 25 patients with SSIs and a control group of 50 without SSIs post-TPH surgery. Inclusion criteria focused on patients aged 18 and above undergoing thoracotomy or minimally invasive thoracic surgery for TPH. Exclusion criteria included compromised immune systems, chronic pulmonary diseases, prior thoracic surgery or active infections at admission. We assessed several predictors: anaemia; operation time over 2 h; hospital stay over 5 days; intraoperative blood loss exceeding 500 mL; body mass index (BMI) ≥25 kg/m2; age ≥ 50 years; use of surgical drains; the presence of open wounds; diabetes mellitus and non-prophylactic antibiotic use. Statistical analysis involved univariate and multivariate logistic regression, using SPSS Version 27.0. Univariate analysis revealed significant associations between SSIs and surgical drain placement, diabetes mellitus, open wounds and non-prophylactic antibiotic use (p < 0.01). Multivariate analysis confirmed these factors as significant predictors of SSIs, with notable odds ratios. Other variables like anaemia, extended hospital stay, excessive intraoperative blood loss, older age and higher BMI did not significantly predict SSIs. Significant predictors for SSIs following TPH surgery include surgical drain placement, diabetes mellitus, open wounds and non-prophylactic antibiotic use. Identifying and managing these risks is crucial in clinical practice to reduce SSIs incidence and improve patient outcomes.

Determinants of malaria prevention and control at household level in Assam: An analysis of data using composite index.

Background: Malaria prevention and control is a major public health problem of tropical countries including India. Usage of insecticide-treated bed nets, and early treatment especially in high-risk areas are the crucial factors for the malaria prevention at household levels. This study aimed to determine the crucial factors associated with malaria prevention at households' level such as household's characteristics, education, knowledge and awareness, insecticide treated bed nets usage, early treatment etc. Methods: Data of 1989 households was used from the cross-sectional survey of malaria-endemic areas of Assam. Principal component analysis and multinomial logistic regression model were used to compute the composite scores of malaria awareness and prevention practices, and to estimate the associated factors with malaria prevention practices, respectively. Results: The average age of household respondents were 41.1 ± 12.0 years and among them 71% were males. Almost 47% respondents were illiterate, and 38.6% of the respondents were farmers and 35% were employed. Multinomial logistic regression analysis indicates that malaria prevention practices are associated with age, education, religion, type of house and occupation of household heads and their level of malaria awareness among them. The prevention practices were significantly five times associated [Adjusted Rates Ratio (ARR): 5.0, 95% CI: 2.7-9.4] with the high level of malaria awareness compared with the low level of awareness. Overall, the level of prevention awareness, education, occupation, and house type related to the standard of living was significantly associated with the malaria prevention practices. Conclusion: Malaria awareness and education are the key factors of malaria prevention practices that need to be accelerated for effective control of malaria. Malaria education and increasing awareness of people have a high impact on malaria prevention practices and their control.

Individualized Prediction of SARS-CoV-2 Infection in Mexico City Municipality during the First Six Waves of the Pandemic.

After COVID-19 emerged, alternative methods to laboratory tests for the individualized prediction of SARS-CoV-2 were developed in several world regions. The objective of this investigation was to develop models for the individualized prediction of SARS-CoV-2 infection in a large municipality of Mexico. The study included data from 36,949 patients with suspected SARS-CoV-2 infection who received a diagnostic tested at health centers of the Alvaro Obregon Jurisdiction in Mexico City registered in the Epidemiological Surveillance System for Viral Respiratory Diseases (SISVER-SINAVE). The variables that were different between a positive test and a negative test were used to generate multivariate binary logistic regression models. There was a large variation in the prediction variables for the models of different pandemic waves. The models obtained an overall accuracy of 73% (63-82%), sensitivity of 52% (18-71%), and specificity of 84% (71-92%). In conclusion, the individualized prediction models of a positive COVID-19 test based on SISVER-SINAVE data had good performance. The large variation in the prediction variables for the models of different pandemic waves highlights the continuous change in the factors that influence the spread of COVID-19. These prediction models could be applied in early case identification strategies, especially in vulnerable populations.

Association of vitamin B1 intake with geriatric cognitive function: An analysis of the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2014.

Background: The association between dietary vitamin B1 intake and cognitive performance in the noninstitutionalized older adult population of the United States remains unclear. Purpose: This study aimed to investigate the association between vitamin B1 intake and cognitive performance in older adults in the United States. Methods: Vitamin B1 intake was assessed through two 24-h dietary recalls. Weighted logistic regression was used to evaluate the association between vitamin B1 intake and three cognitive scores (immediate recall test [IRT], animal fluency test [AFT], and digit symbol substitution test [DSST]). Cognitive performance was measured by these three tests, and individuals scoring below the lowest quartile were categorized as cognitive impairment. Sensitivity analysis, including dose-response curves, subgroup analyses, interaction effects, per 1 SD, and quartiles, were performed to ensure the accuracy of the conclusion. Results: A total of 2896 participants over the age of 60 were included in this study. In the adjusted final model, the association between vitamin B1 intake and low cognitive performance in old age was statistically significant, with the following odds ratios (ORs) and 95% confidence intervals (CIs): IRT, 0.75 (0.57, 0.97), P = 0.018; AFT, 0.68 (0.50, 0.92), P = 0.007; DSST, 0.71 (0.54, 0.92), P = 0.005. Subgroup analyses showed that this association was statistically significant among males, white, low-education, and no memory impairment. The results of the sensitivity analyses confirmed the association between VB1 and cognitive function in old age and the absence of interactions in the final calibrated model. Conclusion: Dietary vitamin B1 intake is negatively associated with cognitive performance in older adults.

Total muscle-to-fat ratio influences urinary incontinence in United States adult women: a population-based study.

Purpose: This study aims to investigate the relationship between the total muscle-to-fat ratio (tMFR) and female urinary incontinence (UI), determine whether tMFR can serve as a useful index for predicting UI, and identify factors that may influence this relationship. Methods: We retrospectively analyzed data from 4391 adult women participating in the National Health and Nutrition Examination Survey (NHANES) conducted between 2011 and 2018. The correlation between tMFR and UI was examined using a dose-response curve generated through a restricted cubic spline (RCS) function, LASSO and multivariate logistic regression. Furthermore, predictive models were constructed incorporating factors such as age, race, hypertension, diabetes, cotinine levels, and tMFR. The performance of these predictive models was evaluated using training and test datasets, employing calibration curves, receiver operating characteristic curves, and clinical decision curves. Mediation effects were also analyzed to explore potential relationships between tMFR and female UI. Results: In a sample of 4391 adult women, 1073 (24.4%) self-reported experiencing UI, while 3318 (75.6%) reported not having UI. Based on the analyses involving LASSO regression and multivariate logistic regression, it was found that tMFR exhibited a negative association with UI (OR = 0.599, 95% CI: 0.497-0.719, P < 0.001). The results from the restricted cubic spline chart indicated a decreasing risk of UI in women as tMFR increased. Furthermore, the model constructed based on logistic regression analysis demonstrated a certain level of accuracy (in the training dataset: area under the curve (AUC) = 0.663; in the test dataset: AUC = 0.662) and clinical applicability. The mediation analysis revealed that the influence of tMFR on the occurrence of UI in women might potentially occur through the blood index lymphocyte count (P = 0.040). Conclusion: A high tMFR serves as a protective factor against UI in women. Furthermore, lymphocyte might be involved in the relationship between tMFR and female UI.

Predictors of divorce and duration of marriage among first marriage women in Dejne administrative town.

Divorce is a common occurrence in the marital lives of spouses. Consequently, numerous divorced spouses and their children face various social, economic, physiological, and health problems after breaking their marriage. This study aimed to identify the predictors of divorce and the duration of marriage. We conducted a community-based cross-sectional study among 423 randomly selected residents of Dejen Township in April 2020, of which only 369 respondents met the study inclusion criteria. We used structured questionnaires to collect data. The predictors of divorce and duration of marriage were analyzed using binary logistic regression and the Gompertz regression model, respectively. A p value less than 0.05 was used to express statistical significance. The prevalence of divorce was 21.14% [95% CI (19.01-23.27%)]. Half of these women broke up their marriage after 11 years. A high age difference (7 or more years) between spouses, an early marriage, infertility among women, the presence of third parties, women without formal education, women in the workforce, sexually dissatisfied women, women who did not live together with their husbands at the same address, partner violence, marital control behaviour of husbands, drug-abused husbands, spouses without children, and women who knew multiple sexual partners were the significant predictors of divorce. Partner violence, sexually dissatisfied women, women who made their own marriage decisions, marital control behaviour of husbands, women who did not live together with their husbands at the same address, drug-abused husbands and spouses without children were significant predictors of shorter marriage durations. In this study, the prevalence of divorce was high. Therefore, a community-based, integrated strategy is needed to minimize the divorce rate.

Prevalence and risk factors associated with under-five years children diarrhea in Malawi: Application of survey logistic regression.

Background: Diarrhea is a leading cause of illness and mortality among children under five, posing a significant public health challenge in Malawi. The current study assesses the prevalence and risk factors linked to diarrhea among under-five children in Malawi. Method: The researcher used the Malawi Multiple Indicator Cluster Survey (MICS) 2019-20 as the dataset for this study. Due to the complex sampling design, survey logistic regression was used to accomplish the study objectives. The sample size was 15569 children who were aged under five. Results: The study found that the prevalence of diarrhea was 24.9%, with a higher percentage observed among children aged 12-23 months (38.5%) compared to other age groups. Additionally, children from the southern region had a higher prevalence of diarrhea at 27% compared to those from the northern region at 19.3%. Children from the poorest households also had a higher prevalence of diarrhea at 28.9% compared to those from the richest households at 22.6%. Furthermore, children with fever had a higher prevalence of diarrhea at 33.3% compared to those who did not have fever at 19.4%. Conclusion: The current study concluded that the prevalence of diarrhea was higher among children aged 12-23 months. Subsequently, policymakers should apply policies to reduce this high prevalence among this age group of children. In addition, the government needs special consideration in diarrhea control for children from the southern region because of the high prevalence of the disease compared to the other regions in Malawi. My study can help policymakers understand the scope and nature of the problem, which can notify the development of policies and programs intended to decrease the prevalence of risk factors and enhance child health outcomes.

Utility of the LACE index to assess risk of mortality and readmission in patients with spinal infections.

Retrospective cohort study. To assess the utility of the LACE index for predicting death and readmission in patients with spinal infections (SI). SIs are severe conditions, and their incidence has increased in recent years. The LACE (Length of stay, Acuity of admission, Comorbidities, Emergency department visits) index quantifies the risk of mortality or unplanned readmission. It has not yet been validated for SIs. LACE indices were calculated for all adult patients who underwent surgery for spinal infection between 2012 and 2021. Data were collected from a single academic teaching hospital. Outcome measures included the LACE index, mortality, and readmission rate within 30 and 90 days. In total, 164 patients were analyzed. Mean age was 64.6 (± 15.1) years, 73 (45%) were female. Ten (6.1%) patients died within 30 days and 16 (9.8%) died within 90 days after discharge. Mean LACE indices were 13.4 (± 3.6) and 13.8 (± 3.0) for the deceased patients, compared to 11.0 (± 2.8) and 10.8 (± 2.8) for surviving patients (p = 0.01, p < 0.001), respectively. Thirty-seven (22.6%) patients were readmitted ≤ 30 days and 48 (29.3%) were readmitted ≤ 90 days. Readmitted patients had a significantly higher mean LACE index compared to non-readmitted patients (12.9 ± 2.1 vs. 10.6 ± 2.9, < 0.001 and 12.8 ± 2.3 vs. 10.4 ± 2.8, p < 0.001, respectively). ROC analysis for either death or readmission within 30 days estimated a cut-off LACE index of 12.0 points (area under the curve [AUC] 95% CI, 0.757 [0.681-0.833]) with a sensitivity of 70% and specificity of 69%. Patients with SI had high LACE indices that were associated with high mortality and readmission rates. The LACE index can be applied to this patient population to predict the risk of early death or unplanned readmission.

Establishment and validation of a multivariate logistic model for risk factors of thyroid nodules using lasso regression screening.

Objective: This study aims to analyze the association between the occurrence of thyroid nodules and various factors and to establish a risk factor model for thyroid nodules. Methods: The study population was divided into two groups: a group with thyroid nodules and a group without thyroid nodules. Regression with the least absolute shrinkage and selection operator (Lasso) was applied to the complete dataset for variable selection. Binary logistic regression was used to analyze the relationship between various influencing factors and the prevalence of thyroid nodules. Results: Based on the screening results of Lasso regression and the subsequent establishment of the Binary Logistic Regression Model on the training dataset, it was found that advanced age (OR=1.046, 95% CI: 1.033-1.060), females (OR = 1.709, 95% CI: 1.342-2.181), overweight individuals (OR = 1.546, 95% CI: 1.165-2.058), individuals with impaired fasting glucose (OR = 1.590, 95% CI: 1.193-2.122), and those with dyslipidemia (OR = 1.588, 95% CI: 1.197-2.112) were potential risk factors for thyroid nodule disease (p<0.05). The area under the curve (AUC) of the receiver operating characteristic (ROC) curve for the Binary Logistic Regression Model is 0.68 (95% CI: 0.64-0.72). Conclusions: advanced age, females, overweight individuals, those with impaired fasting glucose, and individuals with dyslipidemia are potential risk factors for thyroid nodule disease.

Predictors of fuel poverty and the equity of local fuel poverty support: secondary analysis of data from Bradford, England.

AIMS: Addressing fuel poverty is a critical public health issue given its recent rise in prevalence across Europe. Although previous research identifies national risk markers of fuel poverty, evidence is lacking on whether these are consistent across local geographies, and the equity of local interventions. In the UK's current economic climate, it is more crucial than ever that services benefit households in greatest need. This study aimed to determine significant predictors of fuel poverty among households in Bradford, England, comparing them to national-level predictors, and evaluate if households possessing significant fuel poverty predictors were equitably referred to a local fuel poverty service (Warm Homes Healthy People, WHHP). METHODS: A multivariate logistic regression model determined significant fuel poverty predictors in Bradford using household-level data from the Energy Saving Trust and the Low Income High Costs fuel poverty definition. Statistical testing highlighted significant differences in predictors of fuel poverty between households referred to WHHP and all Bradford households. RESULTS: Significant (p < .05) predictors of fuel poverty included: living in an area with lower average household incomes and higher proportion of ethnic minority individuals, and living in a property with a lower energy efficiency rating. Households living in a detached or older property, and homeowners were more likely to be fuel poor. Differences in the direction of the relationship with fuel poverty were identified between some national and local predictors. Most predictors were significantly (p < .05) overrepresented among WHHP households, suggesting equitable service reach. Ethnic minorities, younger people, and multiperson households were underrepresented. CONCLUSIONS: Local fuel poverty predictors were similar to many national-level predictors, but identified differences in the direction of the relationship between some national and local predictors reaffirm the value of locally focused research. WHHP successfully targeted households possessing key predictors, but should ensure that ethnic minorities, younger people, and multiperson households are equitably referred.

Interpretable machine learning in predicting drug-induced liver injury among tuberculosis patients: model development and validation study.

BACKGROUND: The objective of this research was to create and validate an interpretable prediction model for drug-induced liver injury (DILI) during tuberculosis (TB) treatment. METHODS: A dataset of TB patients from Ningbo City was used to develop models employing the eXtreme Gradient Boosting (XGBoost), random forest (RF), and the least absolute shrinkage and selection operator (LASSO) logistic algorithms. The model's performance was evaluated through various metrics, including the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPR) alongside the decision curve. The Shapley Additive exPlanations (SHAP) method was used to interpret the variable contributions of the superior model. RESULTS: A total of 7,071 TB patients were identified from the regional healthcare dataset. The study cohort consisted of individuals with a median age of 47 years, 68.0% of whom were male, and 16.3% developed DILI. We utilized part of the high dimensional propensity score (HDPS) method to identify relevant variables and obtained a total of 424 variables. From these, 37 variables were selected for inclusion in a logistic model using LASSO. The dataset was then split into training and validation sets according to a 7:3 ratio. In the validation dataset, the XGBoost model displayed improved overall performance, with an AUROC of 0.89, an AUPR of 0.75, an F1 score of 0.57, and a Brier score of 0.07. Both SHAP analysis and XGBoost model highlighted the contribution of baseline liver-related ailments such as DILI, drug-induced hepatitis (DIH), and fatty liver disease (FLD). Age, alanine transaminase (ALT), and total bilirubin (Tbil) were also linked to DILI status. CONCLUSION: XGBoost demonstrates improved predictive performance compared to RF and LASSO logistic in this study. Moreover, the introduction of the SHAP method enhances the clinical understanding and potential application of the model. For further research, external validation and more detailed feature integration are necessary.

Efficacy of Random Forest Models in Predicting Multidrug-Resistant Gram-Negative Bacterial Nosocomial Infections Compared to Traditional Logistic Regression Models.

This study evaluates whether random forest (RF) models are as effective as traditional Logistic Regression (LR) models in predicting multidrug-resistant Gram-negative bacterial nosocomial infections. Data were collected from 541 patients with hospital-acquired Gram-negative bacterial infections at two tertiary-level hospitals in Urumqi, Xinjiang, China, from August 2022 to November 2023. Relevant literature informed the selection of significant predictors based on patients' pre-infection clinical information and medication history. The data were split into a training set of 379 cases and a validation set of 162 cases, adhering to a 7:3 ratio. Both RF and LR models were developed using the training set and subsequently evaluated on the validation set. The LR model achieved an accuracy of 84.57%, sensitivity of 82.89%, specificity of 80.10%, positive predictive value of 84%, negative predictive value of 85.06%, and a Yoden index of 0.69. In contrast, the RF model demonstrated superior performance with an accuracy of 89.51%, sensitivity of 90.79%, specificity of 88.37%, positive predictive value of 87.34%, negative predictive value of 91.57%, and a Yoden index of 0.79. Receiver operating characteristic curve analysis revealed an area under the curve of 0.91 for the LR model and 0.94 for the RF model. These findings indicate that the RF model surpasses the LR model in specificity, sensitivity, and accuracy in predicting hospital-acquired multidrug-resistant Gram-negative infections, showcasing its greater potential for clinical application.