Prevalence of neonatal sepsis and associated factors among neonates admitted in the neonatal intensive care unit at Lira Regional Referral Hospital, Northern Uganda. by Brendah Katugume, JohnBaptist Muzungu, Nelson Okello, Eustes Kigongo, Deborah Andrinar Namutebi

“…The univariable analysis gave a general description of the data. Logistic regression analysis was used to show associations and the statistical significance was declared at a P value of 0.05 after multivariable analysis.…”
Get full text

Risk prediction models for dysphagia after radiotherapy among patients with head and neck cancer: a systematic review and meta-analysis by You Pu, Jin Yang, Lian Shui, Qianlong Tang, Xianqin Zhang, Guangguo Liu

“…Of these models, most were constructed based on logistic regression, while only two studies used machine learning methods. …”
Get full text

Evaluating the Impact of Data Transformation Techniques on the Performance and Interpretability of Software Defect Prediction Models by Yu Zhao, Zhiqiu Huang, Lina Gong, Yi Zhu, Qiao Yu, Yuxiang Gao

“…Through empirical research on (i) six classification techniques (random forest, decision tree, logistic regression, Naive Bayes, K-nearest neighbors, and multilayer perceptron), (ii) six performance evaluation indicators (Accuracy, Precision, Recall, F1, MCC, and AUC), (iii) two interpretable methods (permutation and SHAP), (iv) two feature importance measures (Top-k feature rank overlap and difference), and (v) three datasets (Promise, Relink, and AEEEM), our results show that the data transformation methods can significantly improve the performance of the SDP models and greatly affect the variation of the most important features. …”
Get full text

Prediction of postoperative myocardial injury in patients undergoing laparoscopic pheochromocytoma/paraganglioma resection: protocol for an ambispective cohort study by Yuguang Huang, Yuelun Zhang, Ling Lan, Yi Zhang, Ye Ma, Le Shen, Yifei Zhao, Yaohan Li

“…Stepwise and least absolute shrinkage and selection operator regression will be used for predictor selection. Multivariate logistic regression will be used to develop the prediction model, which will be presented as a nomogram. …”
Get full text

Mental health risk in human services work across Europe: the predictive role of employment in various sectors by Ágnes Győri, Éva Perpék, Szilvia Ádám

“…Finally, correlations were explored between perceived psychosocial risk factors and human vs. non-human services occupations, as well as contextual variables by applying multilevel logistic and multinomial regression analyses.ResultsThe prevalence of mental health risk was 45.1%. …”
Get full text

Knowledge, perceptions and practices associated with timing for breast cancer screening among female students at the University of Zimbabwe: A cross-sectional study by Peter Chikuvadze, Grace Nkhoma, Maxwell Mhlanga, Augustine Ndaimani

“…Associations between variables were tested using Chi-square, Fisher’s exact tests, and binary logistic regression. Results: Of the 139 participants, 85% were aged 20-25, single, and undergraduates. …”
Get full text

Seroprevalence and Associated Risk Factors of Foot and Mouth Disease in Cattle in West Shewa Zone, Ethiopia by Beyan Ahmed, Lencho Megersa, Getachew Mulatu, Mohammed Siraj, Gelma Boneya

“…The seroprevalence of foot and mouth disease in West Shewa Zone was found to be 40.4% (95% CI: 35.46–45.27) at an animal and 74.7% (95% CI: 65.58–83.85) at the herd level. Multivariable logistic regression analysis indicated that districts, breed, and animal composition were the potential risk factors of FMD seropositivity. …”
Get full text

Diagnosis Osteoporosis Risk: Using Machine Learning Algorithms Among Fasa Adults Cohort Study (FACS) by Saghar Tabib, Seyed Danial Alizadeh, Aref Andishgar, Babak Pezeshki, Omid Keshavarzian, Reza Tabrizi

“…Methods We analysed the data related to osteoporosis risk factors obtained from the Fasa Adults Cohort Study in eight ML methods, including logistic regression (LR), baseline LR, decision tree classifiers (DT), support vector classifiers (SVC), random forest classifiers (RF), linear discriminant analysis (LDA), K nearest neighbour classifiers (KNN) and extreme gradient boosting (XGB). …”
Get full text

Magnitude of Prompt HIV-Seropositive Status Disclosure to Partner and Associated Factors among Adult Clients on ART at Holeta Health Center, Central Ethiopia, 2020 by Guta Kebede, Adugna Dufera, Tufa Kolola, Teka Girma, Daniel Belema

“…Descriptive analysis was conducted to determine the magnitude of prompt HIV seropositive status disclosure to partner and multivariable logistic regression analysis was computed to identify factors associated with prompt HIV seropositive status disclosure. …”
Get full text

Validating the reproductive tract score (RTS) technique in pre-service buffalo heifers by Freddys Escalona-Ramírez, Jessenia Mercado-Carrillo, Balbino A. Jaimes-Vazques, Antonio Landaeta-Hernández

“…Data was analyzed by Logistic Regression. A linear and positive increase association (p<0.02) was observed between RTS and pregnancy rate (RTS=5:85%, RTS=4:80%, RTS=3:74%, RTS=2:62%, and RTS=1:50%) indicating a beneficial effect of reproductive tract maturity on pregnancy rate. …”
Get full text

Risk Factors of Noncompliance to Preventive Mass Drug Administration for Eliminating Lymphatic Filariasis: A Case-Control Study in Jawi District, Northwest Ethiopia by Fetene Mihretu, Gebeyehu Tsega, Melesse Belayneh, Mesafint Molla Adane

“…Then, data were entered and cleaned by using the EPI DATA software, and analyses were conducted using SPSS version 26. Finally, a logistic regression analysis technique was applied to identify the risk factors using adjusted odds ratio as measures of effect. …”
Get full text

Association of uric acid with the decline in estimated glomerular filtration rate in middle-aged and elderly populations: evidence based on the China Health and Retirement Longitud... by Ying Liang, Ming Lei, Liu Lin, Peijia Liu, Sini Cui, Kaiyuan Hu, Xinning Shao

“…Decline in eGFR was defined as an eGFR decrease of more than 25% or deterioration of the eGFR stage during the 4-year follow-up period. Logistic models corrected for multiple covariables were used to analyse the association of UA with the decline in eGFR.Results The median (IQR) concentrations of serum UA grouped by quartiles were 3.1 (0.6), 3.9 (0.3), 4.6 (0.4) and 5.7 (1.0) mg/dL, respectively. …”
Get full text

Long-term risk factors for developing Barrett’s oesophagus in patients with gastro-oesophageal reflux disease: a longitudinal cohort study by John F Dillon, Paul Brennan, James Cotton, James Carberry, Christopher J Byrne

“…In this study, we examined factors that influence BO development in people living with GORD.Design People living with GORD were recruited from an endoscopy unit with lifestyle, medical and prescribing history collected. Logistic regression analysis was undertaken to assess the effects of multiple parameters on the likelihood of developing BO.Results 1197 participants were recruited. …”
Get full text

Predicting Outcomes for Interhospital Transferred Patients of Emergency General Surgery by Brandon Cave, Daniel Najafali, William Gilliam, Jackson F. Barr, Christian Cain, Chris Yum, Jamie Palmer, Safura Tanveer, Emily Esposito, Quincy K. Tran

“…We used multivariable logistic regression and probit analysis to measure the association of patients’ clinical factors and their outcomes (mortality and survivors’ hospital length of stay [HLOS]). …”
Get full text

Quick sequential organ failure assessment score combined with other sepsis-related risk factors to predict in-hospital mortality: Post-hoc analysis of prospective multicenter study... by Ryo Ueno, Takateru Masubuchi, Atsushi Shiraishi, Satoshi Gando, Toshikazu Abe, Shigeki Kushimoto, Toshihiko Mayumi, Seitaro Fujishima, Akiyoshi Hagiwara, Toru Hifumi, Akira Endo, Takayuki Komatsu, Joji Kotani, Kohji Okamoto, Junichi Sasaki, Yasukazu Shiino, Yutaka Umemura

“…Different types of sepsis-related risk factors (demographic, functional, and laboratory values) were chosen from prior studies. A logistic regression model was used to assess the predictive value of qSOFA for in-hospital mortality in models based on the following combination of predictors: 1) qSOFA-Only; 2) qSOFA+Age; 3) qSOFA+Clinical Frailty Scale (CFS); 4) qSOFA+Charlson Comorbidity Index (CCI); 5) qSOFA+lactate levels; 6) qSOFA+Age+CCI+CFS+lactate levels. …”
Get full text

Elevated Plasma Level of 8-Hydroxy-2′-deoxyguanosine Is Associated with Primary Open-Angle Glaucoma by Altaf A. Kondkar, Taif A. Azad, Tahira Sultan, Essam A. Osman, Faisal A. Almobarak, Saleh A. Al-Obeidan

“…Plasma 8-OHdG had a sensitivity of 78% and specificity of 53%. In logistic regression analysis, 8-OHdG showed a significant effect on POAG outcome (p=0.016) independent of age, sex, smoking, and systemic diseases. …”
Get full text

Therapeutic Effect of Traditional Chinese Medicine on a Rat Model of Branch Retinal Vein Occlusion by Pan Long, Weiming Yan, Jianwen Liu, Manhong Li, Tao Chen, Zuoming Zhang, Jing An

Get full text

Factors influencing reselection of village doctors in rural-oriented tuition-waived medical education program in Shanghai, China: a cross-sectional study by Jing Gao, Juhua Zhang, Chenlei Shi, Aiqin Fan, Peng Zhang

“…Analysis of variance (ANOVA), chi-square tests and logistic regression analysis was conducted.ResultsA total of 419 questionnaires were collected. …”
Get full text

Unveiling the epidemiology and community perspectives on bovine brucellosis in North Shewa, Central Highlands of Ethiopia by Aweke Engdawork, Abdela Bulbula, Awoke Melak, Haileleul Negussie

“…Multivariable Firth’s bias-reduced logistic regression model was used to identify factors associated with brucellosis seropositivity. …”
Get full text

Excess mortality and associated community risk factors related to hurricane Maria in Puerto Rico by Kristen N Cowan, Diego E Zavala, Erick Suarez, José A Lopez-Rodriguez, Omar Alvarez

“…Geospatial analysis using Getis–Ord Gi* Statistic was used to determine if mortality clusters of 6 month mortality risk following hurricane Maria by census tract were statistically significant. Multinomial logistic regression was used to model the association between census tract level social vulnerability and being classified as higher or sustained risk of mortality in the 6 months following Hurricane Maria compared to the previous year’s mortality risk. …”
Get full text