Nevin Manimala

Microbiome. 2025 Mar 3;13(1):64. doi: 10.1186/s40168-025-02041-w.

ABSTRACT

BACKGROUND: The microbiome is a complex ecosystem of interdependent taxa that has traditionally been studied through cross-sectional studies. However, longitudinal microbiome studies are becoming increasingly popular. These studies enable researchers to infer taxa associations towards the understanding of coexistence, competition, and collaboration between microbes across time. Traditional metrics for association analysis, such as correlation, are limited due to the data characteristics of microbiome data (sparse, compositional, multivariate). Several network inference methods have been proposed, but have been largely unexplored in a longitudinal setting.

RESULTS: We introduce LUPINE (LongitUdinal modelling with Partial least squares regression for NEtwork inference), a novel approach that leverages on conditional independence and low-dimensional data representation. This method is specifically designed to handle scenarios with small sample sizes and small number of time points. LUPINE is the first method of its kind to infer microbial networks across time, while considering information from all past time points and is thus able to capture dynamic microbial interactions that evolve over time. We validate LUPINE and its variant, LUPINE_single (for single time point analysis) in simulated data and four case studies, where we highlight LUPINE’s ability to identify relevant taxa in each study context, across different experimental designs (mouse and human studies, with or without interventions, and short or long time courses). To detect changes in the networks across time and groups or in response to external disturbances, we used different metrics to compare the inferred networks.

CONCLUSIONS: LUPINE is a simple yet innovative network inference methodology that is suitable for, but not limited to, analysing longitudinal microbiome data. The R code and data are publicly available for readers interested in applying these new methods to their studies. Video Abstract.

PMID:40033386 | DOI:10.1186/s40168-025-02041-w

Microbiome. 2025 Mar 3;13(1):64. doi: 10.1186/s40168-025-02041-w.

ABSTRACT

BACKGROUND: The microbiome is a complex ecosystem of interdependent taxa that has traditionally been studied through cross-sectional studies. However, longitudinal microbiome studies are becoming increasingly popular. These studies enable researchers to infer taxa associations towards the understanding of coexistence, competition, and collaboration between microbes across time. Traditional metrics for association analysis, such as correlation, are limited due to the data characteristics of microbiome data (sparse, compositional, multivariate). Several network inference methods have been proposed, but have been largely unexplored in a longitudinal setting.

RESULTS: We introduce LUPINE (LongitUdinal modelling with Partial least squares regression for NEtwork inference), a novel approach that leverages on conditional independence and low-dimensional data representation. This method is specifically designed to handle scenarios with small sample sizes and small number of time points. LUPINE is the first method of its kind to infer microbial networks across time, while considering information from all past time points and is thus able to capture dynamic microbial interactions that evolve over time. We validate LUPINE and its variant, LUPINE_single (for single time point analysis) in simulated data and four case studies, where we highlight LUPINE’s ability to identify relevant taxa in each study context, across different experimental designs (mouse and human studies, with or without interventions, and short or long time courses). To detect changes in the networks across time and groups or in response to external disturbances, we used different metrics to compare the inferred networks.

CONCLUSIONS: LUPINE is a simple yet innovative network inference methodology that is suitable for, but not limited to, analysing longitudinal microbiome data. The R code and data are publicly available for readers interested in applying these new methods to their studies. Video Abstract.

PMID:40033386 | DOI:10.1186/s40168-025-02041-w

BMC Med Inform Decis Mak. 2025 Mar 3;25(1):106. doi: 10.1186/s12911-025-02927-7.

ABSTRACT

BACKGROUND: Duration of surgery (DOS) varies substantially for patients with hip and knee arthroplasty (HA/KA) and is a major risk factor for adverse events. We therefore aimed (1) to identify whether machine learning can predict DOS in HA/KA patients using retrospective data available before surgery with reasonable performance, (2) to compare whether machine learning is able to outperform multivariable regression in predictive performance and (3) to identify the most important predictor variables for DOS both in a multi- and single-hospital context.

METHODS: eXtreme Gradient Boosting (XGBoost) and multivariable linear regression were used for predictions. Both models were applied to both the whole dataset which included multiple hospitals (3,704 patients), and a single-hospital dataset (1,815 patients) of the hospital with the highest case-volumes of our sample. Data was split into training (75%) and test data (25%) for both datasets. Models were trained using 5-fold cross-validation (CV) on the training datasets and applied to test data for performance comparison.

RESULTS: On test data in the multi-hospital setting, the mean absolute error (MAE) was 12.13 min (HA) / 13.61 min (KA) for XGBoost. In the single-hospital analysis, performance on test data was MAE 10.87 min (HA) / MAE 12.53 min (KA) for XGBoost. Predictive ability of XGBoost was tended to be better than of regression in all setting, however not statistically significantly. Important predictors for XGBoost were physician experience, age, body mass index, patient reported outcome measures and, for the multi-hospital analysis, the hospital.

CONCLUSION: Machine learning can predict DOS in both a multi-hospital and single-hospital setting with reasonable performance. Performance between regression and machine learning differed slightly, however insignificantly, while larger datasets may improve predictive performance. The study found that hospital indicators matter in the multi-hospital setting despite controlling for various variables, highlighting potential quality differences between hospitals.

TRIAL REGISTRATION: The study was registered at the German Clinical Trials Register (DRKS) under DRKS00019916.

PMID:40033378 | DOI:10.1186/s12911-025-02927-7

BMC Med Inform Decis Mak. 2025 Mar 3;25(1):106. doi: 10.1186/s12911-025-02927-7.

ABSTRACT

BACKGROUND: Duration of surgery (DOS) varies substantially for patients with hip and knee arthroplasty (HA/KA) and is a major risk factor for adverse events. We therefore aimed (1) to identify whether machine learning can predict DOS in HA/KA patients using retrospective data available before surgery with reasonable performance, (2) to compare whether machine learning is able to outperform multivariable regression in predictive performance and (3) to identify the most important predictor variables for DOS both in a multi- and single-hospital context.

METHODS: eXtreme Gradient Boosting (XGBoost) and multivariable linear regression were used for predictions. Both models were applied to both the whole dataset which included multiple hospitals (3,704 patients), and a single-hospital dataset (1,815 patients) of the hospital with the highest case-volumes of our sample. Data was split into training (75%) and test data (25%) for both datasets. Models were trained using 5-fold cross-validation (CV) on the training datasets and applied to test data for performance comparison.

RESULTS: On test data in the multi-hospital setting, the mean absolute error (MAE) was 12.13 min (HA) / 13.61 min (KA) for XGBoost. In the single-hospital analysis, performance on test data was MAE 10.87 min (HA) / MAE 12.53 min (KA) for XGBoost. Predictive ability of XGBoost was tended to be better than of regression in all setting, however not statistically significantly. Important predictors for XGBoost were physician experience, age, body mass index, patient reported outcome measures and, for the multi-hospital analysis, the hospital.

CONCLUSION: Machine learning can predict DOS in both a multi-hospital and single-hospital setting with reasonable performance. Performance between regression and machine learning differed slightly, however insignificantly, while larger datasets may improve predictive performance. The study found that hospital indicators matter in the multi-hospital setting despite controlling for various variables, highlighting potential quality differences between hospitals.

TRIAL REGISTRATION: The study was registered at the German Clinical Trials Register (DRKS) under DRKS00019916.

PMID:40033378 | DOI:10.1186/s12911-025-02927-7

Int J Behav Nutr Phys Act. 2025 Mar 3;22(1):25. doi: 10.1186/s12966-025-01716-9.

ABSTRACT

BACKGROUND: The time spent physically active outside of school (e.g., extracurricular physical activity) is an important contributor to children’s total daily physical activity for health and well-being. Little is known about the opportunities available to children to engage in extracurricular physical activity from low- to middle-income countries. This study aims to answer the question: What are the main perceived barriers and facilitators of extracurricular physical activity among school-age children in Mexico?

METHODS: A multi-method cross-sectional study was performed. Six focus groups with children (aged 9-12 years), six focus groups with parents, 10 one-on-one interviews with parents, 12 interviews with teachers, and six interviews with head teachers were conducted across Campeche, Morelos, and Mexico State, Mexico. A questionnaire was applied to explore children’s physical activity frequency and preferences for time inside and outside of school. Qualitative data analyses were performed with inductive thematic analysis supported with NVivo software. Quantitative data were analysed with descriptive statistics using IBM SPSS 26.

RESULTS: Three main themes summarise the study’s findings: (1) how children spend their time outside of school, (2) the places that children access, and (3) the social environment for physical activity outside of the school. The data suggest that children in Mexico dedicate their spare time to screen, work, do housework, or perform unstructured physical activity mostly at home instead of playing sports or actively outdoors. Family support, enjoyment of physical activity, access to programs and facilities, time, living in a housing complex with open common areas, and mild weather were important facilitators identified. 69.4% of children engage in extracurricular physical activity, none of which was provided by schools. More children commute by walking than riding a bike to and from school. Children living inland spent three times more time at home compared to those in seafront areas.

CONCLUSIONS: Children rely on their families to partake in extracurricular structured physical activity. Policies targeting children’s health and well-being should include school-based extracurricular physical activity programs.

PMID:40033367 | DOI:10.1186/s12966-025-01716-9

BMC Health Serv Res. 2025 Mar 4;25(1):330. doi: 10.1186/s12913-025-12456-8.

ABSTRACT

BACKGROUND: To enable people with stroke to achieve an active everyday life under altered conditions, the development of self-management programs is essential to facilitate the process of change that individuals must undergo. To improve access to self-management, internet-based solutions have been proposed. The aim of this study was to evaluate the feasibility of a novel internet-based intervention, “Strategies for Empowering activities in Everyday Life” (SEE, version 1.0), for clients with stroke.

METHODS: This feasibility study had a preposttest design without a control group and utilized a mixed-method approach. Data were collected through study-specific forms, outcome assessments, interviews, and field notes. Descriptive statistics and content analysis were subsequently applied.

RESULTS: The study involved fifteen clients and staff at clinics in a hospital-based open-care rehabilitation setting. The results indicate that SEE is feasible for clients with stroke. When adopted as expected, SEE has the potential to empower self-management and enhance engagement, balance, and values in everyday activities. The study also indicates that SEE is feasible in terms of adherent delivery of dosage, acceptability, and value, as perceived by clients, occupational therapists, and clinic managers. However, adjustments are needed in the study design, in terms of recruitment strategies, the selection of assessor-based outcome assessment, and the evaluation of adherence. Additionally, the educational program for professionals should be enhanced to better support the implementation of SEE.

CONCLUSION: After the study design, intervention, and educational program are refined, SEE can be prepared for a pilot randomized controlled trial.

TRIAL REGISTRATION: clinicaltrails.gov NCT04588116, date of registration: 8th October 2020.

PMID:40033363 | DOI:10.1186/s12913-025-12456-8

BMC Nurs. 2025 Mar 3;24(1):236. doi: 10.1186/s12912-025-02839-x.

ABSTRACT

BACKGROUND: Needle-stick injuries (NSIs) pose a substantial occupational hazard, exposing healthcare professionals to potentially infectious diseases. Nurses’ clinical competence plays a crucial role in preventing and mitigating the incidence of NSIs. This study aimed to investigate the relationship between clinical competence and the incidence of NSIs, as well as the factors contributing to these injuries, among nurses in Fars Province, southern Iran, from March 2023 to May 2023.

METHODS: This descriptive cross-sectional study included 264 nurses selected through convenience sampling. All participants were employed in various departments of teaching hospitals in Fasa city, southern Iran, during the study period. Data were collected using a demographic questionnaire and a clinical competence questionnaire specifically developed for nurses. The demographic questionnaire captured variables such as age, gender, marital status, educational background, departmental assignment, work experience, and weekly working hours. The clinical competence questionnaire consisted of 55 items assessing seven dimensions: clinical care, leadership, legal and ethical performance, professional development, interpersonal relationships, education and coaching, and critical thinking and research aptitude. Statistical analyses were performed using SPSS software (version 16), employing the Chi-square test, Kruskal-Wallis test, and multiple logistic regression analysis. A significance level of p < 0.05 was applied to all tests.

RESULTS: The findings revealed that 39.4% of the participating nurses exhibited high clinical competence, 51.5% demonstrated moderate competence, and 9.1% were classified as having low competence. Statistical analysis indicated a significant association between clinical competence levels and needle-stick status (P = 0.002). Moreover, a significant difference was identified between clinical competence levels and the frequency of NSIs (P = 0.001). A logistic regression model was employed to assess the likelihood of NSIs based on demographic variables. The results showed that 178 participants (67.42%) had experienced needle-stick or sharp injuries within the preceding year. Among these, 63 males (35.3%) and 115 females (64.6%) reported such incidents. The highest incidence of needle-stick and sharp injuries occurred in the Operating Room (91.7%), followed by Dialysis (88.9%), Pediatrics (80%), Surgical Intensive Care (76.5%), Emergency (74.3%), Women’s Surgery (70%), Post-Cardiac Intensive Care (69.2%), Oncology (63.6%), Internal Medicine (59.1%), Surgery and Infectious Diseases (54.5%), Laboratory and Cardiac Intensive Care (52.9%), Men’s Surgery (50%), and the Psychiatric Ward (41.2%).

CONCLUSIONS: Considering that the majority of nurses working in hospitals exhibited moderate to low levels of clinical competence, it is recommended that hospitals implement an annual clinical competence assessment for nurses. Regular evaluations and targeted training programs can enhance nurses’ competence levels, thereby improving patient care quality and reducing the incidence of NSIs among healthcare providers. Additionally, specific strategies should be developed and implemented in medical centers and hospitals to mitigate the risk of NSIs across all hospital departments, particularly in high-risk areas such as operating rooms and dialysis units, where the prevalence of NSIs is significantly higher.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40033355 | DOI:10.1186/s12912-025-02839-x

BMC Med Inform Decis Mak. 2025 Mar 3;25(1):105. doi: 10.1186/s12911-025-02937-5.

ABSTRACT

Current research on the association between demographic variables and dietary patterns with atherosclerotic cardiovascular disease (ASCVD) is limited in breadth and depth. This study aimed to construct a machine learning (ML) algorithm that can accurately and transparently establish correlations between demographic variables, dietary habits, and ASCVD. The dataset used in this research originates from the United States National Health and Nutrition Examination Survey (U.S. NHANES) spanning 1999-2018. Five ML models were developed to predict ASCVD, and the best-performing model was selected for further analysis. The study included 40,298 participants. Using 20 population characteristics, the eXtreme Gradient Boosting (XGBoost) model demonstrated high performance, achieving an area under the curve value of 0.8143 and an accuracy of 88.4%. The model showed a positive correlation between male sex and ASCVD risk, while age and smoking also exhibited positive associations with ASCVD risk. Dairy product intake exhibited a negative correlation, while a lower intake of refined grains did not reduce the risk of ASCVD. Additionally, the poverty income ratio and calorie intake exhibited non-linear associations with the disease. The XGBoost model demonstrated significant efficacy, and precision in determining the relationship between the demographic characteristics and dietary intake of participants in the U.S. NHANES 1999-2018 dataset and ASCVD.

PMID:40033349 | DOI:10.1186/s12911-025-02937-5

Scand J Trauma Resusc Emerg Med. 2025 Mar 3;33(1):35. doi: 10.1186/s13049-025-01350-1.

ABSTRACT

BACKGROUND: For preoxygenation, German guidelines consider non-invasive ventilation (NIV) as a possible method in prehospital trauma care in the absence of aspiration, severe head or face injuries, unconsciousness, or patient non-compliance. As data on the utilization and characteristics of patients receiving NIV are lacking, this study aims to identify predictors of NIV usage in trauma patients using machine learning and compare these findings with the current national guideline.

METHODS: A cross-regional registry of prehospital emergency services in southwestern Germany was searched for cases of emergency anesthesia in multiply injured patients in the period from 2018 to 2020. Initial vital signs, oxygen saturation, respiratory rate, heart rate, systolic blood pressure, Glasgow Coma Scale (GCS), injury pattern, shock index and age were examined using logistic regression. A decision tree algorithm was then applied in parallel to reduce the number of attributes, which were subsequently tested in several machine learning algorithms to predict the usage of NIV before the induction of anesthesia.

RESULTS: Of 992 patients with emergency anesthesia, 333 received NIV (34%). Attributes with a statistically significant influence (p < 0.05) in favour of NIV were bronchial spasm (odds ratio (OR) 119.75), dyspnea/cyanosis (OR 2.28), moderate and severe head injury (both OR 3.37) and the respiratory rate (OR 1.07). Main splitting points in the initial decision tree included auscultation (rhonchus and bronchial spasm), respiratory rate, heart rate, age, oxygen saturation and head injury with moderate head injury being more frequent in the NIV group (23% vs. 12%, p < 0.01). The rates of aspiration and the level of consciousness were equal in both groups (0.01% and median GCS 15, both p > 0.05). The prediction accuracy for NIV usage was high for all algorithms, except for multilayer perceptron and logistic regression. For instance, a Bayes Network yielded an AUC-ROC of 0.96 (95% CI, 0.95-0.96) and PRC-areas of 0.96 [0.96-0.96] for predicting and 0.95 [0.95-0.96] for excluding NIV usage.

CONCLUSIONS: Machine learning demonstrated an excellent categorizability of the cohort using only a few selected attributes. Injured patients without severe head injury who presented with dyspnea, cyanosis, or bronchial spasm were regularly preoxygenated with NIV, indicating a common prehospital practice. This usage appears to be in accordance with current German clinical guidelines. Further research should focus on other aspects of the decision making like airway anatomy and investigate the impact of preoxygenation with NIV in prehospital trauma care on relevant outcome parameters, as the current evidence level is limited.

PMID:40033329 | DOI:10.1186/s13049-025-01350-1

BMC Sports Sci Med Rehabil. 2025 Mar 3;17(1):34. doi: 10.1186/s13102-025-01088-4.

ABSTRACT

Performance analysis can provide coaches with a range of relevant information and support more informed decision-making. The objective of this research was to determine running performance (RP) within five-minute intervals when scoring and conceding goals in the UEFA Champions League (UCL). Matches from the UCL 2020/2021 season were analyzed, and relevant data were retrieved using the InStat Fitness semi-automatic video system. Statistical analysis employed one-way analysis of variance (ANOVA) for comparisons and partial eta squared (η2) to determine effect size. Team performance was determined by measuring total distance covered (TD) and high-intensity running (HIR) when the team scored a goal, conceded a goal, and when the score did not change. Our primary results indicated significant differences in three out of 20 five-minute intervals for the TD parameter and four out of 20 for HIR when teams scored goals. There were also significant differences in eight out of 20 intervals for TD and three out of 20 for HIR when teams conceded goals. In conclusion, significant goal concessions were observed during all the five-minute intervals in which teams substantially reduced their RP. From a practical point of view, coaches should be aware, especially in the context of the pacing strategy used, that team RP affects the scoreline directly and the match outcome indirectly.

PMID:40033321 | DOI:10.1186/s13102-025-01088-4