| 1. |
- Beeton, Michael L., et al.
(author)
-
Mycoplasma pneumoniae infections, 11 countries in Europe and Israel, 2011 to 2016
- 2020
-
In: Eurosurveillance. - : EUR CENTRE DIS PREVENTION & CONTROL. - 1025-496X .- 1560-7917. ; 25:2, s. 39-51
-
Journal article (peer-reviewed)abstract
- Background: Mycoplasma pneumoniae is a leading cause of community-acquired pneumonia, with large epidemics previously described to occur every 4 to 7 years.Aim: To better understand the diagnostic methods used to detect M. pneumoniae; to better understand M. pneumoniae testing and surveillance in use; to identify epidemics; to determine detection number per age group, age demographics for positive detections, concurrence of epidemics and annual peaks across geographical areas; and to determine the effect of geographical location on the timing of epidemics.Methods: A questionnaire was sent in May 2016 to Mycoplasma experts with national or regional responsibility within the ESCMID Study Group for Mycoplasma and Chlamydia Infections in 17 countries across Europe and Israel, retrospectively requesting details on M. pneumoniae-positive samples from January 2011 to April 2016. The Moving Epidemic Method was used to determine epidemic periods and effect of country latitude across the countries for the five periods under investigation.Results: Representatives from 12 countries provided data on M. pneumoniae infections, accounting for 95,666 positive samples. Two laboratories initiated routine macrolide resistance testing since 2013. Between 2011 and 2016, three epidemics were identified: 2011/12, 2014/15 and 2015/16. The distribution of patient ages for M. pneumoniae-positive samples showed three patterns. During epidemic years, an association between country latitude and calendar week when epidemic periods began was noted.Conclusions: An association between epidemics and latitude was observed. Differences were noted in the age distribution of positive cases and detection methods used and practice. A lack of macrolide resistance monitoring was noted.
|
|
| 2. |
- Belsti, Yitayeh, et al.
(author)
-
Comparison of machine learning and conventional logistic regression-based prediction models for gestational diabetes in an ethnically diverse population : the Monash GDM Machine learning model
- 2023
-
In: International Journal of Medical Informatics. - : Elsevier. - 1386-5056 .- 1872-8243. ; 179
-
Journal article (peer-reviewed)abstract
- Background: Early identification of pregnant women at high risk of developing gestational diabetes (GDM) is desirable as effective lifestyle interventions are available to prevent GDM and to reduce associated adverse outcomes. Personalised probability of developing GDM during pregnancy can be determined using a risk prediction model. These models extend from traditional statistics to machine learning methods; however, accuracy remains sub-optimal.Objective: We aimed to compare multiple machine learning algorithms to develop GDM risk prediction models, then to determine the optimal model for predicting GDM.Methods: A supervised machine learning predictive analysis was performed on data from routine antenatal care at a large health service network from January 2016 to June 2021. Predictor set 1 were sourced from the existing, internationally validated Monash GDM model: GDM history, body mass index, ethnicity, age, family history of diabetes, and past poor obstetric history. New models with different predictors were developed, considering statistical principles with inclusion of more robust continuous and derivative variables. A randomly selected 80% dataset was used for model development, with 20% for validation. Performance measures, including calibration and discrimination metrics, were assessed. Decision curve analysis was performed.Results: Upon internal validation, the machine learning and logistic regression model's area under the curve (AUC) ranged from 71% to 93% across the different algorithms, with the best being the CatBoost Classifier (CBC). Based on the default cut-off point of 0.32, the performance of CBC on predictor set 4 was: Accuracy (85%), Precision (90%), Recall (78%), F1-score (84%), Sensitivity (81%), Specificity (90%), positive predictive value (92%), negative predictive value (78%), and Brier Score (0.39).Conclusions: In this study, machine learning approaches achieved the best predictive performance over traditional statistical methods, increasing from 75 to 93%. The CatBoost classifier method achieved the best with the model including continuous variables.
|
|
