Most screening tests for T2DM in use today were developed using multivariate regression methods that are often further simplified to allow transformation into a scoring formula. The increasing volume ...of electronically collected data opened the opportunity to develop more complex, accurate prediction models that can be continuously updated using machine learning approaches. This study compares machine learning-based prediction models (i.e. Glmnet, RF, XGBoost, LightGBM) to commonly used regression models for prediction of undiagnosed T2DM. The performance in prediction of fasting plasma glucose level was measured using 100 bootstrap iterations in different subsets of data simulating new incoming data in 6-month batches. With 6 months of data available, simple regression model performed with the lowest average RMSE of 0.838, followed by RF (0.842), LightGBM (0.846), Glmnet (0.859) and XGBoost (0.881). When more data were added, Glmnet improved with the highest rate (+ 3.4%). The highest level of variable selection stability over time was observed with LightGBM models. Our results show no clinically relevant improvement when more sophisticated prediction models were used. Since higher stability of selected variables over time contributes to simpler interpretation of the models, interpretability and model calibration should also be considered in development of clinical prediction models.
Abstract
This study presents the results of a network-based analysis of health related quality of life (HRQoL) among Slovenian adolescents. The study aimed to examine the relationship between HRQoL ...and mental well-being among adolescents of different age and gender groups. A cross-sectional study was conducted from November 2019 to January 2020 in 16 primary and 9 secondary schools in Slovenia. The KIDSCREEN-27 scale was used to collect the data on HRQoL, and the Warwick–Edinburgh Mental Well-being Scale to collect data on mental well-being. We used network model trees to demonstrate differences in psychometric network structure measuring correlations between different concepts in adolescent HRQoL. A total of 2972 students aged 10–19 years participated in the study. The significant split in the network tree (
p
< 0.001) indicated differences in relations between HRQoL subscale scores and mental well-being score among adolescents younger than 12 years old. In comparison to older adolescents the correlation between mental well-being and mood scores was significantly weaker in this group of the youngest participants (p < 0.001). A network model tree analysis also uncovered an interesting pattern based on gender and age (
p
< 0.013) where a correlation between mood and family support became weaker for female at the age of 12 and for male at the age of 16. Data mining techniques have recently been used by healthcare researchers and professionals. Network-based analysis is an innovative alternative to classical approaches in HRQoL research. In this study we demonstrate the significant differences in the perceptions of HRQoL and mental well-being among adolescents in different age and gender groups that were discovered using tree-based network analysis.
There is a need of ensuring that learning (ML) models are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end‐users. Further, ...interpretable ML models allow healthcare experts to make reasonable and data‐driven decisions to provide personalized decisions that can ultimately lead to higher quality of service in healthcare. Generally, we can classify interpretability approaches in two groups where the first focuses on personalized interpretation (local interpretability) while the second summarizes prediction models on a population level (global interpretability). Alternatively, we can group interpretability methods into model‐specific techniques, which are designed to interpret predictions generated by a specific model, such as a neural network, and model‐agnostic approaches, which provide easy‐to‐understand explanations of predictions made by any ML model. Here, we give an overview of interpretability approaches using structured data and provide examples of practical interpretability of ML in different areas of healthcare, including prediction of health‐related outcomes, optimizing treatments, or improving the efficiency of screening for specific conditions. Further, we outline future directions for interpretable ML and highlight the importance of developing algorithmic solutions that can enable ML driven decision making in high‐stakes healthcare problems.
This article is categorized under:
Application Areas > Health Care
Four groups of machine learning models for prediction in healthcare based on their interpretability characteristics
Background Physical activity is essential to maternal and infant health. Healthcare professionals should inform pregnant women about benefits of physical activity to prevent possible health issues. ...Those recommendations should elaborate on relevant contemporary evidence. The aim of this study was to review evidence-based recommendations for physical activity during pregnancy. Methods A systematic search, analysis and synthesis of conducted randomised controlled trials (RCTs) was conducted from October 2021 to June 2022 in following databases: PubMed, CINAHL, ScienceDirect and Web of Science. Literature was searched using inclusion and exclusion criteria and following PRISMA recommendations. Results Benefits for pregnant-women health and well-being were reported while performing aerobic exercise, lumbar stabilization and stretching exercise, water exercise, nerve and tendon-slip exercise, resistance training and strength training. For all exercise modalities it is recommended to perform moderate intensity activities during the whole time of pregnancy. Conclusions This systematic literature review supplements current knowledge on physical activity of pregnant women. Exercise interventions are listed and suggested in an integrative model with physical-fitness components to contextualize and promote physical activity among pregnant women. Keywords: Exercise, Intervention, Sport, Lifestyle, Health outcome
There are many methods available for measuring social support and quality of life (QoL) of adolescents, of these, the KIDSCREEN tools are most widely used. Thus, we aimed to translate and validate ...the KIDSCREEN-27 scale for the usage among adolescents aged between 10 and 19 years old in Slovenia.
A cross-sectional study was conducted among 2852 adolescents in primary and secondary school from November 2019 to January 2020 in Slovenia. 6-steps method of validation was used to test psychometric properties of the KIDSCREEN-27 scale. We checked descriptive statistics, performed a Mokken scale analysis, parametric item response theory, factor analysis, classical test theory and total (sub)scale scores.
All five subscales of the KIDSCREEN-27 formed a unidimensional scale with good homogeneity and reliability. The confirmatory factor analysis showed poor fit in user model versus baseline model metrics (CFI = 0.847; TLI = 0.862) and good fit in root mean square error (RMSEA = 0.072; p(χ
) < 0.001). A scale reliability was calculated using Cronbach's α (0.93), beta (0.86), G6 (0.95) and omega (0.93).
The questionnaire showed average psychometric properties and can be used among adolescents in Slovenia to find out about their quality of life. Further research is needed to explore why fit in user model metrics is poor.
Emotional intelligence in nursing is of global interest. International studies identify that emotional intelligence influences nurses' work and relationships with patients. It is associated with ...compassion and care. Nursing students scored higher on measures of emotional intelligence compared to students of other study programmes. The level of emotional intelligence increases with age and tends to be higher in women.
This study aims to measure the differences in emotional intelligence between nursing students with previous caring experience and those without; to examine the effects of gender on emotional intelligence scores; and to test whether nursing students score higher than engineering colleagues on emotional intelligence measures.
A cross-sectional descriptive study design was used.
The study included 113 nursing and 104 engineering students at the beginning of their first year of study at a university in Slovenia.
Emotional intelligence was measured using the Trait Emotional Intelligence Questionnaire (TEIQue) and Schutte Self Report Emotional Intelligence Test (SSEIT).
Shapiro-Wilk's test of normality was used to test the sample distribution, while the differences in mean values were tested using Student t-test of independent samples.
Emotional intelligence was higher in nursing students (n = 113) than engineering students (n = 104) in both measures TEIQue t = 3.972; p < 0.001; SSEIT t = 8.288; p < 0.001. Although nursing female students achieved higher emotional intelligence scores than male students on both measures, the difference was not statistically significant TEIQue t = −0.839; p = 0.403; SSEIT t = −1.159; p = 0.249. EI scores in nursing students with previous caring experience were not higher compared to students without such experience for any measure TEIQue t = −1.633; p = 0.105; SSEIT t = −0.595; p = 0.553.
Emotional intelligence was higher in nursing than engineering students, and slightly higher in women than men. It was not associated with previous caring experience.
•The level of emotional intelligence (EI) tends to be higher in women compared to men.•No statistically significant difference in EI for students with previous caring experience•The level of EI was higher in nursing students compared to engineering students.
Healthcare professionals in healthcare systems need access to freely available, real-time, evidence-based mortality risk prediction smartphone applications to facilitate resource allocation. The ...objective of this study is to evaluate the quality of smartphone mobile health applications that include mortality prediction models, and corresponding information quality. We conducted a systematic review of commercially available smartphone applications in Google Play for Android, and iTunes for iOS smartphone applications. We performed initial screening, data extraction, and rated smartphone application quality using the Mobile Application Rating Scale: user version (uMARS). The information quality of smartphone applications was evaluated using two patient vignettes, representing low and high risk of mortality, based on critical care data from the Medical Information Mart for Intensive Care (MIMIC) III database. Out of 3051 evaluated smartphone applications, 33 met our final inclusion criteria. We identified 21 discrete mortality risk prediction models in smartphone applications. The most common mortality predicting models were Sequential Organ Failure Assessment (SOFA) (
n
= 15) and Acute Physiology and Clinical Health Assessment II (
n
= 13). The smartphone applications with the highest quality uMARS scores were
Observation—NEWS 2
(4.64) for iOS smartphones, and
MDCalc Medical Calculator
(4.75) for Android smartphones. All SOFA-based smartphone applications provided consistent information quality with the original SOFA model for both the low and high-risk patient vignettes. We identified freely available, high-quality mortality risk prediction smartphone applications that can be used by healthcare professionals to make evidence-based decisions in critical care environments.
Aim
To explore nurses' perceptions on caring for children and adolescents who are victims of domestic violence, medical treatment of a victim of domestic violence and social aspects of recognizing ...this problem.
Background
Nurses are often first to recognize family violence; thus, they must have appropriate knowledge, skills and experience. Caring for child victims of domestic violence can be very stressful and emotional and nurses must have support when caring for them.
Methods
A qualitative study was conducted between June and August 2020. Interviews were conducted with paediatric nurses in a university hospital in Slovenia. Interviews were transcribed, coded and synthesized.
Results
We identified four main categories: violence against children; nurses' perception of caring for a child victim of domestic violence; medical treatment of a child who is a victim of domestic violence; the social aspect of recognizing violence against a child.
Conclusions
Domestic violence is present regardless of country, language and nationality. Early interventions should be directed towards recognition of the signs of domestic violence and care for victims of violence and caregivers.
Implications for Nursing Management
It is the responsibility of healthcare systems, hospital managers and nurses themselves to provide nursing care for children and adolescent victims of domestic violence based on the newest and best evidence.
Uvod: Temeljne značilnosti pediatrične zdravstvene nege so najboljša skrb za otroka, vzdrževanje integritete družine in otrokove rutine ter posebna znanja in spretnosti za negovanje otroka. Teorija ...medosebnih odnosov poudarja pomen medosebnega odnosa med medicinsko sestro in pacientom, ki se razvija skozi posamezne faze medsebojnega odnosa. Namen opisa, analize in vrednotenja teorije je ugotoviti možnost prenosa in uporabe teorije v praksi pediatrične zdravstvene nege.Metode: Uporabljen je bil pregled znanstvene in strokovne literature v naslednjih podatkovnih bazah: Web of Science, ProQuest, Medline, PubMed, ScienceDirect in CINAHL. Upoštevana so bila priporočila PRISMA. Identificirane zadetke smo uvrstili v nivo glede na hierarhijo dokazov in ocenili kakovost s pomočjo priporočil GRADE. Teorijo smo opisali, analizirali in evalvirali po modelu avtorice M. Pajnkihar.Rezultati: Izmed 321 identificiranih zadetkov je bilo v končno analizo vključeno 21 zadetkov. S pomočjo analize identificiranih zadetkov ugotavljamo, da večina avtorjev teorijo medosebnih odnosov opredeli kot teorijo srednjega obsega. V veliki meri se strinjajo, da je teorija enostavna in kompleksna ter ima jasno opisane koncepte, propozicije in predpostavke. Fenomen medosebnih odnosov je jasen medicinskim sestram v kliničnem okolju.Diskusija in zaključek: Teorija je uporabna za prakso zdravstvene nege, raziskovanje in izobraževanje. Pred aplikacijo teorije v prakso in izobraževanje na področju pediatrične zdravstvene nege je treba teorijo testirati. Teorija podpira razvoj medosebnih odnosov ter verbalne in neverbalne komunikacije in jo lahko uporabimo za prakso, podprto s teorijo.
Uvod: Vse pogosteje zaznavamo različne težave z načinom prehranjevanja pri otrocih. Otroci med 10. in 14. letom intenzivno rastejo in se razvijajo. Namen raziskave je bil ugotoviti vpliv izbirčnosti ...v prehrani otrok na njihovo prehranjenost v omenjeni starosti.Metode: Uporabljena je bila presečna opisna raziskava. Zajet je bil priložnostni vzorec osnovnošolcev zadnjega triletja. V raziskavi je sodelovalo 62 (49,2 %) učencev moškega in 64 (50,8 %) učencev ženskega spola zadnjega triletja ene izmed osnovnih šol v Sloveniji. Za zbiranje podatkov smo uporabili anketni vprašalnik, pridobili pa smo tudi podatke o telesni masi in višini. Uporabili smo opisno in sklepno statistiko (dvostranski test ANOVA).Rezultati: 37 (53,6 %) deklet in 28 (44,4 %) fantov je trdilo, da so izbirčni. Z dvostranskim testom ANOVA smo ugotovili, da obstaja povezava med izbirčnostjo in prehranjenostjo (p = 0,014). Pri dekletih je vidno večje odstopanje od prehranjenosti kot pri fantih.Diskusija in zaključek: Izbirčno prehranjevanje je v današnjem času zelo pogost problem, saj se je v njem prepoznala skoraj polovica vključenih učencev. Izbirčnost ima lahko negativne posledice v odrasli dobi. V starosti 10–14 let se ustvarjajo prehranjevalne navade, ki so lahko prisotne celotno življenje, zato je bistveno, da delujemo preventivno in s tem preprečimo negativne posledice. V prihodnosti bi bilo treba raziskovanje usmeriti v preventivne dejavnosti in promocijo zdravega prehranjevanja.