| 1. |
- Kelly, D., et al.
(författare)
-
Improved screening of fall risk using free-living based accelerometer data
- 2022
-
Ingår i: Journal of Biomedical Informatics. - : Elsevier BV. - 1532-0464 .- 1532-0480. ; 131
-
Tidskriftsartikel (refereegranskat)abstract
- Falls are one of the most costly population health issues. Screening of older adults for fall risks can allow for earlier interventions and ultimately lead to better outcomes and reduced public health spending. This work proposes a solution to limitations in existing fall screening techniques by utilizing a hip-based accelerometer worn in free-living conditions. The work proposes techniques to extract fall risk features from periods of free-living ambulatory activity. Analysis of the proposed techniques is conducted and compared with existing screening methods using Functional Tests and Lab-based Gait Analysis. 1705 Older Adults from Umea (Sweden) were assessed. Data consisted of 1 Week of hip worn accelerometer data, gait measurements and performance metrics for 3 functional tests. Retrospective and Prospective fall data were also recorded based on the incidence of falls occurring 12 months before and after the study commencing respectively. Machine learning based experiments show accelerometer based measures perform best when predicting falls. Prospective falls had a sensitivity and specificity of 0.61 and 0.66 respectively while retrospective falls had a sensitivity and specificity of 0.61 and 0.68 respectively.
|
|
| 2. |
- Lundgren, Markus, et al.
(författare)
-
Analgesic antipyretic use among young children in the TEDDY study : No association with islet autoimmunity
- 2017
-
Ingår i: BMC Pediatrics. - : Springer Science and Business Media LLC. - 1471-2431. ; 17:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: The use of analgesic antipyretics (ANAP) in children have long been a matter of controversy. Data on their practical use on an individual level has, however, been scarce. There are indications of possible effects on glucose homeostasis and immune function related to the use of ANAP. The aim of this study was to analyze patterns of analgesic antipyretic use across the clinical centers of The Environmental Determinants of Diabetes in the Young (TEDDY) prospective cohort study and test if ANAP use was a risk factor for islet autoimmunity. Methods: Data were collected for 8542 children in the first 2.5 years of life. Incidence was analyzed using logistic regression with country and first child status as independent variables. Holm's procedure was used to adjust for multiplicity of intercountry comparisons. Time to autoantibody seroconversion was analyzed using a Cox proportional hazards model with cumulative analgesic use as primary time dependent covariate of interest. For each categorization, a generalized estimating equation (GEE) approach was used. Results: Higher prevalence of ANAP use was found in the U.S. (95.7%) and Sweden (94.8%) compared to Finland (78.1%) and Germany (80.2%). First-born children were more commonly given acetaminophen (OR 1.26; 95% CI 1.07, 1.49; p = 0.007) but less commonly Non-Steroidal Anti-inflammatory Drugs (NSAID) (OR 0.86; 95% CI 0.78, 0.95; p = 0.002). Acetaminophen and NSAID use in the absence of fever and infection was more prevalent in the U.S. (40.4%; 26.3% of doses) compared to Sweden, Finland and Germany (p < 0.001). Acetaminophen or NSAID use before age 2.5 years did not predict development of islet autoimmunity by age 6 years (HR 1.02, 95% CI 0.99-1.09; p = 0.27). In a sub-analysis, acetaminophen use in children with fever weakly predicted development of islet autoimmunity by age 3 years (HR 1.05; 95% CI 1.01-1.09; p = 0.024). Conclusions: ANAP use in young children is not a risk factor for seroconversion by age 6 years. Use of ANAP is widespread in young children, and significantly higher in the U.S. compared to other study sites, where use is common also in absence of fever and infection.
|
|
| 3. |
- Tedesco, Salvatore, et al.
(författare)
-
Comparison of machine learning techniques for mortality prediction in a prospective cohort of older adults
- 2021
-
Ingår i: International Journal of Environmental Research and Public Health. - : MDPI. - 1661-7827 .- 1660-4601. ; 18:23
-
Tidskriftsartikel (refereegranskat)abstract
- As global demographics change, ageing is a global phenomenon which is increasingly of interest in our modern and rapidly changing society. Thus, the application of proper prognostic indices in clinical decisions regarding mortality prediction has assumed a significant importance for personalized risk management (i.e., identifying patients who are at high or low risk of death) and to help ensure effective healthcare services to patients. Consequently, prognostic modelling expressed as all‐cause mortality prediction is an important step for effective patient management. Machine learning has the potential to transform prognostic modelling. In this paper, results on the development of machine learning models for all‐cause mortality prediction in a cohort of healthy older adults are reported. The models are based on features covering anthropometric variables, physical and lab examinations, questionnaires, and lifestyles, as well as wearable data collected in free‐living settings, obtained for the “Healthy Ageing Initiative” study conducted on 2291 recruited participants. Several machine learning techniques including feature engineering, feature selection, data augmentation and resampling were investigated for this purpose. A detailed empirical comparison of the impact of the different techniques is presented and discussed. The achieved performances were also compared with a standard epidemiological model. This investigation showed that, for the dataset under consideration, the best results were achieved with Random Under‐ Sampling in conjunction with Random Forest (either with or without probability calibration). However, while including probability calibration slightly reduced the average performance, it increased the model robustness, as indicated by the lower 95% confidence intervals. The analysis showed that machine learning models could provide comparable results to standard epidemiological models while being completely data‐driven and disease‐agnostic, thus demonstrating the opportunity for building machine learning models on health records data for research and clinical practice. However, further testing is required to significantly improve the model performance and its robustness.
|
|
| 4. |
- Tedesco, Salvatore, et al.
(författare)
-
Investigation of the analysis of wearable data for cancer-specific mortality prediction in older adults
- 2021
-
Ingår i: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. - : IEEE. - 9781728111797 ; , s. 1848-1851
-
Konferensbidrag (refereegranskat)abstract
- Cancer is an aggressive disease which imparts a tremendous socio-economic burden on the international community. Early detection is an important aspect in improving survival rates for cancer sufferers; however, very few studies have investigated the possibility of predicting which people have the highest risk to develop this disease, even years before the traditional symptoms first occur. In this paper, a dataset from a longitudinal study which was collected among 2291 70-year olds in Sweden has been analyzed to investigate the possibility for predicting 2-7 year cancer-specific mortality. A tailored ensemble model has been developed to tackle this highly imbalanced dataset. The performance with different feature subsets has been investigated to evaluate the impact that heterogeneous data sources may have on the overall model. While a full-features model shows an Area Under the ROC Curve (AUC-ROC) of 0.882, a feature subset which only includes demographics, self-report health and lifestyle data, and wearable dataset collected in free-living environments presents similar performance (AUC-ROC: 0.857). This analysis confirms the importance of wearable technology for providing unbiased health markers and suggests its possible use in the accurate prediction of 2-7 year cancer-related mortality in older adults.
|
|
