1
|
Pickering JW, Scrase R, Troughton R, Jamieson HA. Evaluation of the added value of Brain Natriuretic Peptide to a validated mortality risk-prediction model in older people using a standardised international clinical assessment tool. PLoS One 2022; 17:e0277850. [PMID: 36399481 PMCID: PMC9674136 DOI: 10.1371/journal.pone.0277850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2022] [Accepted: 11/03/2022] [Indexed: 11/19/2022] Open
Abstract
The ability to accurately predict the one-year survival of older adults is challenging for clinicians as they endeavour to provide the most appropriate care. Standardised clinical needs assessments are routine in many countries and some enable application of mortality prediction models. The added value of blood biomarkers to these models is largely unknown. We undertook a proof of concept study to assess if adding biomarkers to needs assessments is of value. Assessment of the incremental value of a blood biomarker, Brain Naturetic Peptide (BNP), to a one year mortality risk prediction model, RiskOP, previously developed from data from the international interRAI-HomeCare (interRAI-HC) needs assessment. Participants were aged ≥65 years and had completed an interRAI-HC assessment between 1 January 2013 and 21 August 2021 in Canterbury, New Zealand. Inclusion criteria was a BNP test within 90 days of the date of interRAI-HC assessment. The primary outcome was one-year mortality. Incremental value was assessed by change in Area Under the Receiver Operating Characteristic Curve (AUC) and Brier Skill, and the calibration of the final model. Of 14,713 individuals with an interRAI-HC assessment 1,537 had a BNP within 90 days preceding the assessment and all data necessary for RiskOP. 553 (36.0%) died within 1-year. The mean age was 82.6 years. Adding BNP improved the overall AUC by 0.015 (95% CI:0.004 to 0.028) and improved predictability by 1.9% (0.26% to 3.4%). In those with no Congestive Heart Failure the improvements were 0.029 (0.004 to 0.057) and 4.0% (0.68% to 7.6%). Adding a biomarker to a risk model based on standardised needs assessment of older people improved prediction of 1-year mortality. BNP added value to a risk prediction model based on the interRAI-HC assessment in those patients without a diagnosis of congestive heart failure.
Collapse
Affiliation(s)
- John W. Pickering
- Better Ageing with Big Data Research Group, Department of Medicine, University of Otago, Christchurch, New Zealand
- Department of Medicine, University of Otago, Christchurch Heart Institute, Christchurch, New Zealand
| | - Richard Scrase
- Te Whatu Ora–Health New Zealand, University of Otago, Christchurch, New Zealand
| | - Richard Troughton
- Department of Medicine, University of Otago, Christchurch Heart Institute, Christchurch, New Zealand
| | - Hamish A. Jamieson
- Better Ageing with Big Data Research Group, Department of Medicine, University of Otago, Christchurch, New Zealand
- * E-mail:
| |
Collapse
|
2
|
Tedesco S, Andrulli M, Larsson MÅ, Kelly D, Alamäki A, Timmons S, Barton J, Condell J, O’Flynn B, Nordström A. Comparison of Machine Learning Techniques for Mortality Prediction in a Prospective Cohort of Older Adults. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:12806. [PMID: 34886532 PMCID: PMC8657506 DOI: 10.3390/ijerph182312806] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 12/01/2021] [Accepted: 12/02/2021] [Indexed: 12/16/2022]
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 UnderSampling 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.
Collapse
Affiliation(s)
- Salvatore Tedesco
- Tyndall National Institute, University College Cork, Lee Maltings Complex, Dyke Parade, T12R5CP Cork, Ireland; (M.A.); (J.B.); (B.O.)
| | - Martina Andrulli
- Tyndall National Institute, University College Cork, Lee Maltings Complex, Dyke Parade, T12R5CP Cork, Ireland; (M.A.); (J.B.); (B.O.)
| | - Markus Åkerlund Larsson
- Department of Public Health and Clinical Medicine, Section of Sustainable Health, Umeå University, SE-901 87 Umeå, Sweden; (M.Å.L.); (A.N.)
| | - Daniel Kelly
- School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry BT48 7JL, UK; (D.K.); (J.C.)
| | - Antti Alamäki
- Department of Physiotherapy, Karelia University of Applied Sciences, Tikkarinne 9, FI-80200 Joensuu, Finland;
| | - Suzanne Timmons
- Centre for Gerontology and Rehabilitation, University College Cork, T12XH60 Cork, Ireland;
| | - John Barton
- Tyndall National Institute, University College Cork, Lee Maltings Complex, Dyke Parade, T12R5CP Cork, Ireland; (M.A.); (J.B.); (B.O.)
| | - Joan Condell
- School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry BT48 7JL, UK; (D.K.); (J.C.)
| | - Brendan O’Flynn
- Tyndall National Institute, University College Cork, Lee Maltings Complex, Dyke Parade, T12R5CP Cork, Ireland; (M.A.); (J.B.); (B.O.)
| | - Anna Nordström
- Department of Public Health and Clinical Medicine, Section of Sustainable Health, Umeå University, SE-901 87 Umeå, Sweden; (M.Å.L.); (A.N.)
- School of Sport Sciences, UiT the Arctic University of Norway, 9037 Tromsø, Norway
| |
Collapse
|
3
|
Tedesco S, Andrulli M, Larsson MA, Kelly D, Timmons S, Alamaki A, Barton J, Condell J, O'Flynn B, Nordstrom A. Investigation of the analysis of wearable data for cancer-specific mortality prediction in older adults. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:1848-1851. [PMID: 34891647 DOI: 10.1109/embc46164.2021.9630370] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
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.
Collapse
|
4
|
Soares MU, Facchini LA, Nedel FB, Wachs LS, Kessler M, Thumé E. Social relationships and survival in the older adult cohort. Rev Lat Am Enfermagem 2021; 29:e3395. [PMID: 33439948 PMCID: PMC7798399 DOI: 10.1590/1518-8345.3844.3395] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2019] [Accepted: 07/15/2020] [Indexed: 12/04/2022] Open
Abstract
Objective: to verify the influence of social relations on the survival of older adults living in southern Brazil. Method: a cohort study (2008 and 2016/17), conducted with 1,593 individuals aged 60 years old or over, in individual interviews. The outcomes of social relations and survival were verified by Multiple Correspondence Analysis, which guided the proposal of an explanatory matrix for social relations, the analysis of survival by Kaplan-Meier, and the multivariate analysis by Cox regression to verify the association between the independent variables. Results: follow-up was carried out with 82.5% (n=1,314), with 46.1% being followed up in 2016/17 (n=735) and 579 deaths (36.4%). The older adults who went out of their homes daily had a 39% reduction in mortality, and going to parties kept the protective effect of 17% for survival. The lower risk of death for women is modified when the older adults live in households with two or more people, in this case women have an 89% higher risk of death than men. Conclusion: strengthened social relationships play a mediating role in survival. The findings made it possible to verify the importance of going out of the house as a marker of protection for survival.
Collapse
Affiliation(s)
- Mariangela Uhlmann Soares
- Universidade Federal de Pelotas, Pelotas, RS, Brazil.,Scholarship holder at the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil
| | | | - Fúlvio Borges Nedel
- Universidade Federal de Santa Catarina, Centro de Ciências da Saúde, Florianópolis, SC, Brazil
| | - Louriele Soares Wachs
- Universidade Federal de Pelotas, Pelotas, RS, Brazil.,Scholarship holder at the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil
| | - Marciane Kessler
- Universidade Federal de Pelotas, Pelotas, RS, Brazil.,Scholarship holder at the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil
| | - Elaine Thumé
- Universidade Federal de Pelotas, Pelotas, RS, Brazil
| |
Collapse
|
5
|
Lee S, Hong GRS. The predictive relationship between factors related to fear of falling and mortality among community-dwelling older adults in Korea: analysis of the Korean longitudinal study of aging from 2006 to 2014. Aging Ment Health 2020; 24:1999-2005. [PMID: 31512495 DOI: 10.1080/13607863.2019.1663490] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
Abstract
OBJECTIVES This study was conducted to identify the predictive relationship between factors related to fear of falling (FOF) and mortality among community-dwelling older adults in Korea. METHOD Data were obtained from the Korean Longitudinal Study of Aging (KLoSA). Hierarchical Cox proportional hazards regression analyses were conducted to identify factors related to FOF and correlations of these factors with mortality. RESULTS During the eight-year follow-up period, 964 participants (23.5%) died. Death was more likely to occur in males (hazard ratio [HR], 2.55; 95% confidence interval [95% CI], 2.17-3.00), those 75 years old or older (HR, 2.76; 95% CI, 2.40-3.17), those without education (HR, 1.27; 95% CI, 1.05-1.52), and those living without a spouse (HR, 1.30; 95% CI, 1.11-1.51). Those afraid of falling (HR, 1.41; 95% CI, 1.17-1.70), limiting their activities due to FOF (HR, 1.40; 95% CI, 1.21-1.62), showing symptoms of depression (HR, 1.34; 95% CI, 1.16-1.54), and having low life satisfaction (HR, 1.34; 95% CI, 1.13-1.59) were also more likely to experience decreased lifespans. CONCLUSION These results suggest that early management and prevention of factors related to FOF should be an effective approach to reducing mortality in older adults.
Collapse
Affiliation(s)
- Sieun Lee
- College of Nursing, Baekseok Culture University, Cheonan-si, Chungcheongnam-Do, South Korea
| | | |
Collapse
|
6
|
Prediction of the Incidence of Falls and Deaths Among Elderly Nursing Home Residents: The SENIOR Study. J Am Med Dir Assoc 2018; 19:18-24. [DOI: 10.1016/j.jamda.2017.06.014] [Citation(s) in RCA: 43] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2017] [Revised: 06/16/2017] [Accepted: 06/16/2017] [Indexed: 12/16/2022]
|