Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms
Jonne Åkerla,1,2 Jaakko Nevalainen,3 Jori S Pesonen,4 Antti Pöyhönen,5 Juha Koskimäki,1 Jukka Häkkinen,6 Teuvo LJ Tammela,1,2 Anssi Auvinen3 1Department of Urology, Tampere University Hospital, Tampere, Finland; 2Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland; 3Facul...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2024-02-01
|
| Series: | Clinical Interventions in Aging |
| Subjects: | |
| Online Access: | https://www.dovepress.com/do-luts-predict-mortality-an-analysis-using-random-forest-algorithms-peer-reviewed-fulltext-article-CIA |
| _version_ | 1827351477364981760 |
|---|---|
| author | Åkerla J Nevalainen J Pesonen JS Pöyhönen A Koskimäki J Häkkinen J Tammela TL Auvinen A |
| author_facet | Åkerla J Nevalainen J Pesonen JS Pöyhönen A Koskimäki J Häkkinen J Tammela TL Auvinen A |
| author_sort | Åkerla J |
| collection | DOAJ |
| description | Jonne Åkerla,1,2 Jaakko Nevalainen,3 Jori S Pesonen,4 Antti Pöyhönen,5 Juha Koskimäki,1 Jukka Häkkinen,6 Teuvo LJ Tammela,1,2 Anssi Auvinen3 1Department of Urology, Tampere University Hospital, Tampere, Finland; 2Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland; 3Faculty of Social Sciences, Tampere University, Tampere, Finland; 4Department of Surgery, Päijät-Häme Central Hospital, Lahti, Finland; 5Centre for Military Medicine, The Finnish Defence Forces, Riihimäki, Finland; 6Department of Urology, Länsi-Pohja healthcare District, Kemi, FinlandCorrespondence: Jonne Åkerla, Department of Urology, Tampere University Hospital, Teiskontie 35, Tampere, 33521, Finland, Tel +358 311 611, Fax +358 311 64256, Email jonne.akerla@gmail.comPurpose: To evaluate a random forest (RF) algorithm of lower urinary tract symptoms (LUTS) as a predictor of all-cause mortality in a population-based cohort.Materials and Methods: A population-based cohort of 3143 men born in 1924, 1934, and 1944 was evaluated using a mailed questionnaire including the Danish Prostatic Symptom Score (DAN-PSS-1) to assess LUTS as well as questions on medical conditions and behavioral and sociodemographic factors. Surveys were repeated in 1994, 1999, 2004, 2009 and 2015. The cohort was followed-up for vital status until the end of 2018. RF uses an ensemble of classification trees for prediction with a good flexibility and without overfitting. RF algorithms were developed to predict the five-year mortality using LUTS, demographic, medical, and behavioral factors alone and in combinations.Results: A total of 2663 men were included in the study, of whom 917 (34%) died during follow-up (median follow-up time 15.0 years). The LUTS-based RF algorithm showed an area under the curve (AUC) 0.60 (95% CI 0.52– 0.69) for five-year mortality. An expanded RF algorithm, including LUTS, medical history, and behavioral and sociodemographic factors, yielded an AUC 0.73 (0.65– 0.81), while an algorithm excluding LUTS yielded an AUC 0.71 (0.62– 0.78).Conclusion: An exploratory RF algorithm using LUTS can predict all-cause mortality with acceptable discrimination at the group level. In clinical practice, it is unlikely that LUTS will improve the accuracy to predict death if the patient’s background is well known.Keywords: lower urinary tract symptoms, mortality, machine learning, cohort studies |
| first_indexed | 2024-03-08T02:03:49Z |
| format | Article |
| id | doaj.art-89a415a53e3a4cc88b74932e736117c6 |
| institution | Directory Open Access Journal |
| issn | 1178-1998 |
| language | English |
| last_indexed | 2024-03-08T02:03:49Z |
| publishDate | 2024-02-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Clinical Interventions in Aging |
| spelling | doaj.art-89a415a53e3a4cc88b74932e736117c62024-02-13T19:43:10ZengDove Medical PressClinical Interventions in Aging1178-19982024-02-01Volume 1923724590390Do LUTS Predict Mortality? An Analysis Using Random Forest AlgorithmsÅkerla JNevalainen JPesonen JSPöyhönen AKoskimäki JHäkkinen JTammela TLAuvinen AJonne Åkerla,1,2 Jaakko Nevalainen,3 Jori S Pesonen,4 Antti Pöyhönen,5 Juha Koskimäki,1 Jukka Häkkinen,6 Teuvo LJ Tammela,1,2 Anssi Auvinen3 1Department of Urology, Tampere University Hospital, Tampere, Finland; 2Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland; 3Faculty of Social Sciences, Tampere University, Tampere, Finland; 4Department of Surgery, Päijät-Häme Central Hospital, Lahti, Finland; 5Centre for Military Medicine, The Finnish Defence Forces, Riihimäki, Finland; 6Department of Urology, Länsi-Pohja healthcare District, Kemi, FinlandCorrespondence: Jonne Åkerla, Department of Urology, Tampere University Hospital, Teiskontie 35, Tampere, 33521, Finland, Tel +358 311 611, Fax +358 311 64256, Email jonne.akerla@gmail.comPurpose: To evaluate a random forest (RF) algorithm of lower urinary tract symptoms (LUTS) as a predictor of all-cause mortality in a population-based cohort.Materials and Methods: A population-based cohort of 3143 men born in 1924, 1934, and 1944 was evaluated using a mailed questionnaire including the Danish Prostatic Symptom Score (DAN-PSS-1) to assess LUTS as well as questions on medical conditions and behavioral and sociodemographic factors. Surveys were repeated in 1994, 1999, 2004, 2009 and 2015. The cohort was followed-up for vital status until the end of 2018. RF uses an ensemble of classification trees for prediction with a good flexibility and without overfitting. RF algorithms were developed to predict the five-year mortality using LUTS, demographic, medical, and behavioral factors alone and in combinations.Results: A total of 2663 men were included in the study, of whom 917 (34%) died during follow-up (median follow-up time 15.0 years). The LUTS-based RF algorithm showed an area under the curve (AUC) 0.60 (95% CI 0.52– 0.69) for five-year mortality. An expanded RF algorithm, including LUTS, medical history, and behavioral and sociodemographic factors, yielded an AUC 0.73 (0.65– 0.81), while an algorithm excluding LUTS yielded an AUC 0.71 (0.62– 0.78).Conclusion: An exploratory RF algorithm using LUTS can predict all-cause mortality with acceptable discrimination at the group level. In clinical practice, it is unlikely that LUTS will improve the accuracy to predict death if the patient’s background is well known.Keywords: lower urinary tract symptoms, mortality, machine learning, cohort studieshttps://www.dovepress.com/do-luts-predict-mortality-an-analysis-using-random-forest-algorithms-peer-reviewed-fulltext-article-CIAlower urinary tract symptomsmortalitymachine learningcohort studies |
| spellingShingle | Åkerla J Nevalainen J Pesonen JS Pöyhönen A Koskimäki J Häkkinen J Tammela TL Auvinen A Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms Clinical Interventions in Aging lower urinary tract symptoms mortality machine learning cohort studies |
| title | Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms |
| title_full | Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms |
| title_fullStr | Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms |
| title_full_unstemmed | Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms |
| title_short | Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms |
| title_sort | do luts predict mortality an analysis using random forest algorithms |
| topic | lower urinary tract symptoms mortality machine learning cohort studies |
| url | https://www.dovepress.com/do-luts-predict-mortality-an-analysis-using-random-forest-algorithms-peer-reviewed-fulltext-article-CIA |
| work_keys_str_mv | AT akerlaj dolutspredictmortalityananalysisusingrandomforestalgorithms AT nevalainenj dolutspredictmortalityananalysisusingrandomforestalgorithms AT pesonenjs dolutspredictmortalityananalysisusingrandomforestalgorithms AT poyhonena dolutspredictmortalityananalysisusingrandomforestalgorithms AT koskimakij dolutspredictmortalityananalysisusingrandomforestalgorithms AT hakkinenj dolutspredictmortalityananalysisusingrandomforestalgorithms AT tammelatl dolutspredictmortalityananalysisusingrandomforestalgorithms AT auvinena dolutspredictmortalityananalysisusingrandomforestalgorithms |