Do LUTS Predict Mortality? An Analysis Using Random Forest Algorithms

Abstract

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 [phone], Fax [phone], Email [email protected]: 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

Keywords

• lower urinary tract symptoms
• mortality
• machine learning
• cohort studies