Browsing by Author "Saaresranta, Tarja"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Lower respiratory tract infections among newly diagnosed sleep apnea patients
    (Springer, 2023-12) Keto, Jaana; Feuth, Thijs; Linna, Miika; Saaresranta, Tarja; Department of Industrial Engineering and Management; University of Helsinki; Turku University Hospital
    Background: Sleep apnea is associated with chronic comorbidities and acute complications. Existing data suggest that sleep apnea may predispose to an increased risk and severity of respiratory tract infections. Methods: We investigated the incidence of lower respiratory tract infections in the first and second year before and after diagnosis of sleep apnea in a Finnish nationwide, population-based, retrospective case–control study based on linking data from the national health care registers for primary and secondary care from 2015–2019. Controls were matched for age, sex, hospital district, and multimorbidity status. We furthermore analysed the independent effect of comorbidities and other patient characteristics on the risk of lower respiratory tract infections, and their recurrence. Results: Sleep apnea patients had a higher incidence of lower respiratory tract infections than their matched controls within one year before (hazard ratio 1.35, 95% confidence interval 1.16–1.57) and one year after (hazard ratio1.39, 95% confidence interval1.22–1.58) diagnosis of sleep apnea. However, we found no difference in the incidence of lower respiratory tract infections within the second year before or after diagnosis of sleep apnea in comparison with matched controls. In sleep apnea, history of lower respiratory tract infection prior to sleep apnea, multimorbidity, COPD, asthma, and age greater than 65 years increased the risk of incident and recurrent lower respiratory tract infections. Conclusions: Sleep apnea patients are at increased risk of being diagnosed with a lower respiratory tract infection within but not beyond one year before and after diagnosis of sleep apnea. Among sleep apnea patients, chronic comorbidities had a significant impact on the risk of lower respiratory tract infections and their recurrence.
  • Thumbnail Image
    Item
    Multimorbidity and overall comorbidity of sleep apnoea: a Finnish nationwide study
    (European Respiratory Society, 2022-04-01) Palomäki, Marja; Saaresranta, Tarja; Anttalainen, Ulla; Partinen, Markku; Keto, Jaana; Linna, Miika; Department of Industrial Engineering and Management; University of Turku; University of Helsinki; Jazz Pharmaceuticals
    The prevalence of sleep apnoea is increasing globally; however, population-based studies have reported a wide variation of prevalence estimates, and data on incidence of clinically diagnosed sleep apnoea are scant. Data on the overall burden of comorbidities or multimorbidity in individuals with incident sleep apnoea are scarce, and the pathways to multimorbidity have only marginally been studied. To study the current epidemiology of sleep apnoea in Finland, overall burden of comorbidities, and multimorbidity profiles in individuals with incident sleep apnoea, we conducted a register-based, nationwide, retrospective study of data from January 2016 to December 2019. The prevalence of clinically diagnosed sleep apnoea was 3.7% in the Finnish adult population; 1-year incidence was 0.6%. Multimorbidity was present in 63% of individuals at the time of sleep apnoea diagnosis. Of those with incident sleep apnoea, 34% were heavily multimorbid (presenting with four or more comorbidities). The three most common chronic morbidities before sleep apnoea diagnosis were musculoskeletal disease, hypertension and cardiovascular disease. In multimorbid sleep apnoea patients, hypertension and metabolic diseases including obesity and diabetes, cardiovascular diseases, musculoskeletal diseases and dorsopathies, in different combinations, encompassed the most frequent disease pairs preceding a sleep apnoea diagnosis. Our study adds to the few population-based studies by introducing overall and detailed figures on the burden of comorbidities in sleep apnoea in a nationwide sample and provides up-to-date information on the occurrence of sleep apnoea as well as novel insights into multimorbidity in individuals with incident sleep apnoea.
  • Thumbnail Image
    Item
    Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformer
    (IEEE, 2023) Chen, Zhaoyang; Siltala-Li, Lina; Lassila, Mikko; Malo, Pekka; Vilkkumaa, Eeva; Saaresranta, Tarja; Virkki, Arho Veli; School Common, BIZ; Department of Information and Service Management; Aalto University School of Business; Department of Information and Service Management; Turku University Hospital; University of Turku
    Background: Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare. Objective: For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures. Methods and procedures: The authors propose a translational engineering method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. This method effectively adapts state-of-the-art Transformer models to create practical cost prediction solutions that can be implemented in OSA management, potentially enhancing patient care and resource allocation. Results: The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's R2 from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the R2 considerably, from 61.6% to 81.9%. Conclusion: The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure. Clinical and Translational Impact Statement: Public Health- Lack of high-quality source data hinders data-driven analytics-based research in healthcare. The paper presents a method that couples data augmentation and prediction in cases of scant healthcare data.
  • Thumbnail Image
    Item
    Validation of an Accelerometer Based BCG Method for Sleep Analysis
    (Aalto University, 2016) Nurmi, Sami; Saaresranta, Tarja; Koivisto, Tero; Meriheinä, Ulf; Palva, Lauri; Sähkötekniikan ja automaation laitos; Department of Electrical Engineering and Automation; Sähkötekniikan korkeakoulu; School of Electrical Engineering
    Sleep problems are one of the most common medical complaints today. Polysomnography (PSG) as the current standard for sleep analysis is expensive, intrusive and complex. Thus, finding a reliable and unobtrusive method for longer-term home use is important. Ballistocardiography (BCG) based methods have shown potential in sleep analysis recently. The usability and performance of a BCG based method in qualitative and quantitative analysis of sleep was evaluated. The method was validated in a clinical test on 20 subjects using PSG as a reference. Heart rate (HR), heart rate variability (HRV), respiratory rate (RR), respiratory rate variability (RRV), respiratory depth (Rdepth) and movement were utilized for sleep stage detection. The BCG parameter accuracy was presented as the mean error from PSG with 95% confidence interval. The errors were -0.1 ± 4.4 beats per minute for HR, -0.9 ± 14.7 ms for high frequency (HF) HRV, -3.0 ± 29.9 ms for low frequency (LF) HRV, 0.3 ± 4.5 breaths per minute for RR and -40 ± 424 ms for RRV respectively. Correlation coefficient was 0.97 for HR, 0.67 for HF HRV, 0.71 for LF HRV, 0.54 for RR and 0.49 for RRV. HR, RRV and Rdepth were typically at an increased level in REM sleep and wakefulness and decreased in deep sleep. RRV was at its highest during wakefulness. HRV was at a decreased level in REM and wakefulness and increased in deep sleep. Movement was higher during wakefulness than in sleep.