Skip to main content
Login | Suomeksi | På svenska | In English

Browsing by Author "Lallukka, Tea"

Sort by: Order: Results:

  • Impact of a CE-Marked Medical Software Sensor on COVID- 19 Pandemic Progression Prediction : a Register Study Using Machine Learning Methods 
    Limingoja, Leevi; Antila, Kari; Jormanainen, Vesa; Röntynen, Joel; Jägerroos, Vilma; Soinen, Leena; Nordlund, Hanna; Vepsäläinen, Kristian; Kaikkonen, Risto; Lallukka, Tea (2022)
    Abstract Background: To address the current COVID-19 and any future pandemic, we need a robust, real-time, and population-scale collection and analysis of data. Rapid and comprehensive knowledge on the trends in reported symptoms in populations provides an earlier window into the progression of the viral spread and helps to predict the needs and timing of professional healthcare. Objective: The objective of this study was to use a CE-marked medical online symptom checker service, ©Omaolo, and validate the data against the national demand for COVID- 19-related care to predict the pandemic progression in Finland. Methods: Our data comprised real-time ©Omaolo COVID-19 symptom checker responses (414,477 in total) and daily admission counts in nationwide inpatient and outpatient registers provided by the Finnish Institute for Health and Welfare (THL) from March 16th to June 15th, 2020 (the first wave of the pandemic in Finland). The symptom checker responses provide self-triage information input to a medically qualified algorithm that produces a personalised probability of having COVID-19, and provides graded recommendations for further actions. We trained linear regression and XGBoost models together with F-score and mutual information feature pre-selectors to predict the admissions once a week, one week in advance. Results: Our models reached a MAPE (mean absolute percentage error) between 24.2% and 36.4% in predicting the national daily patient admissions. The best result was achieved by combining both ©Omaolo and historical patient admission counts. Our best predictor was linear regression with mutual information as the feature pre-selector. Conclusions: Accurate short-term predictions of COVID-19 patient admissions can be made, and both the symptom check questionnaires and the daily admissions data contribute to the accuracy of the predictions. Thus, symptom checkers can be used to estimate the progression of the pandemic, which can be considered when predicting the healthcare burden in a future pandemic.
  • Life-course socio-economic circumstances in acute, chronic and disabling pain among young employees : a double suffering 
    Fagerlund, Pi; Salmela, Jatta; Pietiläinen, Olli; Salonsalmi, Aino; Rahkonen, Ossi; Lallukka, Tea (2021)
    Abstract Background: Pain is known to be socio-economically patterned and associated with disability. However, knowledge is scarce concerning life-course socio-economic circumstances and pain among young adults. Our aim was to examine the associations of childhood and current socio-economic circumstances with acute pain and chronic pain with low and high disability levels among young Finnish municipal employees. Methods: We analyzed questionnaire data retrieved from the Young Helsinki Health Study (n=4683) covering 18–39-year-old employees of the City of Helsinki, Finland. We included a comprehensive set of indicators of childhood and current socio-economic circumstances and examined their associations with acute pain and with chronic pain with low and high disability levels. The level of chronic pain–related disability was assessed by the Chronic Pain Grade Questionnaire. Multinomial logistic regression analyses were conducted with stepwise adjustments for socio-demographic, socio-economic and health-related covariates. Results: Childhood and current socio-economic disadvantage were associated with acute and chronic pain, particularly with chronic pain with high disability level. The strongest associations after adjustments for covariates remained between chronic pain with high disability level and low education level (OR 3.38, 95% CI 2.18–5.24), manual occupation (OR 3.75, 95% CI 1.92–7.34) and experiencing frequent economic difficulties (OR 3.07, 95% CI 2.00–4.70). Conclusions: Pain is highly prevalent already among young employees and there is a socio-economic gradient in both pain chronicity and chronic pain–related disability. Life-course socio-economic determinants of pain should be considered in pain-preventing strategies and in clinical practice.

Yhteystiedot

HELSINGIN YLIOPISTO