Browsing by Author "Koivusalo, Saila"

Now showing 1 - 5 of 5

Optimizing postprandial glucose prediction through integration of diet and exercise : Leveraging transfer learning with imbalanced patient data
(2024-08) Hotta, Shinji; Kytö, Mikko; Koivusalo, Saila; Heinonen, Seppo; Marttinen, Pekka
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Background In recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients’ daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal. Methods In this study, we introduce a unique application of Bayesian transfer learning for postprandial glucose prediction using randomized controlled trial (RCT) data. The data comprises a time series of three key variables: continuous glucose levels, exercise expenditure, and carbohydrate intake. For building the optimal model to predict postprandial glucose levels we initially gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model’s parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient. Results The efficacy of the proposed method was appraised using data from 68 gestational diabetes mellitus (GDM) patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our method. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart. Conclusion An innovative application of the transfer-learning utilizing randomized controlled trial data can improve the challenging modeling task of postprandial glucose prediction for GDM patients, integrating both dietary and exercise behaviors. For more accurate prediction, future research should focus on incorporating the long-term effects of exercise and other glycemic-related factors such as stress, sleep.
Query-Guided Self-Supervised Summarization of Nursing Notes
(2024) Gao, Ya; Moen, Hans; Koivusalo, Saila; Koskinen, Miika; Marttinen, Pekka
A4 Artikkeli konferenssijulkaisussa
Nursing notes, an important part of Electronic Health Records (EHRs), track a patient's health during a care episode. Summarizing key information in nursing notes can help clinicians quickly understand patients' conditions. However, existing summarization methods in the clinical setting, especially abstractive methods, have overlooked nursing notes and require reference summaries for training. We introduce QGSumm, a novel query-guided self-supervised domain adaptation approach for abstractive nursing note summarization. The method uses patient-related clinical queries for guidance, and hence does not need reference summaries for training. Through automatic experiments and manual evaluation by an expert clinician, we study our approach and other state-of-the-art Large Language Models (LLMs) for nursing note summarization. Our experiments show: 1) GPT-4 is competitive in maintaining information in the original nursing notes, 2) QGSumm can generate high-quality summaries with a good balance between recall of the original content and hallucination rate lower than other top methods. Ultimately, our work offers a new perspective on conditional text summarization, tailored to clinical applications.
Short-term effect of plant-based Nordic diet versus carbohydrate-restricted diet on glucose levels in gestational diabetes – the eMOM pilot study
(2023-12) Markussen, Lisa Torsdatter; Kivelä, Jemina; Lindström, Jaana; Ashrafi, Reza A.; Heinonen, Seppo; Koivusalo, Saila; Meinilä, Jelena
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Background: The optimal nutritional treatment for gestational diabetes (GDM) is still a matter of debate. With increasing rates of GDM and potential negative consequences for the health of mother and child, the best treatment should be established. The Nordic diet with emphasis on plant-based protein show promising health outcomes in other populations but has yet to be investigated in GDM population. The aim of this study, which is part of the “Effect of plant-based Nordic diet versus carbohydrate-restricted diet on glucose levels in gestational diabetes” (eMOM) pilot study was to compare the short-term effects of healthy Nordic diet (HND) and the currently recommended moderate restriction of carbohydrates diet (MCRD) on glucose and lipid metabolism in women with GDM. Methods: This was a randomized crossover where each of the diet interventions (HND and MCRD) were consumed for 3 days with a 3-day wash-out period in between. In total, 42 pregnant women diagnosed with GDM (< 29 + 0 gestational week) were randomized. Glucose data was collected by continuous glucose monitors (CGM, Freestyle Libre®, Abbott, USA) worn for 14 days, and participants gave blood samples before and after diet interventions. The primary outcome was time spent in glucose target range (TIR, < 7.8 mmol/L). TIR, 3-day mean tissue glucose as well as changes in fasting glucose, homeostatic model of insulin resistance (HOMA-IR) and blood lipids were analyzed with paired samples statistical analyses. Results: Thirty-six women with complete 14 days CGM data were analyzed. Both diet interventions produced a high degree of TIR (99% SD 1.8), without a difference between the diets (p = 0.727). The 3-day mean glucose was significantly lower in HND than in MCRD (p = 0,049). Fasting insulin (p = 0,034), insulin resistance (p = 0,030), total and LDL cholesterol (p = 0,023 and 0,008) reduced more in the MCRD diet than the HND. NS differences in any other measure of CGM or blood tests. Conclusions: HND and MCRD did not differ in terms of their short-term effect on TIR. A larger study with sufficient power is needed to confirm the differences in short-term mean glucose, insulin resistance and lipid metabolism. Trial registration: Registered in clinicaltrials.gov (21/09/2018, NCT03681054).
Supporting the Management of Gestational Diabetes Mellitus With Comprehensive Self-Tracking: Mixed Methods Study of Wearable Sensors
(2023) Kytö, Mikko; Koivusalo, Saila; Tuomonen, Heli; Strömberg, Lisbeth; Ruonala, Antti; Marttinen, Pekka; Heinonen, Seppo; Jacucci, Giulio
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
VMS : Interactive Visualization to Support the Sensemaking and Selection of Predictive Models
(2024-03-18) He, Chen; Raj, Vishnu; Moen, Hans; Gröhn, Tommi; Wang, Chen; Peltonen, Laura Maria; Koivusalo, Saila; Marttinen, Pekka; Jacucci, Giulio
A4 Artikkeli konferenssijulkaisussa
To compare and select machine learning models, relying on performance measures alone may not always be sufficient. This is particularly the case where different subsets, features, and predicted results may vary in importance relative to the task at hand. Explanation and visualization techniques are required to support model sensemaking and informed decision-making. However, a review shows that existing systems are mostly designed for model developers and not evaluated with target users in their effectiveness. To address this issue, this research proposes an interactive visualization, VMS (Visualization for Model Sensemaking and Selection), for users of the model to compare and select predictive models. VMS integrates performance-, instance-, and feature-level analysis to evaluate models from multiple angles. Particularly, a feature view integrating the value and contribution of hundreds of features supports model comparison on local and global scales. We exemplified VMS for comparing models predicting patients' hospital length of stay through time-series health records and evaluated the prototype with 16 participants from the medical field. Results reveal evidence that VMS supports users to rationalize models in multiple ways and enables users to select the optimal models with a small sample size. User feedback suggests future directions on incorporating domain knowledge in model training, such as for different patient groups considering different sets of features as important.