Anusha Ihalapathirana

Ms. Anusha Ihalapathirana

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
PSPekka Siirtola
Pekka Siirtola
STSatu Tamminen
Satu Tamminen
GCGunjan Chandra
Gunjan Chandra
AIAnusha Ihalapathirana
Anusha Ihalapathirana
Juha RöningJuha Röning
Juha Röning
This study aims to predict emotions using biosignals collected via wrist-worn sensor and evaluate the performance of different prediction models. Two dimensions of emotions were considered: valence and arousal. The data collected by the sensor were used in conjunction with target values obtained from questionnaires. A variety of classification and regression models were compared, including Long Short-Term Memory (LSTM) models. Additionally, the effects of different normalization methods and the impact of using different sensors were studied, and the way in which the results differed between the study subjects was analyzed. The results revealed that regression models generally performed better than classification models, with LSTM regression models achieving the best results. The normalization method called baseline reduction was found to be the most effective, and when used with an LSTM-based regression model it achieved high accuracy in detecting valence (mean square error = 0.43 and R2-score = 0.71) and arousal (mean square error = 0.59 and R2-score = 0.81). Moreover, it was found that even if all biosignals were not used in the training phase, reliable models could be obtained; in fact, for certain study subjects the best results were obtained using only a few of the sensors.

7 September 2023 in Informatics in Medicine Unlocked
Verified
Journal Article
Open access
AIAnusha Ihalapathirana
Anusha Ihalapathirana
KCKonstantina Chalkou
Konstantina Chalkou
PSPekka Siirtola
Pekka Siirtola
STSatu Tamminen
Satu Tamminen
GCGunjan Chandra
Gunjan Chandra
Juha RöningJuha Röning
Juha Röning

1 March 2025 in Clinical Epidemiology
Verified
Journal Article
Open access
PDF file
GCGunjan Chandra
Gunjan Chandra
PLPiia Lavikainen
Piia Lavikainen
PSPekka Siirtola
Pekka Siirtola
STSatu Tamminen
Satu Tamminen
AIAnusha Ihalapathirana
Anusha Ihalapathirana
Juha RöningJuha Röning
Juha Röning
Purpose: This study applied machine learning (ML) and explainable artificial intelligence (XAI) to predict changes in HbA1c levels, a critical biomarker for monitoring glycemic control, within 12 months of initiating a new antidiabetic drug in patients diagnosed with type 2 diabetes. It also aimed to identify the predictors associated with these changes. Patients and Methods: Electronic health records (EHR) from 10,139 type 2 diabetes patients in North Karelia, Finland, were used to train models integrating randomized controlled trial (RCT)-derived HbA1c change values as predictors, creating offset models that integrate RCT insights with real-world data. Various ML models—including linear regression (LR), multi-layer perceptron (MLP), ridge regression (RR), random forest (RF), and XGBoost (XGB)—were evaluated using R² and RMSE metrics. Baseline models used data at or before drug initiation, while follow-up models included the first post-drug HbA1c measurement, improving performance by incorporating dynamic patient data. Model performance was also compared to expected HbA1c changes from clinical trials. Results: Results showed that ML models outperform RCT model, while LR, MLP, and RR models had comparable performance, RF and XGB models exhibited overfitting. The follow-up MLP model outperformed the baseline MLP model, with higher R² scores (0.74, 0.65) and lower RMSE values (6.94, 7.62), compared to the baseline model (R²: 0.52, 0.54; RMSE: 9.27, 9.50). Key predictors of HbA1c change included baseline and post-drug initiation HbA1c values, fasting plasma glucose, and HDL cholesterol. Conclusion: Using EHR and ML models allows for the development of more realistic and individualized predictions of HbA1c changes, accounting for more diverse patient populations and their heterogeneous nature, offering more tailored and effective treatment strategies for managing T2D. The use of XAI provided insights into the influence of specific predictors, enhancing model interpretability and clinical relevance. Future research will explore treatment selection models.

1 January 2023 in Clinical Epidemiology
Verified
Journal Article
Open access
PDF file
PLPiia Lavikainen
Piia Lavikainen
GCGunjan Chandra
Gunjan Chandra
PSPekka Siirtola
Pekka Siirtola
STSatu Tamminen
Satu Tamminen
AIAnusha Ihalapathirana
Anusha Ihalapathirana
JMJanne Martikainen
Janne Martikainen
Purpose: To gain an understanding of the heterogeneous group of type 2 diabetes (T2D) patients, we aimed to identify patients with the homogenous long-term HbA1c trajectories and to predict the trajectory membership for each patient using explainable machine learning methods and different clinical-, treatment-, and socio-economic-related predictors. Patients and Methods: Electronic health records data covering primary and specialized healthcare on 9631 patients having T2D diagnosis were extracted from the North Karelia region, Finland. Six-year HbA1c trajectories were examined with growth mixture models. Linear discriminant analysis and neural networks were applied to predict the trajectory membership individually. Results: Three HbA1c trajectories were distinguished over six years: “stable, adequate” (86.5%), “improving, but inadequate” (7.3%), and “fluctuating, inadequate” (6.2%) glycemic control. Prior glucose levels, duration of T2D, use of insulin only, use of insulin together with some oral antidiabetic medications, and use of only metformin were the most important predictors for the long-term treatment balance. The prediction model had a balanced accuracy of 85% and a receiving operating characteristic area under the curve of 91%, indicating high performance. Moreover, the results based on SHAP (Shapley additive explanations) values show that it is possible to explain the outcomes of machine learning methods at the population and individual levels. Conclusion: Heterogeneity in long-term glycemic control can be predicted with confidence by utilizing information from previous HbA1c levels, fasting plasma glucose, duration of T2D, and use of antidiabetic medications. In future, the expected development of HbA1c could be predicted based on the patient’s unique risk factors offering a practical tool for clinicians to support treatment planning.

25 July 2026 in Informatics in Medicine Unlocked
Verified
Journal Article
Open access
AIAnusha Ihalapathirana
Anusha Ihalapathirana
PSPekka Siirtola
Pekka Siirtola
TMTaneli T. Mattila
Taneli T. Mattila
GCGunjan Chandra
Gunjan Chandra
STSatu Tamminen
Satu Tamminen
OLOuti Laatikainen
Outi Laatikainen

31 March 2026 in Finnish Journal of eHealth and eWelfare
Verified
Journal Article
Open access
AIAnusha Ihalapathirana
Anusha Ihalapathirana
OLOuti Laatikainen
Outi Laatikainen
TMTaneli Mattila
Taneli Mattila
GCGunjan Chandra
Gunjan Chandra
JRJarmo Reponen
Jarmo Reponen
PSPekka Siirtola
Pekka Siirtola
Finland’s nationwide health registers and universal healthcare system provide comprehensive, longitudinal electronic health record data with strong potential for artificial intelligence-driven clinical research. Despite their coverage and richness, raw electronic health record datasets are not directly usable for advanced analytics due to fragmentation, heterogeneity, missingness, and inconsistencies in documentation and coding. This study describes data quality challenges encountered while preparing a breast cancer cohort (diagnosed 2012–2022) from the Wellbeing Services County of North Ostrobothnia as a preparatory step for artificial intelligence-based survival modelling. The initial dataset included 8074 patients across multiple domain-specific data files capturing diagnoses, laboratory results, pathology reports, medications, and procedural information. Following predefined cohort restrictions and preprocessing steps, 1967 patients remained for analysis. Identified challenges were grouped into four categories: 1. human-generated errors 2. decentralization-generated issues 3. time or system life-cycle–generated inconsistencies and 4. data governance/coding issues. The study adopts a qualitative research design aimed at systematically characterizing data quality challenges relevant to artificial intelligence application, and no predictive model was developed at this stage. The findings demonstrate that substantial preprocessing and data loss are often unavoidable in real-world electronic health record research and emphasize the need for standardized documentation, harmonized data structures, and closer collaboration between healthcare professionals, system developers, and data scientists to fully realize the potential of register-based electronic health record data in reliable artificial intelligence-driven research.