Erika Korobeinikova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Erika Korobeinikova has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Elona Juozaitytė
Institute of Oncology, Lithuanian University of Health Sciences, 50161 Kaunas, Lithuania
4 shared publications - Laimonas Jaruševičius
Department of Oncology and Hematology, Institute of Oncology, Lithuanian University of Health Sciences, 50161 Kaunas, Lithuania
4 shared publications - Adomas Bunevicius
Department of Neurology, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, United States
3 shared publications - Arturas Inčiūra
Department of Oncology and Hematology, Oncology Institute, Faculty of Medicine, Medical Academy, Lithuanian University of Health Sciences, LT-50161 Kaunas, Lithuania
3 shared publications - Domas Vaitiekus
Department of Oncology and Hematology, Medical Academy, Lithuanian University of Health Sciences, 44307 Kaunas, Lithuania
3 shared publications - Gabrielė Kasputytė
Faculty of Informatics, Vytautas Magnus University, Studentų 10, Kaunas District, LT-53361 Akademija, Lithuania
3 shared publications
Latest Publications
- Open Access
- 27 April 2026
- Published by Medical Journals Sweden AB in Acta Oncologica
- Vol. 65, 355-362
Radiotherapy and diagnostic capacity in relation to the changing cancer burden in the Baltic States
Background and purpose: Cancer mortality rates in the Baltic States (Estonia, Latvia, and Lithuania) exceeds the European Union (EU) average, in part due to limited access to radiation therapy (RT). We updated RT capacity and utilization to inform regional planning.Patient/material and methods: We conducted a census of all 11 RT centres (2016–2023) via a standardized questionnaire, cross-validated with national registries and international databases. We compared technology availability, workforce, and utilization with EU countries in relation to the present cancer burden and projections to 2050. This multicentre observational study adhered to STrengthening the Reporting of OBservational Studies in Epidemiology (STROBE) guidelines.Results: Only 35–42% of cancer patients received RT, below the 50% recommendation. Linear accelerator availability ranged from 3.8 to 5.1 per million inhabitants, figures that are almost half those seen in EU countries with higher Gross Domestic Product (GDP) per capita. While the use of intensity modulated RT, volumetric modulated arc therapy and stereotactic RT increased, staffing levels has remained static in recent years. Mortality-to-incidence ratio correlated negatively with GDP (r = –0.7) and RT capacity (r = –0.7).Interpretation: Despite technological progress in the Baltic States, major gaps persist in RT access and workforce levels. Baltic States still underperform compared to EU countries with higher GDP per capita in terms of equipment availability, workforce capacity, and overall cancer outcomes. Future-oriented strategic investments, based on regional collaboration and shared infrastructure are urgently needed, including the development of a regional particle therapy centre, to ensure equitable access to state-of-the art advanced cancer care across the Baltic States.
- 27 April 2026
- Published by Medical Journals Sweden AB in Acta Oncologica
- Vol. 65, 355-362
Open AccessRadiotherapy and diagnostic capacity in relation to the changing cancer burden in the Baltic States
Background and purpose: Cancer mortality rates in the Baltic States (Estonia, Latvia, and Lithuania) exceeds the European Union (EU) average, in part due to limited access to radiation therapy (RT). We updated RT capacity and utilization to inform regional planning.Patient/material and methods: We conducted a census of all 11 RT centres (2016–2023) via a standardized questionnaire, cross-validated with national registries and international databases. We compared technology availability, workforce, and utilization with EU countries in relation to the present cancer burden and projections to 2050. This multicentre observational study adhered to STrengthening the Reporting of OBservational Studies in Epidemiology (STROBE) guidelines.Results: Only 35–42% of cancer patients received RT, below the 50% recommendation. Linear accelerator availability ranged from 3.8 to 5.1 per million inhabitants, figures that are almost half those seen in EU countries with higher Gross Domestic Product (GDP) per capita. While the use of intensity modulated RT, volumetric modulated arc therapy and stereotactic RT increased, staffing levels has remained static in recent years. Mortality-to-incidence ratio correlated negatively with GDP (r = –0.7) and RT capacity (r = –0.7).Interpretation: Despite technological progress in the Baltic States, major gaps persist in RT access and workforce levels. Baltic States still underperform compared to EU countries with higher GDP per capita in terms of equipment availability, workforce capacity, and overall cancer outcomes. Future-oriented strategic investments, based on regional collaboration and shared infrastructure are urgently needed, including the development of a regional particle therapy centre, to ensure equitable access to state-of-the art advanced cancer care across the Baltic States.
- Open Access
- 25 December 2025
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 249
Machine Learning Methods for Predicting Cancer Complications Using Smartphone Sensor Data: A Prospective Study
Complications are frequent in cancer patients and contribute to adverse outcomes and higher healthcare costs, underscoring the need for earlier identification and prediction. This study evaluated the feasibility of using passively generated smartphone sensor data to explore early-warning signals of complications and symptom worsening during cancer treatment. A total of 108 patients were continuously monitored using accelerometer, GPS, and screen on/off data collected through the LAIMA application, while symptoms of depression, fatigue, and nausea were assessed every two weeks and complications were confirmed during clinic visits or emergency presentations. Smartphone data streams were aggregated into variables describing activity and sociability patterns. Machine learning models, including Decision Tree, Extreme Gradient Boosting, K-Nearest Neighbors, and Support Vector Machine, were used for complication prediction, and time-series models such as Autoregressive Integrated Moving Average, Holt–Winters, TBATS, Long Short-Term Memory neural network, and General Regression Neural Network were applied to identify early behavioral changes preceding symptom reports. In this exploratory analysis, the ensemble model demonstrated high sensitivity (89%) for identifying complication events. Smartphone-derived behavioral indicators enabled earlier detection of depression, fatigue, and vomiting by about nine days in a subset of patients. These findings demonstrate the feasibility of passive smartphone sensor data as exploratory early-warning signals, warranting validation in larger cohorts.
- 25 December 2025
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 249
Open AccessMachine Learning Methods for Predicting Cancer Complications Using Smartphone Sensor Data: A Prospective Study
Complications are frequent in cancer patients and contribute to adverse outcomes and higher healthcare costs, underscoring the need for earlier identification and prediction. This study evaluated the feasibility of using passively generated smartphone sensor data to explore early-warning signals of complications and symptom worsening during cancer treatment. A total of 108 patients were continuously monitored using accelerometer, GPS, and screen on/off data collected through the LAIMA application, while symptoms of depression, fatigue, and nausea were assessed every two weeks and complications were confirmed during clinic visits or emergency presentations. Smartphone data streams were aggregated into variables describing activity and sociability patterns. Machine learning models, including Decision Tree, Extreme Gradient Boosting, K-Nearest Neighbors, and Support Vector Machine, were used for complication prediction, and time-series models such as Autoregressive Integrated Moving Average, Holt–Winters, TBATS, Long Short-Term Memory neural network, and General Regression Neural Network were applied to identify early behavioral changes preceding symptom reports. In this exploratory analysis, the ensemble model demonstrated high sensitivity (89%) for identifying complication events. Smartphone-derived behavioral indicators enabled earlier detection of depression, fatigue, and vomiting by about nine days in a subset of patients. These findings demonstrate the feasibility of passive smartphone sensor data as exploratory early-warning signals, warranting validation in larger cohorts.
- Open Access
- 10 October 2023
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 12 (1) , e49096
Digital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study
Background: Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. Objective: We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. Methods: We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. Results: As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. Conclusions: This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. International Registered Report Identifier (IRRID): PRR1-10.2196/49096
- 10 October 2023
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 12 (1) , e49096
Open AccessDigital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study
Background: Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. Objective: We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. Methods: We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. Results: As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. Conclusions: This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. International Registered Report Identifier (IRRID): PRR1-10.2196/49096
- Open Access
- 19 May 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Digital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study (Preprint)
BACKGROUND Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. OBJECTIVE We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. METHODS We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. RESULTS As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. CONCLUSIONS This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. INTERNATIONAL REGISTERED REPORT PRR1-10.2196/49096
- 19 May 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDigital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study (Preprint)
BACKGROUND Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. OBJECTIVE We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. METHODS We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. RESULTS As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. CONCLUSIONS This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. INTERNATIONAL REGISTERED REPORT PRR1-10.2196/49096
- Open Access
- 26 June 2015
- Published by Springer Nature in BMC Genomic Data
- Vol. 16 (1) , 70
The prognostic value of IL10 and TNF alpha functional polymorphisms in premenopausal early-stage breast cancer patients
Interleukin-10 and tumor necrosis factor α play an important role in breast carcinogenesis. Genes, encoding those two cytokines, contain single nucleotide polymorphisms, which are associated with differential levels of gene transcription. This study analyzes single nucleotide polymorphisms in interleukin 10 and tumor necrosis factor α genes and their contribution to breast cancer phenotype, lymph node status and survival in a group of young Lithuanian women with early-stage breast cancer patients. We genotyped 100 premenopausal Eastern European (Lithuanian) patients with stage I-II breast cancer, ≤50 years old at the time of diagnosis, for interleukin 10 -592A > C, −819C > T and -1082A > G and tumor necrosis factor α -308G > A single nucleotide polymorphisms in the gene promoter region. We used the polymerase chain reaction, namely a restriction fragment length polymorphism method, for a SNP analysis. All genotypes were in Hardy-Weinberg equilibrium and had the same distribution as the HapMap CEU population. Holders of IL10 -592A > C heterozygous IL10 -592 AC genotype had a higher probability of estrogen receptor positive breast cancer phenotype than homozygous variants (P = 0.017). Phased ACC haplotype of IL10 polymorphisms was associated with younger age of diagnosis (P = 0.017). Of all the tested single nucleotide polymorphisms, only TNFα -308G > A has revealed a prognostic capability for breast cancer survival. GA genotype carriers, compared to GG, showed a significant disadvantage in progression-free survival (P = 0.005, adjusted hazard ratio (HR) = 4.631, 95 % confidence interval (CI) = 1.587 – 13.512), metastasis-free survival (P = 0.010, HR = 4.708, 95 % CI = 1.445 – 15.345) and overall survival (P = 0.037, HR = 4.829, 95 % CI = 1.098 – 21.243). According to our data, IL10 -1082A > G, −819 T > C, −592A > C polymorphisms and phased haplotypes have not revealed a prognostic value for breast cancer. On the contrary, the TNFα -308 polymorphism might modulate the risk and contribute to the identification of patients at a higher risk of breast cancer recurrence, metastasis and worse overall survival among young Lithuanian early-stage breast cancer patients.
- 26 June 2015
- Published by Springer Nature in BMC Genomic Data
- Vol. 16 (1) , 70
Open AccessThe prognostic value of IL10 and TNF alpha functional polymorphisms in premenopausal early-stage breast cancer patients
Interleukin-10 and tumor necrosis factor α play an important role in breast carcinogenesis. Genes, encoding those two cytokines, contain single nucleotide polymorphisms, which are associated with differential levels of gene transcription. This study analyzes single nucleotide polymorphisms in interleukin 10 and tumor necrosis factor α genes and their contribution to breast cancer phenotype, lymph node status and survival in a group of young Lithuanian women with early-stage breast cancer patients. We genotyped 100 premenopausal Eastern European (Lithuanian) patients with stage I-II breast cancer, ≤50 years old at the time of diagnosis, for interleukin 10 -592A > C, −819C > T and -1082A > G and tumor necrosis factor α -308G > A single nucleotide polymorphisms in the gene promoter region. We used the polymerase chain reaction, namely a restriction fragment length polymorphism method, for a SNP analysis. All genotypes were in Hardy-Weinberg equilibrium and had the same distribution as the HapMap CEU population. Holders of IL10 -592A > C heterozygous IL10 -592 AC genotype had a higher probability of estrogen receptor positive breast cancer phenotype than homozygous variants (P = 0.017). Phased ACC haplotype of IL10 polymorphisms was associated with younger age of diagnosis (P = 0.017). Of all the tested single nucleotide polymorphisms, only TNFα -308G > A has revealed a prognostic capability for breast cancer survival. GA genotype carriers, compared to GG, showed a significant disadvantage in progression-free survival (P = 0.005, adjusted hazard ratio (HR) = 4.631, 95 % confidence interval (CI) = 1.587 – 13.512), metastasis-free survival (P = 0.010, HR = 4.708, 95 % CI = 1.445 – 15.345) and overall survival (P = 0.037, HR = 4.829, 95 % CI = 1.098 – 21.243). According to our data, IL10 -1082A > G, −819 T > C, −592A > C polymorphisms and phased haplotypes have not revealed a prognostic value for breast cancer. On the contrary, the TNFα -308 polymorphism might modulate the risk and contribute to the identification of patients at a higher risk of breast cancer recurrence, metastasis and worse overall survival among young Lithuanian early-stage breast cancer patients.