Paraskevas Lagakis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Paraskevas Lagakis has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Panagiotis D. Bamidis
School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
4 shared publications - Stavros Demetriadis
Aristotle University of Thessaloniki
4 shared publications - Antonis Billis
Aristotle University of Thessaloniki
3 shared publications Antonis Billis
2 shared publicationsAnastasia Constantinidou
1 shared publication- Andrea Pace
Neuro-Oncology Unit, IRCCS-Regina Elena National Cancer Institute, Rome, Italy
1 shared publication
Latest Publications
- Open Access
- 23 October 2026
- Published by Elsevier in SSRN Electronic Journal
Tele-Rehabilitation and Tele-Psychological Support for People with Cancer across Nine European Countries: Three Multicentre Randomised Controlled Pilot Trials
Background: Telemedicine is used to deliver supportive cancer care, but evidence of benefit remains heterogeneous. We evaluated tele-rehabilitation and tele-psychological support in three multicentre randomised pilot trials within the eCAN Joint Action.Methods: We conducted three exploratory, open-label pilot trials comparing eight weeks of tele-rehabilitation after breast cancer surgery (Pilot 1a), tele-rehabilitation after head and neck cancer surgery (Pilot 1b), or tele-psychological support for advanced or recurrent cancer (Pilot 2) with usual care. Participants were randomly assigned 1:1. EORTC QLQ-C30 Global Health Status/Quality of Life was the principal summary measure, assessed between groups at week 8. Secondary outcomes were pain (Pilots 1a and 1b) and distress (Pilot 2). Analyses used available outcome data. Findings: Between September 2023 and April 2024, 251 participants were enrolled at 16 centres in nine countries: 107 in Pilot 1a, 40 in Pilot 1b, and 104 in Pilot 2. In Pilot 1a, median week 8 global health status was 75·0 with tele-rehabilitation and 62·5 with usual care (p=0·047); baseline pain imbalance limited interpretation of week 8 pain. Pilot 1b was under-recruited and inconclusive. In Pilot 2, global health status did not differ at week 8 (66·7 vs 66·7; p=0·886), whereas distress was lower with tele-psychological support (3·0 vs 5·5; p=0·039).Interpretation: Findings were preliminary and intervention-specific. Tele-rehabilitation after breast cancer surgery showed a signal of higher global health status, whereas tele-psychological support reduced distress without improving global health status. Larger trials with longer follow-up are needed.
- 23 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTele-Rehabilitation and Tele-Psychological Support for People with Cancer across Nine European Countries: Three Multicentre Randomised Controlled Pilot Trials
Background: Telemedicine is used to deliver supportive cancer care, but evidence of benefit remains heterogeneous. We evaluated tele-rehabilitation and tele-psychological support in three multicentre randomised pilot trials within the eCAN Joint Action.Methods: We conducted three exploratory, open-label pilot trials comparing eight weeks of tele-rehabilitation after breast cancer surgery (Pilot 1a), tele-rehabilitation after head and neck cancer surgery (Pilot 1b), or tele-psychological support for advanced or recurrent cancer (Pilot 2) with usual care. Participants were randomly assigned 1:1. EORTC QLQ-C30 Global Health Status/Quality of Life was the principal summary measure, assessed between groups at week 8. Secondary outcomes were pain (Pilots 1a and 1b) and distress (Pilot 2). Analyses used available outcome data. Findings: Between September 2023 and April 2024, 251 participants were enrolled at 16 centres in nine countries: 107 in Pilot 1a, 40 in Pilot 1b, and 104 in Pilot 2. In Pilot 1a, median week 8 global health status was 75·0 with tele-rehabilitation and 62·5 with usual care (p=0·047); baseline pain imbalance limited interpretation of week 8 pain. Pilot 1b was under-recruited and inconclusive. In Pilot 2, global health status did not differ at week 8 (66·7 vs 66·7; p=0·886), whereas distress was lower with tele-psychological support (3·0 vs 5·5; p=0·039).Interpretation: Findings were preliminary and intervention-specific. Tele-rehabilitation after breast cancer surgery showed a signal of higher global health status, whereas tele-psychological support reduced distress without improving global health status. Larger trials with longer follow-up are needed.
- 2 July 2026
- Published by Springer Nature
- p. 404-411
Design and Evaluation of Eva.ai: A Conversational AI Learning Environment for Programming Education
- 2 July 2026
- Published by Springer Nature
- p. 404-411
Design and Evaluation of Eva.ai: A Conversational AI Learning Environment for Programming Education
- Open Access
- 12 June 2026
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 12 (1) , e75050
Identification of Early Signs of Mental Health Disorders in Older Survivors of Cancer Using Patient-Generated Health Data: Observational Study
Background: Older survivors of cancer face heightened risk of depression and anxiety related to cancer experiences, fear of recurrence, and aging-related difficulties. Conventional mental health monitoring approaches, such as clinical assessments and even electronic patient-reported outcomes, are limited by recall bias, patient burden, and infrequent data collection. Emerging patient-generated health data from wearables and smart home devices offer passive, low-burden, continuous monitoring, but their ability to capture mental health risks in older survivors of cancer remains unclear. Objective: This study aims to explore whether patient-generated health data collected in the wild, either passively or actively, can classify older survivors of cancer as having or not having signs of anxiety and depression based on Patient Health Questionnaire-4 (PHQ-4) scores and to assess the potential added value of passive monitoring modalities, such as smart plugs. Methods: This study recruited 41 older survivors of cancer (mean age 72.3, SD 6.81 years) from the LifeChamps project. Over a 12-week period, participants were monitored using an activity tracker to measure physical activity, sleep, and physiological metrics; a smart scale to capture weight and body composition; and a smart plug to track television use as a proxy for sedentary television viewing. Mental health status was self-reported via the PHQ-4 questionnaire in a mobile app. Machine learning models were trained to classify mental health risk based on features derived from each sensor modality, both independently and in combination. Results: Tree-based gradient boosting models showed good performance in classifying PHQ-4–defined mental health risk. The best-performing configuration, combining smart plug and smart scale features, achieved a mean F 1 -score of 0.77 (SD 0.15) and a mean area under the receiver operating characteristic curve (AUC) of 0.85 (SD 0.10) across 3 repeated train-test splits. Standalone smart plug models, based solely on passive television use patterns, achieved a mean F 1 -score of 0.66 (SD 0.04) and a mean AUC of 0.71 (SD 0.06), outperforming models that relied only on activity tracker data (mean F 1 0.59, SD 0.2). Multimodal combinations tended to improve average performance but did not consistently yield large gains over the strongest single-modality configurations, likely reflecting adherence-related data loss for wearables and scales. Crucially, passive monitoring of television use patterns emerged as a promising behavioral proxy measure of mental health states. Conclusions: This study pioneers the use of passively collected data (eg, smart plugs) for mental health monitoring in older survivors of cancer, demonstrating their potential. Smart plugs capture behavioral patterns without user burden, with reasonable standalone performance (mean AUC 0.71, SD 0.06), positioning them as a promising low-burden modality. Future work should validate findings in larger independent cohorts and in prospective clinical workflows. Such technologies could transform monitoring for vulnerable populations, enabling scalable, inclusive care while reducing health care burdens.
- 12 June 2026
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 12 (1) , e75050
Open AccessIdentification of Early Signs of Mental Health Disorders in Older Survivors of Cancer Using Patient-Generated Health Data: Observational Study
Background: Older survivors of cancer face heightened risk of depression and anxiety related to cancer experiences, fear of recurrence, and aging-related difficulties. Conventional mental health monitoring approaches, such as clinical assessments and even electronic patient-reported outcomes, are limited by recall bias, patient burden, and infrequent data collection. Emerging patient-generated health data from wearables and smart home devices offer passive, low-burden, continuous monitoring, but their ability to capture mental health risks in older survivors of cancer remains unclear. Objective: This study aims to explore whether patient-generated health data collected in the wild, either passively or actively, can classify older survivors of cancer as having or not having signs of anxiety and depression based on Patient Health Questionnaire-4 (PHQ-4) scores and to assess the potential added value of passive monitoring modalities, such as smart plugs. Methods: This study recruited 41 older survivors of cancer (mean age 72.3, SD 6.81 years) from the LifeChamps project. Over a 12-week period, participants were monitored using an activity tracker to measure physical activity, sleep, and physiological metrics; a smart scale to capture weight and body composition; and a smart plug to track television use as a proxy for sedentary television viewing. Mental health status was self-reported via the PHQ-4 questionnaire in a mobile app. Machine learning models were trained to classify mental health risk based on features derived from each sensor modality, both independently and in combination. Results: Tree-based gradient boosting models showed good performance in classifying PHQ-4–defined mental health risk. The best-performing configuration, combining smart plug and smart scale features, achieved a mean F 1 -score of 0.77 (SD 0.15) and a mean area under the receiver operating characteristic curve (AUC) of 0.85 (SD 0.10) across 3 repeated train-test splits. Standalone smart plug models, based solely on passive television use patterns, achieved a mean F 1 -score of 0.66 (SD 0.04) and a mean AUC of 0.71 (SD 0.06), outperforming models that relied only on activity tracker data (mean F 1 0.59, SD 0.2). Multimodal combinations tended to improve average performance but did not consistently yield large gains over the strongest single-modality configurations, likely reflecting adherence-related data loss for wearables and scales. Crucially, passive monitoring of television use patterns emerged as a promising behavioral proxy measure of mental health states. Conclusions: This study pioneers the use of passively collected data (eg, smart plugs) for mental health monitoring in older survivors of cancer, demonstrating their potential. Smart plugs capture behavioral patterns without user burden, with reasonable standalone performance (mean AUC 0.71, SD 0.06), positioning them as a promising low-burden modality. Future work should validate findings in larger independent cohorts and in prospective clinical workflows. Such technologies could transform monitoring for vulnerable populations, enabling scalable, inclusive care while reducing health care burdens.
- 23 May 2025
- Published by Springer Nature
- p. 133-153
Design, Development, Piloting, and Evaluation of Smart, Digital Health Applications to Tackle Urgent Cancer Priorities
- 23 May 2025
- Published by Springer Nature
- p. 133-153
Design, Development, Piloting, and Evaluation of Smart, Digital Health Applications to Tackle Urgent Cancer Priorities
- 1 June 2024
- Published by Springer Nature
- p. 378-385
EvaAI: A Multi-agent Framework Leveraging Large Language Models for Enhanced Automated Grading
- 1 June 2024
- Published by Springer Nature
- p. 378-385
EvaAI: A Multi-agent Framework Leveraging Large Language Models for Enhanced Automated Grading
- Open Access
- 16 May 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 215
Semantic interoperability for an AI-based applications platform for smart hospitals using HL7 FHIR
- 16 May 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 215
Open AccessSemantic interoperability for an AI-based applications platform for smart hospitals using HL7 FHIR
- 27 February 2024
- Published by Springer Nature
- p. 363-373
Automated Grading in Coding Exercises Using Large Language Models
- 27 February 2024
- Published by Springer Nature
- p. 363-373
Automated Grading in Coding Exercises Using Large Language Models
- Open Access
- 18 May 2023
- Published by IOS Press
- Vol. 302, 376-377
Towards the Definition of an Intelligent System for Organizing Medical Visits and Collecting Medical Data
Appointment Scheduling (AS), typically serves as the basis for the majority of non-urgent healthcare services and is a fundamental healthcare-related procedure which, if done correctly and effectively, can lead to significant benefits for the healthcare facility. The main objective of this work is to present ClinApp, an intelligent system able to schedule and manage medical appointments and collect medical data directly from patients.
- 18 May 2023
- Published by IOS Press
- Vol. 302, 376-377
Open AccessTowards the Definition of an Intelligent System for Organizing Medical Visits and Collecting Medical Data
Appointment Scheduling (AS), typically serves as the basis for the majority of non-urgent healthcare services and is a fundamental healthcare-related procedure which, if done correctly and effectively, can lead to significant benefits for the healthcare facility. The main objective of this work is to present ClinApp, an intelligent system able to schedule and manage medical appointments and collect medical data directly from patients.
- 9 April 2022
- Published by Springer Nature
- p. 443-453
Automated Essay Feedback Generation in the Learning of Writing: A Review of the Field
- 9 April 2022
- Published by Springer Nature
- p. 443-453
Automated Essay Feedback Generation in the Learning of Writing: A Review of the Field