Andrius Paulauskas

Mr. Andrius Paulauskas


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
18 November 2019 in Information
Verified
Journal Article
Open access
PDF file
RMRytis Maskeliūnas
Rytis Maskeliūnas
RDRobertas Damaševičius
Robertas Damaševičius
CLConnie Lethin
Connie Lethin
APAndrius Paulauskas
Andrius Paulauskas
Anna EspositoAnna Esposito
Anna Esposito
VAVincenzo Aschettino
Vincenzo Aschettino
We describe the iDO serious game developed during implementation of the Innovative Digital Training Opportunities on Dementia for Direct Care Workers (IDO) project. The project targets formal and informal caregivers of persons with dementia in order to improve caregiver knowledge and competences skills with a non-traditional source of training. This paper describes the steps faced to define the iDO caregiver behavior improvement model, design of game mechanics, development of game art and game characters, and implementation of gameplay. Furthermore, it aimed to assess the direct impact of the game on caregivers (n = 48) and seniors with early signs of dementia (n = 14) in Lithuania measured with the Geriatric Depression Scale (GDS) and Dementia Attitudes Scale (DAS). The caregivers’ GDS scores showed a decrease in negative answers from 13.4% (pre-game survey) to 5.2% (post-game survey). The seniors’ GDS scores showed a decrease in negative answers from 24.9% (pre-game survey) to 10.9% (post-game survey). The overall DAS scores increased from 6.07 in the pre-game survey to 6.41 in the post-game survey, statistically significant for both caregivers and seniors (p < 0.001), respectively. We conclude that the game aroused positive moods and attitudes for future caregivers of persons with dementia, indicating a more relaxed status and a decreased fear in accomplishing the caring process.
1

30 November 2022 in Information
Verified
Journal Article
Open access
PDF file
RMRytis Maskeliūnas
Rytis Maskeliūnas
RDRobertas Damasevicius
Robertas Damasevicius
APAndrius Paulauskas
Andrius Paulauskas
Maria Gabriella CeravoloMaria Gabriella Ceravolo
Maria Gabriella Ceravolo
Marina CharalambousMarina Charalambous
Marina Charalambous
Carlos Vaz de CarvalhoCarlos Vaz de Carvalho
Carlos Vaz de Carvalho
This paper describes a serious game based on a knowledge transfer model using deep reinforcement learning, with an aim to improve the caretakers’ knowledge and abilities in post-stroke care. The iTrain game was designed to improve caregiver knowledge and abilities by providing non-traditional training to formal and informal caregivers who deal with stroke survivors. The methodologies utilized professional medical experiences and real-life evidence data gathered during the duration of the iTrain project to create the scenarios for the game’s deep reinforcement caregiver behavior improvement model, as well as the design of game mechanics, game images and game characters, and gameplay implementation. Furthermore, the results of the game’s direct impact on caregivers (n = 25) and stroke survivors (n = 21) in Lithuania using the Geriatric Depression Scale (GDS) and user experience questionnaire (UEQ) are presented. Both surveys had favorable outcomes, showing the effectiveness of the approach. The GDS scale (score 10) revealed a low number of 28% of individuals depressed, and the UEQ received a very favorable grade of +0.8.

6 October 2022
Verified
Book Chapter
Closed access
PDF file
AAAfxentis Afxentiou
Afxentis Afxentiou
PFPeter Frühmann
Peter Frühmann
MKMaria Kyriakidou
Maria Kyriakidou
MPMaria Patsarika
Maria Patsarika
Daina GudonieneDaina Gudoniene
Daina Gudoniene
Francisco García-PeñalvoFrancisco García-Peñalvo
Francisco García-Peñalvo

18 July 2025 in BMC Psychology
Verified
Journal Article
Open access
JJJovita Janavičiūtė-Pužauskė
Jovita Janavičiūtė-Pužauskė
RPRaimonda Petrolienė
Raimonda Petrolienė
LZLoreta Zajančkauskaitė-Staskevičienė
Loreta Zajančkauskaitė-Staskevičienė
APAndrius Paulauskas
Andrius Paulauskas
LŠLiuda Šinkariova
Liuda Šinkariova
Background: This study aims to determine whether cognitive training based on an egocentric perspective leads to greater improvements in target functions compared to training using an allocentric perspective or conventional rehabilitation. Additionally, it seeks to examine whether egocentric perspective-based training enhances the near transfer effect, resulting in improved other cognitive functions compared to allocentric perspective-based training and conventional rehabilitation. Methods: 132 stroke patients (65.9% males) aged 31 to 83 (mean age 62.54 ± 10.62) undergoing inpatient rehabilitation were randomly assigned to one of the three groups: allocentric (N = 40) or egocentric perspective-based (N = 46) selective visual attention and short-term visual memory training and control (conventional rehabilitation) group (N = 46). Evaluations were performed before (at the beginning of rehabilitation for control group) and after the intervention (two weeks after pre-test for control group). The target functions included the changes in short-term visual memory, visual-spatial attention, attention-orientation, while near transfer effect included the changes in visuo-construction abilities, task switching, verbal memory, verbal fluency, language, visuo-spatial abilities, general cognitive function. To investigate how different perspectives affect selective visual attention and short-term visual memory training and near-transfer effect over time, while accounting for baseline cognitive scores, were conducted mixed repeated measures ANOVA and ANCOVA (controlled for age, years of education, lesion location, and days since stroke). A priori power analysis and effect sizes using Cohen’s dz for matched pairs were calculated. Results: The results showed that cognitive rehabilitation tasks based on egocentric perspective in combination to conventional rehabilitation are effective in improving attention-orientation and cause near transfer effect on spatial abilities and general cognitive functioning. While tasks based on allocentric perspective in combination to conventional rehabilitation are effective in improving short-term visual memory and cause near transfer effect on spatial abilities. Conclusions: The cognitive improvements and near-transfer effects observed in our results indicate that combining conventional rehabilitation with tasks based on egocentric and allocentric perspectives integrated in virtual reality environments can enhance rehabilitation effectiveness. However, further studies are required to confirm the generalizability of these findings. Trial registration: The present study, along with its protocol, was retrospectively registered in the ISRCTN clinical trial registry on January 3, 2024 (https://doi.org/10.1186/ISRCTN14922230).

10 February 2026 in Journal of Stroke and Cerebrovascular Diseases
Verified
Journal Article
Open access
JJJovita Janavičiūtė-Pužauskė
Jovita Janavičiūtė-Pužauskė
RPRaimonda Petrolienė
Raimonda Petrolienė
LZLoreta Zajančkauskaitė-Staskevičienė
Loreta Zajančkauskaitė-Staskevičienė
APAndrius Paulauskas
Andrius Paulauskas
LŠLiuda Šinkariova
Liuda Šinkariova
This study aimed to evaluate the role of egocentric and allocentric perspectives in facilitating far transfer (improvement of emotional state and psychomotor functions) following cognitive training in stroke patients. In a three-arm, non-blind, randomized clinical trial, 128 patients with acute stroke were randomly allocated to one of the following groups: 1) control, 2) allocentric perspective, or 3) egocentric perspective groups. Each group received a 2-week intervention, with the experimental groups completing an additional 10 sessions. Cognitive function was measured by the Addenbrooke Cognitive Evaluation-III, depression by the Patient Health Questionnaire-9, anxiety by the Generalized Anxiety Disorder-7 scale, and psychomotor function by the Finger Tapping Test. Cognitive training tasks based on allocentric and egocentric perspectives, when combined with conventional rehabilitation, did not yield a statistically significant far transfer effect compared to conventional rehabilitation alone. No significant differences between-groups were observed for changes in anxiety (F(2, 111) = .056, p = .945, η2 = .058), depression (F(2, 109) = 0.831, p = .160, η2 = .074), or dominant (F(2, 111) = 0.059, p = .943, η2 = .001) and non-dominant (F(2, 108) = 1.375, p = .257, η2 = .290) psychomotor functions. The incorporation of an allocentric and egocentric perspective based cognitive training tasks in conventional rehabilitation do not provide significantly better improvements in emotional state and psychomotor functions. The ISRCTN clinical trial registry (https://doi.org/10.1186/ISRCTN14922230).

28 March 2020 in International Journal of Computers Communications & Control
Verified
Journal Article
Open access
PDF file
CCCenker Canbulut
Cenker Canbulut
APAndrius Paulauskas
Andrius Paulauskas
Tomas BlažauskasTomas Blažauskas
Tomas Blažauskas
The use of peripheral devices could be a good alternative to interact with Virtual Environment in addition to native controllers. Using combination of Concept-II peripheral device with VR mobile will cause latency issues due to different data transmission rates between those components. This latency issue leads to two major problems, such as micro-stutter in Virtual Environment (VE) and distance inaccuracy in time between the Concept-II peripheral device and VR mobile. In this paper, the authors present three algorithms based on interpolation and extrapolation methods, which aim to provide immersive VR experience by ensuring stutter-free and accurate rowing sessions for the user. This is relevance when considering the adoption of peripheral devices (i.e. the Concept-II peripheral device) as an alternative to interact with Virtual Environment in addition to native controllers. Predicting virtual rowing shell’s position using interpolation by position method gives accurate time results but introduces high amount of micro-stutter. Using extrapolation method by taking speed parameter to predict rowing shell’s position has very high time error but gives pleasant, stutter-free virtual rowing experience. Finally, adding this speed parameter a correction constant value for predicting virtual rowing shell’s position provides stutter-free and very accurate in time rowing session for the user.