Jaruševičius, Laimonas
Radiotherapy and diagnostic capacity in relation to the changing cancer burden in the Baltic StatesItem type:Publication, research article[2026][S1][M001][8]; ;Paļskis, Kristaps ;Dosanjh, Manjit ;Bray, Freddie ;Gershkevitsh, Eduard ;Balode, Inga ;Bernans, Alvis ;Boka, Gaļina; ;Liepa, Zanda ;Mežeckis, Māris; ;Radziņa, Maija ;Skomskis, Romas ;Smailytė, Giedrė ;Stepiņa, SandraVenius, JonasActa Oncologica, 2026-04-27, vol. 65, p. 355-362Background 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.
15 Plaučių vėžio diagnostikos ir gydymo rekomendacijos: mokomoji knygaItem type:Publication, book[2026][K2b][M001][140]; ; ; ; ;Česas, Alvydas; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; Kaunas : Lietuvos pulmonologų ir alergologų draugija, 2026-04-23Plaučių vėžys vis dar tebėra didžiulė grėsmė ne tik pasaulio, Europos Sąjungos, bet ir Lietuvos gyventojams. Siekiant pagerinti pagalbą plaučių vėžiu sergantiems ligoniams, suvienodinti specialistų požiūrį į šios ligos diagnostikos ir gydymo standartus, Lietuvos sveikatos mokslų universiteto ir Lietuvos sveikatos priežiūros specialistų draugijų iniciatyva bei bendru darbu nuo 2007-ųjų kas kelerius metus išleidžiamos „Plaučių vėžio diagnostikos ir gydymo rekomendacijos“. Išlaikydami tradicijas ir tęstinumą pristatome aštuntąsias atnaujintas ir papildytas „Plaučių vėžio diagnostikos ir gydymo rekomendacijas“, kurios yra gausaus autorių, savo srities ekspertų ir pagrindinių Lietuvos sveikatos priežiūros specialistų draugijų atstovų, kolektyvo ilgametės patirties, bendro nuolatinio darbo rezultatas. Plaučių vėžio gydymas išlieka viena dinamiškiausių onkologijos sričių, todėl ankstesnes rekomendacijas buvo būtina atnaujinti apžvelgiant svarbiausias prigijusias naujoves. Plaučių vėžio profilaktika, ankstyva diagnostika ir atrankinė patikra yra viena iš prioritetinių sričių naujame Europos Sąjungos kovos su vėžiu plane. Kai kuriose Europos Sąjungos šalyse jau yra įdiegtos nacionalinės plaučių vėžio patikros programos, kitose, taip pat ir Lietuvoje, vykdomos ar jau atliktos bandomosios programos. Tačiau, kol nėra patvirtinta nacionalinė plaučių vėžio patikros programa Lietuvoje, šiose rekomendacijose paliekame tikslinės plaučių vėžio atrankinės patikros gaires, kurios sėkmingai pritaikytos daugelyje Europos Sąjungos šalių ir yra patvirtintos Lietuvoje Plaučių vėžio metodiniame dokumente. Tikimės, kad netolimoje ateityje galėsime pristatyti ir nacionalinę plaučių vėžio atrankinės patikros programą. [...].
10 Machine Learning Methods for Predicting Cancer Complications Using Smartphone Sensor Data: A Prospective StudyItem type:Publication, research article[2026][S1][M001][18] ;Dargė, Gabrielė ;Kasputytė, Gabrielė ;Savickas, Paulius; ;Bunevičienė, Inesa; ; ; ; ;Bunevičius, Romas ;Krikštolaitis, Ričardas ;Krilavičius, TomasApplied Sciences, 2026-01-01, vol. 16, no. 1, p. 1-18Complications 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.
13 Treatment Outcomes for Malignant Peripheral Lung Tumours: A Prospective Single-Centre Comparison of Thermal Ablation, Surgery, and RadiotherapyItem type:Publication, research article[2025][S1][M001][21]; ;Maziliauskienė, Gertrūda ;Dubeikaitė, Rūta; ; ; ; ; ; ; ; ;Mišeikytė-Kaubrienė, Edita; Medicina, 2025-11-03, vol. 61, no. 11, p. 1-21Background and Objectives: Lung cancer and pulmonary metastases are major causes of cancer-related mortality. Surgery is a standard curative approach, but many patients are ineligible due to age, comorbidities, or treatment preference. This study aimed to evaluate the safety, effectiveness, and quality-of-life outcomes of thermal ablation versus surgery and stereotactic body radiotherapy (SBRT) for malignant lung lesions. Materials and Methods: A prospective, non-randomized study was conducted on 68 patients with primary or metastatic lung tumours treated by surgery (n = 19), SBRT (n = 29), or thermal ablation (n = 20). The key outcomes included recurrence rates and patterns, disease-free and overall survival, complications, hospitalization, and health-related quality of life (HRQoL). Results: Surgery demonstrated the lowest total and regional recurrence rates (21.1% and 10.5%, respectively), significantly lower than SBRT (57.1% and 42.9%, respectively; p < 0.05). Additionally, surgery led to the longest disease-free survival but was associated with the highest complication rate (78.9%) and the greatest HRQoL decline. SBRT had fewer complications (17.2%) and moderate HRQoL outcomes. Thermal ablation showed no significant differences in recurrence (45.0% of total recurrence) or survival compared to surgery or SBRT, with a moderate complication rate (45.0%) and the most favorable HRQoL outcomes. Major complications were rare and comparable across all groups. Conclusions: Thermal ablation demonstrated comparable disease control and quality-of-life outcomes to SBRT, with lower complication rates. While surgery remains superior in local disease control, its invasiveness and impact on quality of life underscore the importance of minimally invasive treatments in multidisciplinary management of malignant lung lesions.
35WOS© Citations 1 Personalized Multidisciplinary Management of Skull Osteosarcoma at the Kaunas Clinics Sarcoma CenterItem type:Publication, conference poster[2025][T1e][M001,N010][3]; ; ; ; ; ; ; ; ; ; 10th Kaunas/Lithuania International Hematology/Oncology Colloquium : 23 May 2025 : Online Poster Abstract Book / Editor Prof. Elona Juozaitytė, 2025-05-23, p. 22-24Introduction and aim Sarcomas are rare malignancies of mesenchymal origin, with an annual incidence of 5–7 cases per 100,000 (1,2). Osteosarcoma (OS) is the most common primary malignant bone tumor, representing around 20% of all primary bone cancers (3). However, craniofacial (skull and jaw) localization is exceptionally rare and accounts for less than 10% of all cases (4). In contrast to conventional osteosarcoma, typically affecting adolescents and young adults, craniofacial OS more often occurs in older patients (4). Clinically, these tumors present as a firm, enlarging mass in the facial or cranial region and might cause symptoms such pain, facial asymmetry, neurologic signs or dental issues (5). Standard treatment of high-grade OS consists of perioperative chemotherapy (ChT) and surgery aiming R0 resection. Treatment should be planned and delivered by a specialized sarcoma multidisciplinary team (MDT) (6). As the anatomical complexity of the skull poses significant challenges for surgical management, achieving wide margins is often unfeasible (4). In such cases, postoperative radiotherapy may be considered (7). Despite optimal treatment, craniofacial OS carries a significant risk of local recurrence up to in 30–40%of the cases. Five-year overall survival in localized disease is 60-70% (7). Notably, these tumors demonstrate lower rates of pulmonary metastases compared to appendicular OS, possibly due to higher rates of local relapse influencing its prognosis (4). We present a case of an adult patient with OS of the skull to highlight its diagnostic and therapeutic complexity and the importance of personalized management in a specialized sarcoma center. Case report A 42-year-old man presented at the Sarcoma Center, Hospital of LUHS Kaunas Clinics, with a progressively enlarging lump on his forehead and intense headache. MRI revealed a 4.4 × 2.8 × 5.0 cm tumor mass occupying the frontal sinuses, with intracranial and extracranial extension. Biopsy confirmed the diagnosis of high-grade osteosarcoma. No evidence of distant metastasis was found. As the patient was deemed fit for ChT and given the importance of a shrinkage to achieve clear margins neoadjuvant MAP ChT was started. However, after the first cycle of metotrexate, the patient developed severe acute kidney injury. Methotrexate and cisplatin were excluded in favor of carboplatin and doxorubicin. After two cycles of ChT MRI showed initial dimensional and tissue response and considering the good tolerability the MDT decided to proceed with two more cycles to improve the quality of surgery. R0 surgery including reconstruction with cement cranioplasty followed, with excellent cosmetic and functional outcome. Due to clear margins and the risk of postoperative complications, adjuvant radiotherapy was not administered. The patient completed two further cycles of postoperative ChT. After a-1-year followup, the patient remains free from disease. Discussion Craniofacial OS are rare and present unique management challenges due to the complex anatomy of the skull and proximity to vital structures (4). In this case, the involvement of both intracranial and extracranial compartments required careful coordination between oncology, radiology, surgery, and supportive care. Since management in a specialized sarcoma center is crucial to coordinate care across disciplines and to provide individualized treatment planning (6) treatment decisions were made through repeated multidisciplinary team (MDT) discussions at a dedicated sarcoma center, enabling timely adaptation of the therapeutic plan based on toxicity and response. The initial use of MAP ChT was guided by the need to achieve maximal tumor shrinkage to allow radical resection. However, the onset of methotrexate-induced nephrotoxicity necessitated a regimen change. Response evaluation after two cycles of carboplatin-doxorubicin showed favorable changes in both size and imaging characteristics (e.g., mineralization, reduced enhancement), which informed the MDT decision to prolong neoadjuvant treatment. This highlights the critical role of dynamic response assessment in guiding the number of ChT cycles and improving resectability. Achieving R0 margins was essential to omit radiotherapy and avoid additional morbidity, which can be significant in such a delicate and functionally critical craniofacial region (7). This case reveals the value of specialized sarcoma center care, where individualized treatment, case-by-case MDT decision-making, and response guided therapy are fundamental for optimal outcomes. Conclusions Management of all sarcomas, including skull OS should be conducted in a specialized sarcoma center to ensure expert, multidisciplinary care. Treatment must be tailored case-by-case, balancing oncologic goals with patient-specific factors and therapy tolerability
15 Large language models for enhancing pretreatment education in pediatric radiation oncologyItem type:Publication, conference output[2025][T1a][M001][3] ;Wawrzuta, Dominik ;Napieralska, Aleksandra ;Ludwikowska, Katarzyna; ;Trofimoviča-Krasnorucka, Anastasija ;Rausis, Gints ;Szulc, Agata ;Pędzwiatr, Katarzyna ;Poláchová, Kateřina ;Klejdysz, JustynaChojnacka, MarzannaRadiotherapy and Oncology : ESTRO 2025, 2-6 May 2025, Vienna, Austria, 2025-05-01, vol. 206, no. Suppl. 1, p. 2149-2151Purpose/Objective: Pediatric radiotherapy patients and their parents often become aware of the need for treatment early on, but consultations with radiation oncologists typically occur later in the care process. Consequently, they search for information online, often encountering unreliable sources [1]. Large language models (LLMs) have the potential to serve as an educational pretreatment tool, providing reliable answers to their questions [2,3]. Our objective was to evaluate the quality of the responses provided by LLMs for patients and parents seeking information on pediatric radiation oncology. Material/Methods: We collected 80 pretreatment questions related to radiotherapy from pediatric patients and their parents. Responses were generated using GPT-3.5, GPT-4, and a fine-tuned GPT-3.5 model, specifically trained using pediatric radiotherapy guides from various institutions. In addition, a radiation oncologist (RO) provided expert answers as the gold standard. Thus, four distinct answers were obtained for each of the 80 questions. A multi-institutional group of nine pediatric radiotherapy experts conducted a blind review, evaluating responses based on reliability, conciseness, and comprehensibility using Likert scales (1-5 for reliability, 1-3 for conciseness, and 1-3 for comprehensibility). Each response was reviewed by five different experts. A composite score (scale 0-1) was calculated by averaging the standardized scores across the three dimensions. The flowchart of the methodological steps followed in the study is presented in Figure 1. Results: The RO and GPT-4 generated the highest-quality responses (median composite scores: 0.90 vs. 0.86, p=0.26). However, GPT-4 often provided overly verbose answers (median concision scores: 3.00 vs. 2.80, p<0.0001). The finetuned GPT-3.5 model outperformed the base GPT-3.5 model in overall quality (median composite scores: 0.81 vs. 0.74, p<0.05), particularly improving conciseness (median concision scores: 2.80 vs. 2.40, p<0.0001), but often produced overly simplistic answers that lacked nuance (median reliability scores: 4.00 vs. 4.50, p<0.05). The results for all categories are presented in Figure 2. Low-quality responses, mostly characterized by irrelevant or excessively detailed information, were rare, occurring in 4% of GPT-generated answers (mainly in GPT-3.5), and were absent in RO responses. Conclusion: LLMs have the potential to be effective tools for pretreatment education in pediatric radiation oncology. However, only advanced models such as GPT-4 provide information comparable to that of a radiation oncologist, though occasional low-quality responses still occur. Caution should be exercised when using GPT-3.5 models, as they are more prone to providing irrelevant answers to patient questions.
3 Large language models for pretreatment education in pediatric radiation oncology: A comparative evaluation studyItem type:Publication, research article[2025][S1][M001][6] ;Wawrzuta, Dominik ;Napieralska, Aleksandra ;Ludwikowska, Katarzyna; ;Trofimoviča-Krasnorucka, Anastasija ;Rausis, Gints ;Szulc, Agata ;Pędziwiatr, Katarzyna ;Poláchová, Kateřina ;Klejdysz, JustynaChojnacka, MarzannaClinical and translational radiation oncology, 2025-03-01, vol. 51, p. 1-6Background and purpose: Pediatric radiotherapy patients and their parents are usually aware of their need for radiotherapy early on, but they meet with a radiation oncologist later in their treatment. Consequently, they search for information online, often encountering unreliable sources. Large language models (LLMs) have the potential to serve as an educational pretreatment tool, providing reliable answers to their questions. We aimed to evaluate the responses provided by generative pre-trained transformers (GPT), the most popular subgroup of LLMs, to questions about pediatric radiation oncology.
27WOS© Citations 4 Optimizing contouring process in radiotherapy: AI-powered automation for organs segmentationItem type:Publication, conference paper[2024][T1a][M001][1] ;Venskauskaitė, R.; ; ;Adlienė, D.Šutienė, K.Physica Medica : Abstracts of the 5th European Congress of Medical Physics : 11-14 September 2024, 2024-09-04, vol. 125, no. Suppl. 1, p. 418-418Introduction: Manual delineation of organs at risk (OARs) is crucial step for precise radiation delivery and radiation-induced toxicity. Recent artificial intelligence (AI) advancements offer a solution by reducing observer variability, adhering to guidelines, and improving accuracy of the contouring. Despite this, auto-segmentation is underutilized due to limited open-source frameworks for DICOM RT structure sets. The purpose of this study was to develop a custom software adapted to the needs of radiotherapy department. Materials & Methods: Total Segmentator_v2 is nnUnet based on AI segmentation package available on GitHub capable of segmenting 117 structures. However, direct use in radiotherapy workflow is not possible due to requirements for data format conversion and not all the structures are appropriate for treatment planning. Due to this reason, a custom software based on Python programming language was developed and adapted to the needs of radiotherapy department. Results: Using publicly available AI models, custom software tools were developed, allowing fully automatic segmentation and preparation of structure set. Depending on the scanned body area, up to 39 structures could be contoured in 4-6 minutes, providing significant time saving in comparison with manual segmentation. The nnUnet self-adapting neural network architecture, in conjunction with Total Segmentator_v2 software and additional Python functionalities, demonstrated high efficiency in the automated delineation process. Summary: Implementing automated workflow, potentially were improved the efficiency and accuracy of delineation, paving the way for more precise and personalized treatment planning. Even publicly available AI-based segmentation tools could be successfully used for routine delineation, further clinical validation is necessary
20 Neoadjuvant intensified chemotherapy vs standard therapy in locally advanced rectal cancerItem type:Publication, conference paper[2024][T1a][M001][1]; ; ; ; ; ; ; Annals of Oncology : Abstract Book of the ESMO Gastrointestinal Cancers Congress 2024, 26-29 June 2024, 2024-06-29, vol. 35, no. Suppl. 1, p. 105-105Background Standard therapy for locally advanced rectal cancer includes concurrent chemoradiotherapy (CRT) followed by surgery and adjuvant chemotherapy. An alternative strategy - neoadjuvant intensified chemotherapy (NIC) involves administration of neoadjuvant chemotherapy (FOLFOX4) before surgery plus concomitant chemoradiation (in those only who did not achieve MRF (neg.)) with the goal of delivering optimized systemic therapy to eradicate micrometastases. A comparison of these 2 approaches was the aim of study. Methods This is a prospective single institution clinical trial. The study included patients with locally advanced stage II-III rectal cancer. Patients were randomized 1:1 for neoadjuvant concomitant CRT or NIC (FOLFOX4 regimen, a total of 8 cycles). Results 142 patients (pts.) were included into the study. The median follow-up is 24 months. Both groups are well balanced. At baseline, MRF was involved in 40/65 pts. (62%) in the NIC arm and in 49/77 pts. (64%) in CRT arm (p=0.862). Radiologically, MRF remained involved after initial treatment in 17/40 pts (42.5%) NIC group and 22/49 pts. (44.9%) in the CRT group. Surgery was not performed in 11/65 pts. (16,9%) from NIC arm due to disease progression or early deaths during neoadjuvant treatment. In the CRT arm surgery was not performed in 15/77 pts. (19,5%). After surgery, circumferential resection margin (CRM) was involved in 2/44 pts. (5%) in NIC and in 1/55 pts. (2%). pCR was achieved in 3/44 pts (7%) NIC group and in 9/55 pts. (16%) CRT group (not sig). After treatment in NIC arm, a reduction in the tumor stage (evaluated by radiologist) was observed in 13/50 (26%) pts, and in pathologist’s report – in 27/44 pts (61%). In CRT arm, radiological downstaging was achieved in 28/69 pts. (41%) and pathologically in 39/55 (71%) ((not sig).). Three-year DFS was 86,4% and 92,7% in NIC and CRT groups, respectively (p = 0.6). Three-year overall survival (OS) did not differ statistically significantly between groups. Conclusions The preliminary findings of this ongoing prospective clinical trial did not show statistically significant difference in 3 year DFS and OS between neoadjuvant intensified chemotherapy and neoadjuvant concomitant chemoradiation arms but numerically chemoradiation arm was more benefitial.
13 Changing Clinical Characteristics and Management of Local Rectal Cancer During Recent DecadesItem type:Publication, conference poster[2024][T1e][M001][2]; ; ; ; ; ; ; ; ; ; ; ; ; ; ; 9th Kaunas / Lithuania International Hematology / Oncology Colloquium : 24 May 2024 : Online Poster Abstract Book / Editor Elona Juozaitytė, 2024-05-24, p. 3-4Background and Objective Diagnostics and treatment of rectal cancer has changed dramatically over the past 20 years. Detailed radiological examination using MRI, surgical and radiotherapy innovations, neoadjuvant and adjuvant therapy have been implemented into the practice. Multidisciplinary team discussions on regular basis has started in the Hospital since 2013. Indeed, the wide application of screening programs is essential for early diagnosis of the disease – the pilot colorectal cancer screening in Kaunas region has started from 2009 and wide screening program was implemented in all the country since 2013. These innovations affect patients' life expectancy and quality. This is a retrospective analysis covering 20 years of single-institution clinical experience in the diagnostics and treatment of local rectal cancer. Material and Method Data on 924 patients which were treated for local (stage I-III) rectal cancer from 2004 till 2024 were retrospectively collected at the Hospital of Lithuanian University of Health Sciences (LUHS) Kauno klinikos. The period was divided into two decades (A, from 2004 till 2013, and B, from 2014 till March of 2024) to assess treatment progress. The groups were compared in terms of clinical characteristics and applied treatment. [...].
28