Vytautas Juknevičius

Vytautas Juknevičius

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
10 February 2025 in Nature Medicine
Verified
Journal Article
Open access
PDF file
LJL. S. Johnson
L. S. Johnson
PZP. Zadrozniak
P. Zadrozniak
GJG. Jasina
G. Jasina
AGA. Grotek-Cuprjak
A. Grotek-Cuprjak
JAJason G Andrade
Jason G Andrade
JHJ. S. Healey
J. S. Healey
Developments in ambulatory electrocardiogram (ECG) technology have led to vast amounts of ECG data that currently need to be interpreted by human technicians. Here we tested an artificial intelligence (AI) algorithm for direct-to-physician reporting of ambulatory ECGs. Beat-by-beat annotation of 14,606 individual ambulatory ECG recordings (mean duration = 14 ± 10 days) was performed by certified ECG technicians (n = 167) and an ensemble AI model, called DeepRhythmAI. To compare the performance of the AI model and the technicians, a random sample of 5,235 rhythm events identified by the AI model or by technicians, of which 2,236 events were identified as critical arrhythmias, was selected for annotation by one of 17 cardiologist consensus panels. The mean sensitivity of the AI model for the identification of critical arrhythmias was 98.6% (95% confidence interval (CI) = 97.7–99.4), as compared to 80.3% (95% CI = 77.3–83.3%) for the technicians. False-negative findings were observed in 3.2/1,000 patients for the AI model versus 44.3/1,000 patients for the technicians. Accordingly, the relative risk of a missed diagnosis was 14.1 (95% CI = 10.4–19.0) times higher for the technicians. However, a higher false-positive event rate was observed for the AI model (12 (interquartile range (IQR) = 6–74)/1,000 patient days) as compared to the technicians (5 (IQR = 2–153)/1,000 patient days). We conclude that the DeepRhythmAI model has excellent negative predictive value for critical arrhythmias, substantially reducing false-negative findings, but at a modest cost of increased false-positive findings. AI-only analysis to facilitate direct-to-physician reporting could potentially reduce costs and improve access to care and outcomes in patients who need ambulatory ECG monitoring.

27 June 2021 in Medicina
Verified
Journal Article
Open access
PDF file
VJVytautas Juknevičius
Vytautas Juknevičius
ABAndrius Berukstis
Andrius Berukstis
RJRenata Juknevičienė
Renata Juknevičienė
EJEugenijus Jasiūnas
Eugenijus Jasiūnas
Pranas ŠerpytisPranas Šerpytis
Pranas Šerpytis
ALAleksandras Laucevičius
Aleksandras Laucevičius
Background and Objectives: Renal artery denervation (RDN) procedure is a broadly discussed method in the treatment of resistant hypertension. Many studies report short-term (3–12 months) results for blood pressure and arterial stiffness. The primary endpoints were changes in 24 h mean systolic blood pressure (BP) and office systolic BP 48 months after RDN. The secondary endpoints were changes in aortic pulse wave velocity and impact of polypharmacy on these variables. Materials and Methods: Renal artery denervation was performed in 73 patients treated for resistant hypertension; 49 patients remained in final analysis. Patient examination was carried out before the procedure, and subsequently at 3, 6, 12, 24, and 48 months later. Patients’ antihypertensive and overall medication regimens were carefully analysed. Results: Mean 24 h arterial blood pressure lowered and was sustained at lower levels for up to 48 months; median (interequartile range—IQR) from 158(23.5)/100(14.2) to 140(26.5)/86(16.2) mmHg. Mean reduction in 24 h ambulatory systolic BP was −11 ± 25 mmHg (95% CI, −20 to −2; p < 0.001), while office systolic BP reduced by −7 ± 23 mmHg (95%CI, −24 to −1; p < 0.02). A significant reduction in median aortic pulse wave velocity 12 months after the procedure (drop from baseline 11.2 [3.15] m/s (95%CI 6.1 to 16.2) to 9.8 [2.1] m/s (95%CI 6.1 to 13.7; p = 0.002)). After 48 months, there was no worsening compared to the baseline level of 10.3 [4.0] m/s (95% CI 6.9 to 17.8) (p > 0.05). The total mean number of antihypertensive drugs remained unchanged: 5.97(±1.1) vs. 5.24 (±1.45). A higher number of pills after 48 months was associated with higher aortic pulse wave velocity (1–5 pill group: 8.1 ± 1.6 m/s; 6–10 pill group: 10.9 ± 1.8 m/s; >11 pill group: 15.1 ± 2.6 m/s) (p = 0.003). Conclusions: Antihypertensive effect after renal denervation lasts up to 48 months with no worsening of arterial stiffness compared to baseline. In our study, polypharmacy was associated with increased arterial stiffness 48 months after the procedure.

22 July 2022 in Medicine
Verified
Journal Article
Open access
RJRenata Juknevičienė
Renata Juknevičienė
VJVytautas Juknevičius
Vytautas Juknevičius
EJEugenijus Jasiūnas
Eugenijus Jasiūnas
BRBeatričė Raščiūtė
Beatričė Raščiūtė
BJBarysienė Jūratė
Barysienė Jūratė
Pranas ŠerpytisPranas Šerpytis
Pranas Šerpytis
High-sensitivity troponin assay brought new challenges as we detect elevated concentration in many other diseases, and it became difficult to distinguish the real cause of this elevation. In this notion, diagnosis of acute coronary syndrome (ACS) remains a challenge in emergency department (ED). We aim to examine different approaches for rule-in and rule-out of ACS using risk scores, copeptin, and coronary computed tomography angiography (CCTA). A prospective observational study was designed to evaluate chest pain patients. Consecutive adult patients admitted to the ED with a chief complaint of chest pain due to any cause were included. All patients were followed-up for 6 months after discharge for major adverse cardiovascular events and readmissions. Admission data, ED processes, and diagnoses were analyzed. One hundred forty-six patients were included, average age was 63 ± 13.4 years, and 95 (65.1%) were male. Global Registry of Acute Coronary Events (GRACE) and History, ECG, Age, Risk factors, Troponin (HEART) scores showed good prognostic abilities, but HEART combination with copeptin improves diagnoses of myocardial infarction (area under the curve [AUC] 0.764 vs AUC 0.864 P = .0008). Patients with elevated copeptin were older, had higher risk scores, and were more likely to be admitted to hospital and diagnosed with ACS in ED. For copeptin, AUC was 0.715 (95% confidence interval 0.629–0.803), and for combination with troponin, AUC of 0.770 (0.703–0.855) did not improve rule-in of myocardial infarction. High-sensitivity troponin I assay alongside prior stroke, history of carotid stenosis, dyslipidemia, use of diuretics, and electrocardiogram changes (left bundle branch block or ST depression) are good predictors of myocardial infarction (χ² = 52.29, AUC = 0.875 [0.813–0.937], P < .001). The regression analysis showed that combination of copeptin and CCTA without significant stenosis can be used for ACS rule-out (χ² = 26.36, P < .001, AUC = 0.772 [0.681–0.863], negative predictive value of 96.25%). For rule-in of ACS, practitioner should consider not only scores for risk stratification but carefully analyze medical history and nonspecific electrocardiogram changes and even with normal troponin results, we strongly suggest thorough evaluation in chest pain unit. For rule-out of ACS combination of copeptin and CCTA holds great potential.

1 January 2026 in IEEE Journal of Translational Engineering in Health and Medicine
Verified
Journal Article
Open access
KEKarolina Eitminaviciene
Karolina Eitminaviciene
DSDaivaras Sokas
Daivaras Sokas
ŽAŽygimantas Abramikas
Žygimantas Abramikas
DKDziugile Kersnauskaite
Dziugile Kersnauskaite
DSDominika Sirviene
Dominika Sirviene
APAndrius Petrėnas
Andrius Petrėnas

16 March 2022
Verified
Thesis
Closed access
VJVytautas Juknevičius
Vytautas Juknevičius
Evaluation of patients with resistant arterial hypertension before and after pharmacological treatment correction or a renal artery sympathetic denervation procedure