Background: Artificial intelligence (AI) is rapidly transforming thoracic surgery by enhancing diagnostic accuracy, surgical precision, intraoperative guidance, and postoperative management. AI-driven technologies, including machine learning (ML), deep learning, computer vision, and robotic-assisted surgery, have the potential to optimize clinical workflows and improve patient outcomes. However, challenges such as data integration, ethical concerns, and regulatory barriers must be addressed to ensure AI’s safe and effective implementation. This review aims to analyze the current applications, benefits, limitations, and future directions of AI in thoracic surgery. Methods: This review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive literature search was performed using PubMed, Scopus, Web of Science, and Cochrane Library for studies published up to January 2025. Relevant articles were selected based on predefined inclusion and exclusion criteria, focusing on AI applications in thoracic surgery, including diagnostics, robotic-assisted surgery, intraoperative guidance, and postoperative care. A risk of bias assessment was conducted using the Cochrane Risk of Bias Tool and ROBINS-I for non-randomized studies. Results: Out of 279 identified studies, 36 met the inclusion criteria for qualitative synthesis, highlighting AI’s growing role in diagnostic accuracy, surgical precision, intraoperative guidance, and postoperative care in thoracic surgery. AI-driven imaging analysis and radiomics have improved pulmonary nodule detection, lung cancer classification, and lymph node metastasis prediction, while robotic-assisted thoracic surgery (RATS) has enhanced surgical accuracy, reduced operative times, and improved recovery rates. Intraoperatively, AI-powered image-guided navigation, augmented reality (AR), and real-time decision-support systems have optimized surgical planning and safety. Postoperatively, AI-driven predictive models and wearable monitoring devices have enabled early complication detection and improved patient follow-up. However, challenges remain, including algorithmic biases, a lack of multicenter validation, high implementation costs, and ethical concerns regarding data security and clinical accountability. Despite these limitations, AI has shown significant potential to enhance surgical outcomes, requiring further research and standardized validation for widespread adoption. Conclusions: AI is poised to revolutionize thoracic surgery by enhancing decision-making, improving patient outcomes, and optimizing surgical workflows. However, widespread adoption requires addressing key limitations through multicenter validation studies, standardized AI frameworks, and ethical AI governance. Future research should focus on digital twin technology, federated learning, and explainable AI (XAI) to improve AI interpretability, reliability, and accessibility. With continued advancements and responsible integration, AI will play a pivotal role in shaping the next generation of precision thoracic surgery.

Hypertrophic cardiomyopathy (HCM) is an inherited myocardial disease with the presence of left ventricular hypertrophy (LVH). The disease is characterized by high locus, allelic and phenotypic heterogeneity, even among members of the same family. The list of confirmed and potentially relevant genes implicating the disease is constantly increasing, with novel genes frequently reported. Heterozygous alterations in the five main sarcomeric genes (MYBPC3, MYH7, TNNT2, TNNI3, and MYL2) are estimated to account for more than half of confirmed cases. The genetic discoveries of recent years have shed more light on the molecular pathogenic mechanisms of HCM, contributing to substantial advances in the diagnosis of the disease. Genetic testing applying next-generation sequencing (NGS) technologies and early diagnosis prior to the clinical manifestation of the disease among family members demonstrate an important improvement in the field.

Background Recent advances in machine learning have enabled development of the automated Alberta Stroke Program Early CT Score (ASPECTS) prediction algorithms using non-contrast enhanced computed tomography (NCCT) scans. The applicability of automated ASPECTS in daily clinical practice is yet to be established. The objective of this meta-analysis was to directly compare the performance of automated and manual ASPECTS predictions in recognizing early stroke changes on NCCT. Methods The MEDLINE, Scopus, and Cochrane databases were searched. The last database search was performed on March 10, 2022. Studies reporting the diagnostic performance and validity of automated ASPECTS software compared with expert readers were included. The outcomes were the interobserver reliability of outputs between ASPECTS versus expert readings, experts versus reference standard, and ASPECTS versus reference standard by means of pooled Fisher’s Z transformation of the interclass correlation coefficients (ICCs). Results Eleven studies were included in the meta-analysis, involving 1976 patients. The meta-analyses showed good interobserver reliability between experts (ICC 0.72 (95% CI 0.63 to 0.79); p<0.001), moderate reliability in the correlation between automated and expert readings (ICC 0.54 (95% CI 0.40 to 0.67); p<0.001), good reliability between the total expert readings and the reference standard (ICC 0.62 (95% CI 0.52 to 0.71); p<0.001), and good reliability between the automated predictions and the reference standard (ICC 0.72 (95% CI 0.61 to 0.80); p<0.001). Conclusions Artificial intelligence-driven ASPECTS software has comparable or better performance than physicians in terms of recognizing early stroke changes on NCCT.

Traditionally, surgical clipping was the only available treatment modality for intracranial aneurysms. However, in the last few decades, the endovascular therapy of intracranial aneurysms (IAs) has seen a tremendous evolution and development. From coiling to flow diversion and flow disruptor devices, endovascular treatment modalities have increased in number and received broader indications throughout the years. In this review article, the treatment modalities for the endovascular management of IAs are presented, emphasizing newer devices and technologies.

Introduction: Endovascular thrombectomy (EVT) is a well-established and effective therapeutic option for patients that meet certain criteria. However, this modality is not well studied in patients with pre-existing disability. The aim of the present study was to investigate the impact of mechanical thrombectomy in patients with acute onset ischemic stroke and pre-stroke dependency (PSD) in regard to their clinical outcome and mortality.Materials and Methods: The MEDLINE, Scopus, and Cochrane Library databases were comprehensively searched with a cut-off date of December 11th, 2021. We performed meta-analysis to investigate the 90-day clinical outcome, the 90-day mortality, and the rate of symptomatic intracerebral hemorrhage (sICH) between the PSD (modified Rankin Scale score ≥ 3) and non-PSD (modified Rankin Scale score = 0–2) groups who underwent EVT for acute onset ischemic stroke.Results: Six studies were included in the meta-analysis involving 4,543 cases with no PSD and 591 cases with PSD. The non-PSD group showed a statistically significant better clinical outcome at 90 days compared to the PSD group [RR (95% CI) = 1.44 (1.06, 1.85); p_z = 0.02]. The non-PSD group demonstrated a statistically significant lower risk of death at 90 days in comparison to the PSD group [RR (95% CI) = 0.45 (0.41, 0.50); p_z < 0.01]. Lastly, the rate of sICH was comparable between the two groups [RR (95% CI) = 0.89 (0.64, 1.24); p_z = 0.48].Discussion: We report a higher rate of unfavorable clinical outcome and a higher mortality rate in patients with PSD undergoing EVT compared to those with no previous disability. However, there was a significant proportion of PSD cases who fared well post-procedurally, indicating that PSD patients should not be routinely excluded from mechanical thrombectomy.Systematic Review Registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021284181, identifier: CRD42021284181.

The study’s objective was the evaluation of the diagnostic accuracy of the T2-FLAIR mismatch sign in terms of diagnosing IDH-mutant non-codeleted (IDHmut-Noncodel) lower grade gliomas (LGG) of the brain. We searched the MEDLINE, Scopus and Cochrane Central databases. The last database search was performed on 12 April 2021. Studies that met the following were included: MRI scan assessing the presence of T2-FLAIR mismatch sign, and available IDH mutation and 1p/19q codeletion status. The quality of studies was assessed using the QUADAS-2 tool. Twelve studies involving 14 cohorts were included in the quantitative analysis. The diagnostic odds ratio [DOR (95% confidence interval; CI)] was estimated at 34.42 (20.95, 56.56), P_z < 0.01. Pooled sensitivity and specificity (95% CI) were estimated at 40% (31–50%; P_z = 0.05) and 97% (93–99%; P_z < 0.01), respectively. The likelihood ratio (LR; 95% CI) for a positive test was 11.39 (6.10, 21.29; P_z < 0.01) and the LR (95% CI) for a negative test was 0.40 (0.24, 0.65; P_z < 0.01).The T2-FLAIR mismatch sign is a highly specific biomarker for the diagnosis of IDHmut-Noncodel LGGs. However, the test was found positive in some other tumors and had a high number of false negative results. The diagnostic accuracy of the mismatch sign might be improved when combined with further imaging parameters.