Implementation of Artificial Intelligence in Personalized Prognostic Assessment of Lung Cancer: A Narrative Review.

Artificial Intelligence (AI) has revolutionized the management of non-small-cell lung cancer (NSCLC) by enhancing different aspects, including staging, prognosis assessment, treatment prediction, response evaluation, recurrence/prognosis prediction, and personalized prognostic assessment. AI algorithms may accurately classify NSCLC stages using machine learning techniques and deep imaging data analysis. This could potentially improve precision and efficiency in staging, facilitating personalized treatment decisions. Furthermore, there are data suggesting the potential application of AI-based models in predicting prognosis in terms of survival rates and disease progression by integrating clinical, imaging and molecular data. In the present narrative review, we will analyze the preliminary studies reporting on how AI algorithms could predict responses to various treatment modalities, such as surgery, radiotherapy, chemotherapy, targeted therapy, and immunotherapy. There is robust evidence suggesting that AI also plays a crucial role in predicting the likelihood of tumor recurrence after surgery and the pattern of failure, which has significant implications for tailoring adjuvant treatments. The successful implementation of AI in personalized prognostic assessment requires the integration of different data sources, including clinical, molecular, and imaging data. Machine learning (ML) and deep learning (DL) techniques enable AI models to analyze these data and generate personalized prognostic predictions, allowing for a precise and individualized approach to patient care. However, challenges relating to data quality, interpretability, and the ability of AI models to generalize need to be addressed. Collaboration among clinicians, data scientists, and regulators is critical for the responsible implementation of AI and for maximizing its benefits in providing a more personalized prognostic assessment. Continued research, validation, and collaboration are essential to fully exploit the potential of AI in NSCLC management and improve patient outcomes. Herein, we have summarized the state of the art of applications of AI in lung cancer for predicting staging, prognosis, and pattern of recurrence after treatment in order to provide to the readers a large comprehensive overview of this challenging issue.

Robotic surgery for thymic cysts: clinical features, management, and results of a multicentric study.

Thymic cysts are rare, radiological diagnosis is often incidental, and cysts seldom assume clinical relevance for symptoms of compression. Thymoma were occasionally found inside both complex and simple thymic cysts. Given the challenges in accurately clinical diagnosing and since the occasionally discovering of thymoma inside both complex and simple thymic cysts, the management of thymic cysts remains controversial. Advancements in surgical tools such as robotics, applied to thymic conditions, could potentially transform the approach to thymic cysts. We report one the largest multicentric series of thymic cysts surgically treated with robotic approach, focusing on preoperative findings and surgical results. Cases were gathered from three Italian thoracic surgery centers with homogeneous clinical practice, significant experience in thymic neoplasms, and thoracic robotic skilled. Surgical intervention was indicated for patients with radiological diagnosis of thymic cysts under the following circumstances: the presence of symptoms, concurrent myasthenia gravis, cysts growing in follow-up, and the complexity of the cyst with suspicion of neoplasm. Data were collected and matched according to postoperative and pathological features to identify potential prognostic factors. Population include 57 patients, 29/28 male/female ratio with mean age of 59.46 ± 11.67 years. The average size of the thymic cysts was 29.14 ± 24.53 ranged between 3 and 150 mm. All patients undergone CT scan and mean of values of density was 25.82 ± 11-82 Hounsfield. Surgical procedures were robotic approach in all case including total/extended thymectomy 35 (61.4%) and cyst resection/partial thymectomy 22 (38.6%). There were no mortality or recurrence. Major complications rate was 5.3%. No correlations were observed between preoperative features and complication. Pathological examination revealed microfoci of thymic tumor in four cases. Robot-assisted surgery for thymic cysts showed excellent early clinical outcomes with low rate of postoperative complications also in case of large lesion. Thymic cysts should not be underestimated due to the risk of coexistent thymic neoplasm.

Uniportal Video-Assisted Thoracoscopic Surgery Completion Lobectomy Long after Wedge Resection or Segmentectomy in the Same Lobe: A Bicenter Study.

BACKGROUND: Completion lobectomy (CL) following a prior resection in the same lobe may be complicated by severe pleural or hilar adhesions. The role of uniportal video-assisted thoracoscopic surgery (U-VATS) has never been evaluated in this setting. METHODS: Data were collected from two Italian centers. Between 2015 and 2022, 122 patients (60 men and 62 women, median age 67.7 ± 8.913) underwent U-VATS CL at least 4 weeks after previous lung surgery. RESULTS: Twenty-eight (22.9%) patients were affected by chronic obstructive pulmonary disease (COPD) and twenty-five (20.4%) were active smokers. Among the cohort, the initial surgery was performed using U-VATS in 103 (84.4%) patients, triportal-VATS in 8 (6.6%), and thoracotomy in 11 (9.0%). Anatomical segmentectomy was the initial surgery in 46 (37.7%) patients, while hilar lymphadenectomy was performed in 16 (13.1%) cases. CL was performed on 110 (90.2%) patients, segmentectomy on 10 (8.2%), and completion pneumonectomy on 2 (1.6%). Upon reoperation, moderate pleural adhesions were observed in 38 (31.1%) patients, with 2 (1.6%) exhibiting strong adhesions. Moderate hilar adhesions were found in 18 (14.8%) patients and strong adhesions in 11 (9.0%). The median operative time was 203.93 ± 74.4 min. In four (3.3%) patients, PA taping was performed. One patient experienced intraoperative bleeding that did not require conversion to thoracotomy. Conversion to thoracotomy was necessary in three (2.5%) patients. The median postoperative drainage stay and postoperative hospital stay were 5.67 ± 4.44 and 5.52 ± 2.66 days, respectively. Postoperative complications occurred in 34 (27.9%) patients. Thirty-day mortality was null. Histology was the only factor found to negatively influence intraoperative outcomes (p = 0.000). Factors identified as negatively impacting postoperative outcomes at univariate analyses were male sex (p = 0.003), age > 60 years (p = 0.003), COPD (p = 0.014), previous thoracotomy (p = 0.000), previous S2 segmentectomy (p = 0.001), previous S8 segmentectomy (p = 0.008), and interval between operations > 5 weeks (p= 0.005). In multivariate analysis, only COPD confirmed its role as an independent risk factor for postoperative complications (HR: 5.12, 95% CI (1.07-24.50), p = 0.04). CONCLUSIONS: U-VATS CL seems feasible and safe after wedge resection and anatomical segmentectomy.

Multicentre retrospective analysis on pulmonary metastasectomy: an European perspective.

OBJECTIVES: To assess the current practice of pulmonary metastasectomy at 15 European Centres. Short- and long-term outcomes were analysed. METHODS: Retrospective analysis on patients ≥18 years who underwent curative-intent pulmonary metastasectomy (January 2010 to December 2018). Data were collected on a purpose-built database (REDCap). Exclusion criteria were: previous lung/extrapulmonary metastasectomy, pneumonectomy, non-curative intent and evidence of extrapulmonary recurrence at the time of lung surgery. RESULTS: A total of 1647 patients [mean age 59.5 (standard deviation; SD = 13.1) years; 56.8% males] were included. The most common primary tumour was colorectal adenocarcinoma. The mean disease-free interval was 3.4 (SD = 3.9) years. Relevant comorbidities were observed in 53.8% patients, with a higher prevalence of metabolic disorders (32.3%). Video-assisted thoracic surgery was the chosen approach in 54.9% cases. Wedge resections were the most common operation (67.1%). Lymph node dissection was carried out in 41.4% cases. The median number of resected lesions was 1 (interquartile range 25-75% = 1-2), ranging from 1 to 57. The mean size of the metastases was 18.2 (SD = 14.1) mm, with a mean negative resection margin of 8.9 (SD = 9.4) mm. A R0 resection of all lung metastases was achieved in 95.7% cases. Thirty-day postoperative morbidity was 14.5%, with the most frequent complication being respiratory failure (5.6%). Thirty-day mortality was 0.4%. Five-year overall survival and recurrence-free survival were 62.0% and 29.6%, respectively. CONCLUSIONS: Pulmonary metastasectomy is a low-risk procedure that provides satisfactory oncological outcomes and patient survival. Further research should aim at clarifying the many controversial aspects of its daily clinical practice.

Survival Outcome After Surgery in Patients With Thymoma Distant Recurrence.

OBJECTIVE: The aim of this study is to describe characteristics and survival outcome of patients who underwent surgical treatment for distant thymoma relapse according to the definition of the International Thymic Malignancy Interest Group. METHODS: Data of patients affected by thymoma recurrence from four different institutions were collected and retrospectively reviewed. Patients with locoregional metastases who underwent nonsurgical therapies and with incomplete data on follow-up were excluded. According to the International Thymic Malignancy Interest Group distant recurrence definition, patients with recurrence due to hematogenic localization were included. Clinical and pathologic characteristics were described using descriptive statistics, whereas survival outcome was calculated using Kaplan-Meier curves and Cox regression analysis. RESULTS: The analysis was conducted on 40 patients. A single localization was present in 13 patients, the relapse was intrathoracic in 28 cases (70%), and lung involvement was found in 26 cases. The liver was operated in seven cases, whereas other kinds of abdominal involvement were detected in eight cases. Adjuvant treatment was administered in 22 cases (55%).Five- and 10-year overall survival (OS) were 67% and 30%, respectively. Univariable analysis identified as significant favorable factor a low-grade histology (A, B1, B2): five-year OS at 92.3% versus 53.3% in high-grade (B3-C) (p = 0.035). Site of recurrence and number of localization did not influence the prognosis, but in patients with adjuvant therapy administration, there was a survival advantage also if not statistically significant: five-year OS 84.8% versus 54.5% in patients without adjuvant therapy (p = 0.101).Multivariable analysis confirmed as independent prognostic factor low-grade histology: hazard ratio = 0.176, 95% confidence interval 0.042-0.744, p = 0.018. CONCLUSIONS: Our study revealed a good survival outcome in patients who underwent surgery for distant thymoma recurrence, independently from the number and site of the relapse localization. Patients with A, B1, or B2 histology presented a significantly better survival than patients with B3-C.

Robotic thymectomy in thymic tumours: a multicentre, nation-wide study.

OBJECTIVES: Robotic thymectomy has been suggested and considered technically feasible for thymic tumours. However, because of small-sample series and the lack of data on long-term results, controversies still exist on surgical and oncological results with this approach. We performed a large national multicentre study sought to evaluate the early and long-term outcomes after robot-assisted thoracoscopic thymectomy in thymic epithelial tumours. METHODS: All patients with thymic epithelial tumours operated through a robotic thoracoscopic approach between 2002 and 2022 from 15 Italian centres were enrolled. Demographic characteristics, clinical, intraoperative, postoperative, pathological and follow-up data were retrospectively collected and reviewed. RESULTS: There were 669 patients (307 men and 362 women), 312 (46.6%) of whom had associated myasthenia gravis. Complete thymectomy was performed in 657 (98%) cases and in 57 (8.5%) patients resection of other structures was necessary, with a R0 resection in all but 9 patients (98.6%). Twenty-three patients (3.4%) needed open conversion, but no perioperative mortality occurred. Fifty-one patients (7.7%) had postoperative complications. The median diameter of tumour resected was 4 cm (interquartile range 3-5.5 cm), and Masaoka stage was stage I in 39.8% of patients, stage II in 56.1%, stage III in 3.5% and stage IV in 0.6%. Thymoma was observed in 90.2% of patients while thymic carcinoma occurred in 2.8% of cases. At the end of the follow-up, only 2 patients died for tumour-related causes. Five- and ten-year recurrence rates were 7.4% and 8.3%, respectively. CONCLUSIONS: Through the largest collection of robotic thymectomy for thymic epithelial tumours we demonstrated that robot-enhanced thoracoscopic thymectomy is a technically sound and safe procedure with a low complication rate and optimal oncological outcomes.

Surgeon experience influence lymphadenectomy during VATS lobectomy: National VATS database results.

OBJECTIVES: Aim of this study is to identify the factors that may influence the lymphadenectomy during VATS anatomical lung resection with particular interest on operator experience. MATERIALS AND METHODS: Clinical and pathological data from the prospective VATS Italian nationwide registry were reviewed and analysed. Patients with incomplete data regarding tumor and surgical characteristics, GGO, or with distant metastases were excluded. Patients clinical data, tumor characteristics, operation information and surgeon experience were collected and compared to resected lymph nodes number (#RN), resected N2 nodes number (#N2RN) and resected N2 stations number. A multivariable model was built using logistic regression analysis. Surgeon experience was categorized considering the number of VATS major anatomical resection and years after residency. RESULTS: The final analysis was conducted on 3727 patients. The median #RN and #N2RN were 11 (1-51) and 5 (0-41). Regarding the analysed outcomes, #N2RN > 6 resulted in 1812 (48.8%)cases, #RN > 10 in 2124 (57.0%)cases and more than 3 N2 stations were harvested in 1447 (38.8%)patients. First operator experience with number of VATS lobectomies>50 (p < 0.001), operator seniority after residency5-10years (p < 0.001), cTNM II/III(p = 0.017), lobectomy/bilobectomy vs segmentectomy (p < 0.001), and upper/middle lobe tumor location (p < 0.005)resulted significantly associated to #N2RN > 6 at the multivariable analysis. First operator experience with number of VATS lobectomies>50 (p < 0.001), operator seniority after residency5-10years (p < 0.001) and lobectomy/bilobectomy (p < 0.001) resulted significantly associated to #RN > 10 at the multivariable analysis. CONCLUSIONS: Our study showed that lymphadenectomy during VATS lobectomy is influenced by tumor factors such as cTstage and tumor location but also by operator experience, with a higher number of resected lymph nodes in surgeons with a high number of VATS procedures and years after residency compared to surgeons with less experience.

BRCA1-associated protein 1: Tumor predisposition syndrome and Kury-Isidor syndrome, from genotype-phenotype correlation to clinical management.

The BAP1 tumor suppressor gene encodes a deubiquitinase enzyme involved in several cellular activities, including DNA repair and apoptosis. Germline pathogenic variants in BAP1 have been associated with heritable conditions including BAP1 tumor predisposition syndrome 1 (BAP1-TPDS1) and a neurodevelopmental disorder known as Kury-Isidor syndrome (KURIS). Both these conditions are caused by monoallelic, dominant alterations of BAP1 but have never been reported in the same subject or family, suggesting a mutually exclusive genotype-phenotype correlation. This distinction is extremely important considering the early onset and aggressive nature of the types of cancer reported in individuals with TPDS1. Genetic counseling in subjects with germline BAP1 variants is fundamental to predicting the effect of the variant and the expected phenotype, assessing the potential risk of developing cancer for the tested subject and the family members who may carry the same variant and providing the multidisciplinary clinical team with the proper information to establish precise surveillance and management protocols.

The Prognostic Role of the Number of Involved Structures in Thymic Epithelial Tumors: Results from the ESTS Database.

BACKGROUND: The role of the number of involved structures (NIS) in thymic epithelial tumors (TETs) has been investigated for inclusion in future staging systems, but large cohort results still are missing. This study aimed to analyze the prognostic role of NIS for patients included in the European Society of Thoracic Surgeons (ESTS) thymic database who underwent surgical resection. METHODS: Clinical and pathologic data of patients from the ESTS thymic database who underwent surgery for TET from January 2000 to July 2019 with infiltration of surrounding structures were reviewed and analyzed. Patients' clinical data, tumor characteristics, and NIS were collected and correlated with CSS using Kaplan-Meier curves. The log-rank test was used to assess differences between subgroups. A multivariable model was built using logistic regression analysis. RESULTS: The final analysis was performed on 303 patients. Histology showed thymoma for 216 patients (71.3%) and NET/thymic carcinoma [TC]) for 87 patients (28.7%). The most frequently infiltrated structures were the pleura (198 cases, 65.3%) and the pericardium in (185 cases, 61.1%), whereas lung was involved in 96 cases (31.7%), great vessels in 74 cases (24.4%), and the phrenic nerve in 31 cases (10.2%). Multiple structures (range, 2-7) were involved in 183 cases (60.4%). Recurrence resulted in the death of 46 patients. The CSS mortality rate was 89% at 5 years and 82% at 10 years. In the univariable analysis, the favorable prognostic factors were neoadjuvant therapy, Masaoka stage 3, absence of metastases, absence of myasthenia gravis, complete resection, thymoma histology, and no more than two NIS. Patients with more than two NIS presented with a significantly worse CSS than patients with no more than two NIS (CSS 5- and 10-year rates: 9.5% and 83.5% vs 93.2% and 91.2%, respectively; p = 0.04). The negative independent prognostic factors confirmed by the multivariable analysis were incomplete resection (hazard ratio [HR] 2.543; 95% confidence interval [CI] 1.010-6.407; p = 0.048) and more than two NIS (HR 1.395; 95% CI 1.021-1.905; p = 0.036). CONCLUSIONS: The study showed that more than two involved structures are a negative independent prognostic factor in infiltrative thymic epithelial tumors that could be used for prognostic stratification.

Surgeon experience does not influence nodal upstaging during vats lobectomy: Results from a large prospective national database.

BACKGROUND: Despite recent improvement in preoperative staging, nodal and mediastinal upstaging occur in about 5% to 15% of cN0 patients. Different clinical and tumor characteristics are associated with upstaging, whereas the role of the surgeon's experience is not well evaluated. This study aimed to investigate if operator experience might influence nodal upstaging during video-assisted thoracic surgery anatomical lung resection. METHODS: Clinical and pathological data from the prospective video-assisted thoracic surgery Italian nationwide registry were reviewed and analyzed. Patients with incomplete data about tumor and surgical characteristics, ground glass opacities tumors, cN2 to 3, and M+ were excluded. Clinical data, tumor characteristics, and surgeon experience were correlated to nodal and mediastinal (N2) upstaging using Pearson's χ2 statistic or Fisher exact test for categorical variables and Mann-Whitney U and t tests for quantitative variables. A multivariable model was built using logistic regression analysis. Surgeon experience was categorized considering the number of video-assisted thoracic surgery major anatomical resections and years after residency. RESULTS: Final analysis was conducted on 3,319 cN0 patients for nodal upstaging and 3,471 cN0N1 patients for N2 upstaging. Clinical tumor-nodes-metastasis stage was stage I in 2,846 (81.9%) patients, stage II in 533 (15.3%), and stage III (cT3N1) in 92 (2.8%). Nodal upstaging occurred in 489 (13.1%) patients, whereas N2 upstaging occurred in 229 (6.1%) patients. Years after residency (P = .60 for nodal, P = .13 for N2 upstaging) and a number of video-assisted thoracic surgery procedures(P = .49 for nodal, P = .72 for nodal upstaging) did not correlate with upstaging. Multivariable analysis confirmed cT-dimension (P = .001), solid nodules (P < .001), clinical tumor-nodes-metastasis (P < .001) and maximum standardized uptake values (P < .001) as factors independently correlated to nodal upstaging, whereas cT-dimension (P = .005), clinical tumor-nodes-metastasis (P < .001) and maximum standardized uptake values (P = .028) resulted independently correlated to N2 upstaging. CONCLUSION: Our study showed that surgeon experience did not influence nodal and mediastinal upstaging during -assisted thoracic surgery anatomical resection, whereas cT-dimension, clinical tumor-nodes-metastasis, and maximum standardized uptake values resulted independently correlated to nodal and mediastinal upstaging.

Prognostic Factors of Non-Predominant-Lepidic Lung Adenocarcinoma Presenting as Ground Glass Opacity: Results of a Multicenter Study.

This study aims to define the clinicopathological characteristics and prognosis of non-predominant lepidic invasive adenocarcinoma presenting as Ground Glass Opacity (GGO) nodules. The goal is to assess statistical relationships between histology, tumor size, location, and the incidence of relapse and lymph node dissemination. A retrospective multicenter study was conducted, including patients with GGO observed on CT scans between 2003 and 2021. Anamnestic, radiological, and histological data, as well as SUV values, lymphatic and vascular invasion, pathological stage, resection type, and adjuvant treatment, were analyzed. The primary endpoints were to evaluate prognostic factors for death and recurrence using Cox regression analysis. All 388 patients, including 277 with non-predominant lepidic invasive adenocarcinoma and 161 with lepidic adenocarcinoma, underwent curative anatomical resection. Non-predominant lepidic invasive adenocarcinoma demonstrated a worse prognosis than lepidic adenocarcinoma (p = 0.001). Independent prognostic factors for death and recurrence included lymph node involvement (p = 0.002) and vascular and lymphatic invasion (p < 0.001). In conclusion, non-predominant lepidic invasive adenocarcinoma and lymphatic and vascular invasion are prognostic factors for death and recurrence in GGO patients. Results suggest adjuvant treatment in the case of pN1-N2 disease, emphasizing the necessity of lymphadenectomy (sampling or systematic) for accurate staging and subsequent therapeutic procedures.

The genetic susceptibility in the development of malignant pleural mesothelioma: somatic and germline variants, clinicopathological features and implication in practical medical/surgical care: a narrative review.

Background and Objective: Malignant pleural mesothelioma (MPM) is a very aggressive primary tumor of the pleura whose main risk factor is exposure to asbestos. However, only a minority of exposed people develops MPM and the incidence of MPM cases without an apparent association with asbestos exposure has been increasing in recent years, suggesting that genetic predisposing factors may play a crucial role. In addition, several studies reported familial cases of MPM, suggesting that heredity may be an important and underestimated feature in MPM development. Several candidate genes have been associated with a predisposition to MPM and most of them play a role in DNA repair mechanisms: overall, approximately 20% of MPM cases may be related to genetic predisposition. A particular category of patients with high susceptibility to MPM is represented by carriers of pathogenic variants in the BAP1 gene. Germline variants in BAP1 predispose to the development of MPM following an autosomal dominant pattern of inheritance in the familial cases. MPMs in these patients are significantly less aggressive, and patients require a multidisciplinary approach that involves genetic counseling, medical genetics, pathology, surgical, medical, and radiation oncology expertise. In the present narrative review, we presented a comprehensive overview of genetic susceptibility in the development of MPM. Methods: The narrative review is based on a selective literature carried out in PubMed in 2023. Inclusion criteria were original articles in English language, and clinical trials (randomized, prospective, or retrospective). Key Content and Findings: We summarized the somatic and germline variants and the differences in terms of clinicopathological features and prognosis between gene-related MPM (GR-MPM) and asbestos-related MPM (AR-MPM). We also discussed the indications for screening, genetic testing, and surveillance of patients with BAP1 germline variants. Conclusions: In this narrative review, we have emphasized that the BAP1 gene's harmful germline variations are inherited in an autosomal dominant manner in familial cases. MPMs in individuals with these variations are less severe, and their medical care necessitates a collaborative effort. Additionally, we have outlined the current therapeutic prospects for MPM, including the possibility of gene-specific therapy, which is currently promising but still requires clinical validation.

Uniportal video-assisted thoracic surgery Ivor-Lewis oesophagectomy with circular stapling anastomosis.

ABSTRACT: Amongst all minimally invasive oesophagectomies, uniportal video-assisted thoracic surgery (VATS) Ivor-Lewis remains the most challenging procedure due to the skills required for performing the intrathoracic anastomosis. We present an easy and safe circular stapling latero-terminal anastomosis for performing uniportal VATS Ivor-Lewis. The patient had an uneventful post-operative recovery and was disease-free 9 months after surgery.