A Machine Learning Approach for Postoperative Outcome Prediction: Surgical Data Science Application in a Thoracic Surgery Setting.

BACKGROUND: The use of innovative methodologies, such as Surgical Data Science (SDS), based on artificial intelligence (AI) could prove to be useful for extracting knowledge from clinical data overcoming limitations inherent in medical registries analysis. The aim of the study is to verify if the application of an AI analysis to our database could develop a model able to predict cardiopulmonary complications in patients submitted to lung resection. METHODS: We retrospectively analyzed data of patients submitted to lobectomy, bilobectomy, segmentectomy and pneumonectomy (January 2006-December 2018). Fifty preoperative characteristics were used for predicting the occurrence of cardiopulmonary complications. The prediction model was developed by training and testing a machine learning (ML) algorithm (XGBOOST) able to deal with registries characterized by missing data. We calculated the receiver operating characteristic curve, true positive rate (TPR), positive predictive value (PPV) and accuracy of the model. RESULTS: We analyzed 1360 patients (lobectomy: 80.7%, segmentectomy: 11.9%, bilobectomy 3.7%, pneumonectomy: 3.7%) and 23.3% of them experienced cardiopulmonary complications. XGBOOST algorithm generated a model able to predict complications with an area under the curve of 0.75, a TPR of 0.76, a PPV of 0.68. The model's accuracy was 0.70. The algorithm included all the variables in the model regardless of their completeness. CONCLUSIONS: Using SDS principles in thoracic surgery for the first time, we developed an ML model able to predict cardiopulmonary complications after lung resection based on 50 patient characteristics. The prediction was also possible even in the case of those patients for whom we had incomplete data. This model could improve the process of counseling and the perioperative management of lung resection candidates.

Computed tomography-guided microcoil placement for localizing small pulmonary nodules before uniportal video-assisted thoracoscopic resection.

PURPOSE: The increasing number of computed tomography (CT) performed allows the more frequent identification of small, solid pulmonary nodules or ground-glass opacities. Video-assisted thoracic surgery (VATS) represents the standard in most lung resections. However, since VATS limit is the digital palpation of the lung parenchyma, many techniques of nodule localization were developed. The aim of this study was to determine the feasibility and safety of CT-guided microcoil insertion followed by uniportal VATS wedge resection (WR). MATERIALS AND METHODS: Retrospective study in a single institution, including patients undergone CT-guided microcoil insertion prior to uniportal VATS resection between May 2015 and December 2018. The lesion was identified using fluoroscopy. RESULTS: Forty-six consecutive patients were enrolled (22 male and 24 female). On CT: 5 cases of GGO, 2 cases of semisolid nodules, 39 cases of solid nodules. The median pathologic tumor size was 1.21 cm. Neither conversion to thoracotomy nor microcoil dislodgement was recorded. All patients underwent uniportal VATS WR (9/46 underwent completion lobectomy after frozen section). WR median time was 105 min (range 50-150 min). No patients required intraoperative re-resection for positive margins. After radiological procedure, 1 case of hematoma and 2 cases of pneumothorax were recorded. Four complications occurred in the postoperative period. The mean duration of chest drain and length of stay were 2.9 and 4.6 days, respectively. CONCLUSIONS: CT-guided microcoil insertion followed by uniportal VATS resection was a safe and feasible procedure having a minimal associated complications rate and offering surgeons the ease of localization of small intrapulmonary nodules.

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.

Impact of enhanced pathway of care in uniportal video-assisted thoracoscopic surgery.

Enhanced Recovery After Surgery (E.R.A.S.) is a multimodal, evidence-based and patient-centered pathway designed to minimize surgical stress, enhancing recovery and improving perioperative outcomes. However, considering that the potential clinical implication of E.R.A.S. on patients undergoing video-assisted thoracic surgery (V.A.T.S.) has not properly defined, we proposed to implement our minimally invasive program with a specific clinical pathway able to enhance recovery after lung resection. Aim of this study was to assess the impact of this integrated program of Enhanced Pathway of Care (E.P.C.) in Uniportal V.A.T.S. patients undergoing lung resection, in terms of efficiency and safety. We conducted a retrospective, observational study enrolling patients undergoing uniportal V.A.T.S. resections from January 2015 to May 2020. Two groups were created: pre-E.P.C. and E.P.C. Propensity score matching analysis was performed to evaluate length of stay (LOS), postoperative cardiopulmonary complications (CPC) and readmission rate (READM). We analyzed 1167 patients (E.P.C. group: 182; pre-E.P.C. group: 985). E.P.C. group has a mean LOS shorter compared to pre-E.P.C. group (3.13 vs 4.19 days, p < 0.0001) without increasing on CPC (E.P.C. 12% vs pre-E.P.C. 11%, p = 0.74) and READM rate (E.P.C. 1.6% vs pre-E.P.C. 4.9%, p = 0.07). In particular, the LOS was shortened in the E.P.C. patients submitted to lobectomy, segmentectomy and wedge resection. Moreover, the three subgroups had similar CPC and READM rates for E.P.C. and control patients. In conclusion, this study demonstrated the benefits and safety of E.P.C. program showing a reduction of LOS for patients undergoing uniportal V.A.T.S. resection.

Uniportal video-assisted thoracoscopic thymectomy: the glove-port with carbon dioxide insufflation.

BACKGROUND: Since 2004, uniportal video-assisted thoracic surgery (VATS) approach was progressively widespread and also applied in the treatment of thymoma, with promising results. We report the first series of patients who undergone uniportal VATS thymectomy using a homemade glove-port with carbon dioxide (CO2) insufflation. The aim of this article is to analyze the safety and feasibility to perform an extended thymectomy (ET). METHODS: A prospective, single-centre, short-term observational study including patients with mediastinal tumours undergoing scheduled uniportal VATS resection using a glove-port with CO2. Operations were performed through a single incision of 3.5 cm at the fifth intercostal space, right or left anterior axillary line. A 5 mm-30° camera and working instruments were employed through a glove-port with CO2. RESULTS: Thirty-eight patients (20 men; mean age 61.6 years) underwent ET between September 2016 and October 2019. Thirteen patients had a history of Myasthenia Gravis (MG) with thymoma and 8 had incidental findings of thymoma. Additionally, 8 mediastinal cysts and 9 thymic hyperplasia were included. Mean diameter of the tumor was 5.1 cm (range, 1.6-14 cm) and mean operation time was 143 minutes. Mean postoperative drainage duration and hospital stay were 2.3 and 4.3 days, respectively. Mean blood loss was 41 mL. There was no occurrence of surgical morbidity or mortality. During the follow-up period (1-36 months), no recurrence was noted. CONCLUSIONS: Our results suggest that uniportal VATS thymectomy through glove-port and CO2 is safe and feasible procedure, even with large thymomas. Furthermore, the glove-port system represents a valid, cheap and widely available alternative to the commercial devices usually adopted in thoracic surgery.

Chest wall lipoma mimicking intrathoracic mass: Imaging with surgical correlation.

Lipoma is the most frequent benign soft-tissue tumor. It originates from fat cells. According to position, it is distinguished in superficial, typically subcutaneous lipoma, or deep, such as intramuscular lipoma. This latter form is infrequently and may resemble well-differentiated liposarcoma. For this reason, early radiological detection and characterization are necessary to obtain a wide complete resection and histopathologic evaluation to differentiate benign from malign lesions. We report an extremely rare case of an intrathoracic intramuscular lipoma of the chest wall detect and characterize with chest X-ray and computed tomography examinations, resected with thoracoscopic intervention and confirmed with histopathologic analysis.

Pre-treatment systemic immune-inflammation represents a prognostic factor in patients with advanced non-small cell lung cancer.

BACKGROUND: Inflammation plays an important role in pathogenesis, development and progression of lung cancer. The aim of the study is to assess the prognostic role of Systemic Immune-Inflammation Index (SII), obtained by analyzing the neutrophil, lymphocyte and platelet counts, and to design prognostic models for patients receiving first-line chemo- or targeted therapy for advanced non-small cell lung cancer (NSCLC). METHODS: We conducted an analysis on 311 patients with advanced NSCLC, treated with first line chemo- or targeted therapy till June 2015 at our Institution. Patients were stratified in two groups with SII ≥1,270 (Group A) vs. SII <1,270 (Group B). Progression free survival (PFS) and overall survival (OS) were estimated using Kaplan-Meier method. The best SII cutoff was identified by X-tiles program. A Cox regression model was carried out for univariate and multivariate analyses. RESULTS: At baseline, 179 patients had SII ≥1,270 (Group A), whilst 132 had lower SII (Group B). The median OS was 12.4 months in Group A and 21.7 months in Group B (P<0.001), whilst the median PFS was 3.3 and 5.2 months, respectively (P=0.029). At multivariate analysis, male gender, ECOG-PS ≥2 and SII >1,270 were predictors of worst OS, whilst IV tumor stage was only slightly significant (P=0.08). Otherwise, only wild-type EGFR status and SII ≥1,270 were independent prognostic factors for worst PFS. CONCLUSIONS: Pre-treatment SII is an independent prognostic factor for patients with advanced NSCLC treated with first-line therapies.

Video-assisted thoracic surgery lobectomy does not offer any functional recovery advantage in comparison to the open approach 3 months after the operation: a case matched analysis†.

OBJECTIVES: The objective of the present study was to compare functional loss [forced expiratory volume in one second to forced vital capacity ratio (FEV1), DLCO and VO2max reduction] after VATS versus open lobectomies. METHODS: We performed a prospective observational study on 195 patients who had a pulmonary lobectomy from June 2010 to November 2014 and who were able to complete a 3-months functional evaluation follow-up program. Since the VATS technique was our first choice for performing lobectomies from January 2012, we divided the patients into two groups: the OPEN group (112 patients) and the VATS group (83 patients). The open approach was intended as a muscle sparing/nerve sparing lateral thoracotomy. Fourteen baseline factors were used to construct a propensity score to match the VATS-group patients with their OPEN-group counterparts. These two matched groups were then compared in terms of reduction of FEV1, DLCO and VO2max (Mann-Whitney test). RESULTS: The propensity score analysis yielded 83 well-matched pairs of OPEN and VATS patients. In both groups, 3 months postoperatively, we found a reduction in FEV1, DLCO and VO2max values (OPEN patients: FEV1-10%, DLCO -11.9%, VO2max - 5.5%; VATS patients: FEV1-7.2%, DLCO-10.6%, VO2max-6.9%). The reductions in FEV1, DLCO and VO2max were similar to those in the two matched groups, with a Cohen effect size <0.2 for all the comparisons. CONCLUSIONS: In 3 months, both OPEN patients and VATS patients experienced a reduction in their preoperative functional parameters. VATS lobectomy does not offer any advantages in terms of FEV1, DLCO and exercise capacity recovery in comparison to the muscle-sparing thoracotomy approach.

Hyponatremia normalization as an independent prognostic factor in patients with advanced non-small cell lung cancer treated with first-line therapy.

The aim of the study was to assess, for the first time, the prognostic role of hyponatremia and sodium normalization in patients receiving first-line chemo- or targeted therapy for advanced non-small cell lung cancer.Four hundred thirty-three patients with advanced non small cell lung cancer were treated with first line chemo- or targeted therapy between 2006 and 2015 at our institutions. Patients were stratified in two groups, with or without hyponatremia (group A and B, respectively). Progression free survival (PFS) and overall survival (OS) were estimated using Kaplan-Meier method. A Cox regression model was carried out for univariate and multivariate analyses.Sixty-nine patients (16%) presented with hyponatremia at the start of first-line therapy. The median OS was 8.78 months in Group A and 15.5 months in Group B (p < 0.001), while the median PFS was 4.1 months and 6.3 months respectively (p = 0.24). In Group A, median OS was significantly higher in patients who normalized their sodium levels (11.6 vs. 4.7 months, p = 0.0435). Similarly, the median PFS was significantly higher in patients who normalized their sodium levels (6.7 vs. 3.3 months, p = 0.011). At multivariate analysis, sodium normalization was an independent prognostic factor for both OS and PFS.Sodium normalization during first-line therapy is an independent prognostic factor for OS and PFS in patients with advanced lung cancer treated with first-line therapies. Frequent clinical monitoring and prompt treatment of hyponatremia should be emphasized to optimize the outcome of these patients.

Clinical pathway for thoracic surgery in an Italian centre.

Clinical care pathways are developed to standardize postoperative patient care and the main impetus is to improve quality of care, decrease variation in care and reduce costs. We report the clinical pathway of care adopted at our centre since the introduction of Uniportal VATS program for major lung resections.

Recurrent air leak soon after pulmonary lobectomy: an analysis based on an electronic airflow evaluation†.

OBJECTIVES: The objective of this analysis was to evaluate the incidence and risk factors of recurrent air leak (RAL) occurring soon after pulmonary lobectomy based on electronic airflow measurements. METHODS: A prospective observational analysis of 129 consecutive patients managed with a single chest tube connected with an electronic chest drainage system. The incidence and timing of RAL among patients who had an air leak sealed within the first 24 postoperative hours was recorded. Stepwise logistic regression and bootstrap analyses were used to test the association of several baseline and surgical variables with RAL. RESULTS: A total of 95 patients (68%) had their air leak stopped within 24 h after the operation. Twelve patients had RAL (13%) after the first stop. All RALs occurred within the first 24 h from operation. Logistic regression showed that the presence of moderate-to-severe chronic obstructive pulmonary disease [COPD; forced expiratory volume in 1 s (FEV1) <80% and FEV1/forced vital capacity ratio <0.7] was an independent risk factor associated with RAL (P = 0.02, bootstrap frequency 83%). Seven of 27 (26%) patients with COPD had RAL, a proportion significantly higher than in patients without COPD (5 of 68, 7.3%, P = 0.03). CONCLUSIONS: A large proportion of patients with COPD developed RAL. In this high-risk group, we advise against chest tube removal in the first 24 h after operation, even in the case of absence or cessation of air leak.

Prognostic models to predict survival in patients with advanced non-small cell lung cancer treated with first-line chemo- or targeted therapy.

BACKGROUND: We aimed to assess the prognostic role of neutrophilia, lymphocytopenia and the neutrophil-to-lymphocyte ratio (NLR), and to design models to define the prognosis of patients receiving first-line chemo- or targeted therapy for advanced non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: We retrospectively analysed 401 consecutive patients with advanced NSCLC treated with first line chemo- or targeted therapy. Patients were stratified into two groups with pre-treatment NLR ≥ 3.7 (Group A) vs. < 3.7 (Group B). The best NLR cut-off was identified by ROC curve analysis. RESULTS: At baseline 264 patients had NLR≥3.7 (Group A), whilst 137 had lower NLR (Group B). Median OS was 10.8 months and 19.4 months in the two groups (p < 0.001), while median PFS was 3.6 months and 5.6 months, respectively (p = 0.012). At multivariate analysis, ECOG-PS≥2, stage IV cancer, non-adenocarcinoma histology, EGFR wild-type status and NLR were predictors of worse OS. Stage IV cancer, wild type EGFR status and NLR≥3.7 were independent prognostic factors for worse PFS. Patients were stratified according to the presence of 0-1 prognostic factors (8%), 2-3 factors (73%) and 4-5 factors (19%) and median OS in these groups was 33.7 months, 14.6 months and 6.6 months, respectively (p < 0.001). Similarly, patients were stratified for PFS based on the presence of 0-1 prognostic factor (15%), 2 factors (41%) and 3 factors (44%). The median PFS was 8.3 months, 4.6 months and 3.3 months respectively (p < 0.001). CONCLUSIONS: Pre-treatment NLR is an independent prognostic factor for patients with advanced NSCLC treated with first-line therapies.

Clinical and pathologic predictors of clinical outcome of malignant pleural mesothelioma.

AIMS AND BACKGROUND: Although worldwide use of asbestos has decreased, the incidence of malignant pleural mesothelioma (MPM) is expected to increase over the next few decades. A number of scoring systems has been proposed to assess clinicopathologic features and to predict the prognosis. We assessed the relationship between patients' features and disease evolution in order to choose the best treatment able to prolong overall survival (OS) and progression-free survival (PFS). METHODS: We retrospectively analyzed patients with locally advanced or metastatic MPM, treated at the Department of Medical Oncology, Università Politecnica Marche, Italy, from January 2003 to September 2013. Data on age, sex, smoking history, asbestos exposure, performance status, tumor stage, histology, type of treatment, and routine laboratory tests including complete blood count panel, date of death, or censored status were collected. The OS and PFS were estimated using Kaplan-Meier method and Cox analysis was performed to analyze the prognostic relevance of clinical parameters. RESULTS: We enrolled a total of 62 patients. Univariate analysis showed that histologic type, performance status, response to first-line therapy, pretreatment hemoglobin levels, and plasmatic Ca125 were significant prognostic factors. Conversely, no significant correlation was found between age, sex, smoking history, reported exposure to asbestos, stages at diagnosis, treatments, and OS and PFS. CONCLUSIONS: Our results showed that anemia and increased Ca125 might be considered negative prognostic parameters in MPM patients and confirmed the prognostic role of histotype, performance status, and response to first-line chemotherapy.

Patient satisfaction with health-care professionals and structure is not affected by longer hospital stay and complications after lung resection: a case-matched analysis.

OBJECTIVES: The objective of this investigation was to assess satisfaction with care of patients with long hospital stay (LHS) or complications after pulmonary resection in comparison with case-matched counterparts with a regular postoperative course. METHODS: This is a prospective observational analysis on 171 consecutive patients submitted to pulmonary resections (78 wedges, 8 segmentectomies, 83 lobectomies, 3 pneumonectomies) for benign (35), primary (93) or secondary malignant (43) diseases. A hospital stay >7 days was defined as long (LHS). Major cardiopulmonary complications were defined according to the ESTS database. Patient satisfaction was assessed by the administration of the EORTC IN-PATSAT32 module at discharge. The questionnaire is a 32-item self-administered survey including different scales, reflecting the perceived level of satisfaction about the care provided by doctors, nurses and other personnel. To minimize selection bias, propensity score case-matching technique was applied to generate two sets of matched patients: patients with LHS with counterparts without it; patients with complications with counterparts without it. RESULTS: Median length of postoperative stay was 4 days (range 2-43). Forty-one patients (24%) had a hospital stay>7 days and 21 developed cardiopulmonary complications (12%). Propensity score yielded two well-matched groups of 41 patients with and without LHS. There were no significant differences in any patient satisfaction scale between the two groups. The comparison of the results of the patient satisfaction questionnaire between the two matched groups of 21 patients with and without complications did not show significant differences in any scale. CONCLUSIONS: Patients experiencing poor outcomes such as long hospital stay or complications have similar perception of quality of care compared with those with regular outcomes. Patient-reported outcome measures are becoming increasingly important in the evaluation of the quality of care and may complement more traditional objective indicators such as morbidity or length of stay.

Locally advanced rectal cancer: the importance of a multidisciplinary approach.

Rectal cancer accounts for a relevant part of colorectal cancer cases, with a mortality of 4-10/100000 per year. The development of locoregional recurrences and the occurrence of distant metastases both influences the prognosis of these patients. In the last two decades, new multimodality strategies have improved the prognosis of locally advanced rectal cancer with a significant reduction of local relapse and an increase in terms of overall survival. Radical surgery still remains the principal curative treatment and the introduction of total mesorectal excision has significantly achieved a reduction in terms of local recurrence rates. The employment of neoadjuvant treatment, delivered before surgery, also achieved an improved local control and an increased sphincter preservation rate in low-lying tumors, with an acceptable acute and late toxicity. This review describes the multidisciplinary management of rectal cancer, focusing on the effectiveness of neoadjuvant chemoradiotherapy and of post-operative adjuvant chemotherapy both in the standard combined modality treatment programs and in the ongoing research to improve these regimens.

Preoperative maximum oxygen consumption is associated with prognosis after pulmonary resection in stage I non-small cell lung cancer.

BACKGROUND: The objective of this investigation was to evaluate whether maximum oxygen consumption (VO2max) is a reliable prognostic factor after lung resection for pathologic stage I non-small cell lung cancer (NSCLC). METHODS: Observational analysis of 157 patients undergoing pulmonary lobectomy or segmentectomy for pathologic stage I (T1 or T2-N0 only) NSCLC, with preoperative measurement of Vo2max and complete follow-up (2006-2011). Survival was calculated by the Kaplan-Meier method. The log-rank test was used to assess differences in survival between groups. The relationships between survival and several baseline and clinical variables were determined by Cox multivariate analyses. RESULTS: The median follow-up time was 40 months. The average preoperative Vo2max was 16.1 mL/kg · min and 69% of predicted value. Sixty-two (40%) patients had a Vo2max below 60%. The median and 5-year overall survivals of patients with preoperative Vo2max above 60% were significantly longer than in those with Vo2max below 60% (median not reached vs 48 months: 73% vs 40%, p=0.0004). Cox regression model showed that an age older than 70 years (p=0.005, hazard ratio 2.3) and Vo2max below 60% (p=0.001, hazard ratio 2.4) were independent prognostic factors significantly associated with overall survival. Cancer-specific survival was also longer in patients with Vo2max above 60% (81% vs 61%, p=0.01). CONCLUSIONS: Exercise tolerance may influence the physiologic outcomes associated with cancer that can potentially affect survival. Physical rehabilitation aimed at improving exercise tolerance can possibly improve the long-term prognosis after operations for lung cancer.