Artificial Intelligence: Can It Save Lives, Hospitals, and Lung Screening?

BACKGROUND: Early detection is essential in lung cancer survival. Lung screening or incidental detection on unrelated imaging holds the most promise for early detection. With the large volume of imaging performed today, management of incidental pulmonary nodules can be difficult. We hypothesized an artificial intelligence (AI) tool could reliably read all imaging reports, detect, and effectively triage indeterminate pulmonary nodules without adding additional personnel, helping save lives. METHODS: An incidental lung nodule clinic (ILNC) was created using AI and an existing nurse practitioner. Over 26 months, the software read all radiology reports, visualizing any lung tissue. Patients with nodules >3 mm and considered indeterminate by the nurse practitioner were referred to the ILNC. High-risk patients with benign nodules were offered entry into the lung screening program. RESULTS: Of 502,632 imaging reports analyzed, 22,136 (4.4%) had positive findings. Follow-up data were lacking in 11,797 (2.3%), 911 (7.7%) were verified lost, and 518 (4.4%) were referred to the ILNC. There were 393 patients with benign nodules and accepted enrollment in the lung screening program. Mean age of enrolled patients was 61 years, and 53% were men. Workup included 499 diagnostic computed tomographic scans, 39 positron emission tomographic scans, and 27 biopsy samples that identified 15 malignancies (2.9%), with 14 lung cancers (8 stage I, 4 stage III, and 2 stage IV). Treatment included 5 lobectomies, and 4 underwent stereotactic body radiation therapy. Financials were favorable. CONCLUSIONS: AI software can supplement practitioners, help diagnose lung cancer earlier, save lives, and generate value-based revenue for the hospital.

Mobile Lung Screening: Should We All Get on the Bus?

BACKGROUND: Despite favorable recommendations, national lung screening adoption remains low (2% to 3%). Patients living in rural areas have additional challenges, including access to lung screening programs. We initiated a mobile lung screening program to serve the rural patients at risk. This is what we learned from this 12-month feasibility project. METHODS: Utilizing a multidisciplinary approach, we began an 8-month design and build schedule. This was the first build of this type. The operational team included a radiology technician, nurse practitioner, driver with a commercial driver's license, and program developer. Specialized software was used for data mining. Downstream revenue projections were based on previously published Medicare claims data. Generally accepted accounting principles were used. RESULTS: The prototype bus was delivered January 2018. During the 12-month feasibility period, we performed 548 low-dose lung screenings at 104 sites. Mean patient age was 62 years, mean pack-years of smoking was 41; 258 (47%) were male. Five lung cancers were found in addition to a type B thymoma. Financially, we exceeded the break-even analysis by 28%. The 5-year pro forma using 1 year of actual data and 4 additional years of projected data demonstrated a net present value of 1 million, internal rate of return of 34.6%, and profitability index of 2.2-all highly dependent on downstream revenue. CONCLUSIONS: Although challenges exist, a commercially viable bus and a financially sound mobile program can be developed. However, without a centralized approach for incidental findings, the downstream revenue may be at risk as well as the financial viability of the project.

Safety of Next Day Discharge After Lobectomy: Have We Broken the Speed Limit?

BACKGROUND: Utilizing our standardized approach to air leak reduction (STAR) protocol has led to a continual decrease in the need for inpatient recovery after lobectomy. Although next-day discharges do occur, the current literature, to our knowledge, has not addressed their safety. We analyzed our STAR data set to study this group and their outcomes. METHODS: A retrospective review of prospectively collected data from the STAR data set was performed. Characteristics were compared between patients discharged on postoperative day (POD) 1 and those with longer admissions. Outcome data was analyzed. RESULTS: From June 2010 through June 2017, 390 patients underwent lobectomy and met study criteria. Of these, 150 (38%) were discharged on POD 1 versus 240 (62%) who were discharged later (mean length of stay, 3.9 days). There was no increase in morbidity, mortality, or 30-day readmission between the 2 groups. Distinguishing characteristics of the POD 1 group included more nonsmokers, use of a minimally invasive technique, and a lower incidence of prolonged air leak. FEV1 (forced expiratory volume in 1 second) and Dlco (diffusing capacity of the lung for carbon monoxide) data were also favorable in the POD 1 group. The percentage of patients sent home POD 1 increased from an average of 23% over the first 3 years of the study to 63% over the last 3 years. CONCLUSIONS: Appropriately identified patients can safely go home on POD 1 after lobectomy without an increase in 30-day readmission, morbidity, or mortality. A continued focus on lobectomy length of stay reduction has the capacity to increase patient satisfaction and lead to reduction in health care costs.

Intrabronchial Pneumonectomy for Vanishing Lung Syndrome: First Reported Case.

Vanishing lung syndrome is a clinical presentation of giant bullous emphysema associated with significant morbidity and mortality. We present a case of a 50-year-old white woman with vanishing lung syndrome who presented with a spontaneous secondary pneumothorax and an uncontrolled bronchopleural fistula. The large bronchopleural fistula was initially controlled with a double-lumen endotracheal tube and a tube thoracostomy. After surgical efforts failed, complete left lung isolation was performed with multiple intrabronchial valves. In essence, a medical pneumonectomy was performed. The patient was weaned from mechanical ventilation and discharged to rehabilitation. She was ambulatory at 5-month follow-up.

Traumatic Rupture of A Posterior Mediastinal Teratoma following Motor-Vehicle Accident.

We report a case of a posterior mediastinal mature cystic teratoma with rupture secondary to blunt chest trauma in a 20-year-old male involved in a motor-vehicle accident. Initial treatment was guided by Advanced Trauma Life Support and a tube thoracostomy was performed for presumed hemothorax. The heterogeneous collection within the thoracic cavity was discovered to be the result of a ruptured cystic mass. Pathologic findings confirmed the mass consistent with a mature cystic teratoma. As mediastinal teratomas are most commonly described arising from the anterior mediastinum, the posterior location of the teratoma described in this report is exceedingly rare.

Standardized Approach to Prolonged Air Leak Reduction After Pulmonary Resection.

BACKGROUND: Prolonged air leaks after pulmonary resection lead to patient discomfort, increased hospital length of stay, greater health care costs, and increased morbidity. A standardized approach to air leak reduction (STAR) after lung resection was developed and studied. METHODS: A retrospective review was conducted of a prospective database from 1 surgeon who had adopted STAR as standard of care. Three independent factors shown to reduce air leaks are incorporated in STAR: fissureless operative technique, staple line buttressing, and protocol-driven chest tube management. Patient characteristics and outcomes were compared against aggregate data from The Society of Thoracic Surgeons National Database (2012-2014). RESULTS: From June 2010 through May 2015, 475 patients met the study criteria. Of these, 264 (55.6%) had lobectomies, 198 (41.7%) had wedge resections, and 13 (2.7%) had segmentectomies. Prolonged air leaks were reduced in the STAR lobectomy group by 52% (5.7% versus 10.9%; p = 0.0079) and in the STAR wedge group by 40% (2.5% versus 4.2%; p = 0.38). Hospital length of stay for lobectomies (3.2 versus 6.3 days; p = 0.0001), wedge resections (3.3 versus 4.5 days; p = 0.0152), and segmentectomies (3.2 versus 5.2 days; p = 0.0001) was significantly reduced. Readmission rate was 4% and none were related to air leak. No difference was seen in mortality rates. CONCLUSIONS: Use of STAR for pulmonary resection, particularly for lobectomies, shows decreased postoperative prolonged air leaks when compared with The Society of Thoracic Surgeons National Database. This aggressive approach did not lead to air leak-related hospital readmissions nor compromise postoperative mortality. The STAR protocol is an innovative strategy that has the potential to improve postoperative pulmonary resection outcomes.

Safety of Outpatient Chest Tube Management of Air Leaks After Pulmonary Resection.

Prolonged air leaks are the most common postoperative complication following pulmonary resection, leading to increased hospital length of stay (LOS) and cost. This study assesses the safety of discharging patients home with a chest tube (CT) after pulmonary resection. A retrospective review was performed of a single surgeon's experience with pulmonary resections from January 2010 to January 2015. All patients discharged home with a CT were included. Discharge criteria included a persistent air leak controlled by water seal, resolution of medical conditions requiring hospitalization, and pain managed by oral analgesics. Patient demographics, type of resection, LOS, and 30-day morbidity and mortality data were analyzed. Comparisons were made with the Society of Thoracic Surgery database January 2011 to December 2013. Four hundred ninety-six patients underwent pulmonary resection. Sixty-five patients (13%) were discharged home postoperatively with a CT. Fifty-eight patients underwent a lobectomy, two patients a bilobectomy, and five patients had a wedge excision. Two patients were readmitted: One with a lower extremity deep venous thrombosis and the other with a nonlife threatening pulmonary embolus. Four patients developed superficial CT site infections that resolved after oral antibiotics. Patients discharged home with a CT following lobectomy had a shorter mean LOS compared to lobectomy patients (3.65 vs 6.2 days). Mean time to CT removal after discharge was 4.7 days (range 1-22 days) potentially saving 305 inpatient hospital days. Select patients can be discharged home with a CT with reduced postoperative LOS and without increase in major morbidity or mortality.

High-grade esophageal dysplasia: long-term survival and quality of life after esophagectomy.

BACKGROUND: Esophagectomy for high-grade dysplasia in Barrett's esophagus has been advocated. Although long-term survival data exist, little is known about functional outcome and quality of life in this particular subset of patients. METHODS: The records of all patients who underwent esophageal resection for high-grade dysplasia from June 1991 through July 1997 were reviewed. Long-term functional outcome and quality of life were assessed using a two-part written survey. RESULTS: There were 54 patients (48 men, 6 women). Median age was 64 years (range, 36 to 83 years). Ivor Lewis esophagogastrectomy was performed in 34 patients (63%), transhiatal esophagectomy in 10 (18%), extended esophagectomy in 8 (15%), and other in 2 (4%). Invasive carcinoma was found in 19 patients (35%). Five patients (9%) were stage 0, 7 (13%) stage I, 3 (6%) stage IIA, 1 (2%) stage IIB, and 3 patients (6%) stage III. There was one operative death (1.8%). Complications occurred in 31 patients (57%). Median hospitalization was 13 days (range, 11 to 44 days). Follow-up was complete in all patients and ranged from 6 months to 9 years (median, 63 months). Overall 5-year survival was 86% and did not differ significantly from a population matched for age and gender. Five-year survival for patients with only high-grade dysplasia was 96% and 68% for patients with cancer (p = 0.017). Quality of life was measured by the Medical Outcomes Study 36-Item Short-Form Health Survey. For patients with only high-grade dysplasia, the role-physical and role-emotional scores were better than for the control population (p < 0.03). For patients with cancer, the health perception score was worse than for the control population (p < 0.03). Scores measuring physical-function, social function, mental health, bodily pain, and energy/fatigue were similar. CONCLUSIONS: Although perioperative morbidity is significant, surgical resection of high-grade dysplasia in Barrett's esophagus provides excellent long-term survival with acceptable function and quality of life.