The economic impact of a nurse practitioner–directed lung cancer screening, incidental pulmonary nodule, and tobacco-cessation clinic

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.

Estimating revenue, costs, and operating margin of any hospital-based thoracic surgery practice using a novel financial model

OBJECTIVE

The study objective was to develop a generalizable financial model that estimates payor-specific reimbursements associated with anatomic lung resections for any hospital-based thoracic surgery practice.

METHODS

Medical records of patients who presented to the thoracic surgery clinic and eventually underwent an anatomic lung resection from January 2019 to December 2020 were reviewed. The volume of preoperative and postoperative studies, clinic visits, and outpatient referrals was measured. Neither subsequent studies nor procedures from outpatient referrals were captured. Diagnosis-related group, cost-to-charge ratios, Current Procedural Terminology Medicare payment data, and Private:Medicare and Medicaid:Medicare payment ratios were used to estimate payor-specific reimbursements and operating margin.

RESULTS

A total of 111 patients met inclusion criteria and underwent 113 operations: 102 (90%) lobectomies, 7 (6%) segmentectomies, and 4 (4%) pneumonectomies. These patients underwent 554 total studies, received 60 referrals to other specialties, and had 626 total clinic visits. The total charges and Medicare reimbursement were $12.5 M and $2.7 M, respectively. After adjusting for a 41% Medicare, 2% Medicaid, and 57% Private payor mix, the total reimbursement was $4.7 M. With a 0.252 cost-to-charge ratio, total costs and operating income were $3.2 M and $1.5 M, respectively (ie, 33% operating margin). Average reimbursement per surgery by payor was $51k for Private, $29k for Medicare, and $23k for Medicaid.

CONCLUSIONS

For any hospital-based thoracic surgery practice, this novel financial model can calculate both overall and payor-specific reimbursements, costs, and operating margin across the full perioperative spectrum. By manipulating hospital name, hospital state, volume, and payor mix, any program can gain insights into their financial contributions and use the outputs to guide investment decisions.

Lung Cancer Screening

Lung cancer is a leading cause of cancer death in the United States and globally with the majority of lung cancer cases attributable to cigarette smoking. Given the high societal and personal cost of a diagnosis of lung cancer including that most cases of lung cancer when diagnosed are found at a late stage, work over the past 40 years has aimed to detect lung cancer earlier when curative treatment is possible. Screening trials using chest radiography and sputum failed to show a reduction in lung cancer mortality however multiple studies using low dose CT have shown the ability to detect lung cancer early and a survival benefit to those screened. This review will discuss the history of lung cancer screening, current recommendations and screening guidelines, and implementation and components of a lung cancer screening program.

Status and related factors of burnout among palliative nurses in China: a cross-sectional study

Background

Burnout occurs frequently in nurses and seems more common in nurses providing palliative care. However, to our knowledge, there is a lack of understanding regarding the factors influencing burnout among palliative nurses in China.

Methods

A cross-sectional design was conducted. A total of 331 palliative nurses from 25 hospitals participated in this study. Anonymous data were collected through a self-designed social-demographic questionnaire, the Nursing Burnout Scale, the Perceived Social Support Scale, the General Self-Efficacy Scale, the Connor-Davidson Resilience Scale, and the Simplified Coping Style Questionnaire. Independent sample t tests, one-way ANOVA, Pearson correlations, and multiple linear regressions were performed to identify the related factors of the three dimensions of burnout.

Results

In the results of multiple linear regression, resilience, health condition, coping style, and pessimistic personality were common related factors; in addition, end-of-life care training, social support, and income satisfaction were statistically significantly associated with burnout. These factors could explain 38.6%, 27.8%, and 34.5% of the total variance in emotional exhaustion, depersonalization, and reduced personal accomplishment, respectively.

Conclusions

The findings of this study help policy makers and nurse managers better understand burnout among palliative nurses in China. The results highlighted the importance of implementing culture-oriented training programs, providing perceived organizational support, and building a reasonable salary system to decrease burnout among palliative nurses, increase the quality of nursing and promote the development of Chinese palliative care.

"It's Really Like Any Other Study": Rural Radiology Facilities Performing Low-Dose Computed Tomography for Lung Cancer Screening

RATIONALE

The majority of eligible people have not been screened for lung cancer. There is emerging evidence that there are location-based disparities applicable to lung cancer screening.

OBJECTIVE

Describe lung cancer screening radiologic services in rural Oregon and understand the barriers and facilitators to implementation of lung cancer screening using LDCT.

METHODS

A mixed-methods descriptive study utilizing surveys and semi-structured interviews of key informants. We approached representatives from all 37 small and rural hospitals in Oregon. We purposively interviewed key informants from a sub-set based on LDCT implementation outcomes.

RESULTS

We surveyed representatives from 29 radiology facilities and qualitatively interviewed 18 key informants from 19 facilities (representing 12 health care systems). Among the surveyed radiology facilities, 59% were performing LDCT for lung cancer screening. Key informants reported that facilities which performed this service were often motivated by community needs, less by financial gain or evidence strength and all described the importance of a champion. Key informants described that implementing lung cancer screening programmatic components that were within their normal scope of practice (e.g. specifying the LDCT parameters) were burdensome to establish but were surmountable barriers. Most informants reported they did not perform other components of high-quality programs (e.g. ensuring adherence to recommended follow-up testing) and suggested these steps were important but the responsibility of primary care providers.

CONCLUSIONS

Many rural hospital facilities in Oregon offer LDCT for lung cancer screening, but do not perform all the recommended components of a screening program. Disparities in lung cancer screening utilization and adherence are unlikely to be solved by an exclusive focus at the radiology facility level and may require additional interventions at the primary care level.

Addressing Disparities in Lung Cancer Screening Eligibility and Healthcare Access. An Official American Thoracic Society Statement

Background: There are well-documented disparities in lung cancer outcomes across populations. Lung cancer screening (LCS) has the potential to reduce lung cancer mortality, but for this benefit to be realized by all high-risk groups, there must be careful attention to ensuring equitable access to this lifesaving preventive health measure.Objectives: To outline current knowledge on disparities in eligibility criteria for, access to, and implementation of LCS, and to develop an official American Thoracic Society statement to propose strategies to optimize current screening guidelines and resource allocation for equitable LCS implementation and dissemination.Methods: A multidisciplinary panel with expertise in LCS, implementation science, primary care, pulmonology, health behavior, smoking cessation, epidemiology, and disparities research was convened. Participants reviewed available literature on historical disparities in cancer screening and emerging evidence of disparities in LCS.Results: Existing LCS guidelines do not consider racial, ethnic, socioeconomic, and sex-based differences in smoking behaviors or lung cancer risk. Multiple barriers, including access to screening and cost, further contribute to the inequities in implementation and dissemination of LCS.Conclusions: This statement identifies the impact of LCS eligibility criteria on vulnerable populations who are at increased risk of lung cancer but do not meet eligibility criteria for screening, as well as multiple barriers that contribute to disparities in LCS implementation. Strategies to improve the selection and dissemination of LCS in vulnerable groups are described.

Development and outcomes of a comprehensive multidisciplinary incidental lung nodule and lung cancer screening program

BACKGROUND

Appropriate management of lung nodules detected incidentally or through lung cancer screening can increase the rate of early-stage diagnoses and potentially improve treatment outcomes. However, the implementation and management of comprehensive lung nodule programs is challenging.

METHODS

This single-center, retrospective report describes the development and outcomes of a comprehensive lung nodule program at a community practice in Tennessee. Computed tomography (CT) scans potentially revealing incidental lung nodules were identified by a computerized search. Incidental or screening-identified lung nodules that were enlarging or not seen in prior scans were entered into a nodule database and guideline-based review determined whether to conduct a diagnostic intervention or radiologic follow-up. Referral rates, diagnosis methods, stage distribution, treatment modalities, and days to treatment are reported.

RESULTS

The number of patients with lung nodules referred to the program increased over 2 years, from 665 patients in Year 1 to 745 patients in Year 2. Most nodules were incidental (62-65%). Nodules identified with symptoms (15.2% in Year 1) or through screening (12.6% in Year 1) were less common. In Year 1, 27% (182/665) of nodules required a diagnostic intervention and 18% (121/665) were malignant. Most diagnostic interventions were image-guided bronchoscopy (88%) or percutaneous biopsy (9%). The proportion of Stage I-II cancer diagnoses increased from 23% prior to program implementation to 36% in Year 1 and 38% in Year 2. In screening cases, 71% of patients completed follow-up scans within 18 months. Only 2% of Year 1 patients under watchful waiting required a diagnostic intervention, of which 1% received a cancer diagnosis.

CONCLUSIONS

The current study reports outcomes over the first 2 years of a lung cancer screening and incidental nodule program. The results show that the program was successful, given the appropriate level of data management and oversight. Comprehensive lung nodule programs have the potential to benefit the patient, physician, and hospital system.

Patient-Centered, Guideline-Concordant Discussion and Management of Pulmonary Nodules

Providing guideline-concordant management of pulmonary nodules can present challenges when a patient's anxiety about cancer or fear of invasive procedures colors judgment. The way in which providers discuss and make decisions about how to evaluate a pulmonary nodule can affect patient satisfaction, distress, and adherence to evaluation. This article discusses the complexity of tailoring patient-provider communication, decision-making, and implementation of guidelines for pulmonary nodule evaluation to the individual patient, emphasizing the importance of how information is conveyed and the value of listening to and addressing patients' concerns. We summarize the relevant guideline recommendations and literature, and provide two case scenarios to illustrate a patient-centered approach to discussing and managing pulmonary nodules from our perspectives as a pulmonologist and thoracic surgeon.

Multidisciplinary selection of pulmonary nodules for surgical resection: Diagnostic results and long-term outcomes

OBJECTIVE

Pulmonary nodules found incidentally or by lung cancer screening differ in prevalence, risk profile, and diagnostic intervention. The results of surgical intervention for incidental versus screening lung nodules during multidisciplinary Pulmonary Nodule and Lung Cancer Screening Clinic (PNLCSC) follow-up have not been reported.

METHODS

All patients evaluated at a PNLCSC from 2012 to 2018 following referral by primary care physicians, specialist physicians, or self-referral after computed tomography (CT) identified nodules on routine diagnostic CT (incidental group) or lung cancer screening CT (screening group) were included. Follow-up interval, invasive intervention, histology, postoperative events, survival, and recurrence were compared.

RESULTS

Of 747 patients evaluated in the PNLCSC, 129 (17.2%) underwent surgical intervention. The surgical cohort consisted of 104 (80.6%) incidental and 25 (19.3%) screening patients followed over a mean of 122 and 70 days, respectively. More benign lesions were excised in the incidental group (20.2%, 21/104)-representing 3.3% (21/632) of all incidental nodules evaluated-than in the screening group (4%, 1/25) (P = .038). Operative mortality was zero. Among 99 patients with primary lung cancer, 87% (screening) and 86.8% (incidental) were pathologic stage Ia. Complete follow-up was available in 725 of 747 (97%), and no patient developed progressive disease. Disease-free survival at 5 years was 74.9% (incidental) and 89.3% (screening) (P = .48).

CONCLUSIONS

A unique multidisciplinary PNLCSC for incidental and lung cancer screening-detected nodules with individualized risk assessment reliably identifies primary and metastatic tumors while exposing few patients to diagnostic excision for benign disease. Longer-term outcomes, strategies to limit radiation exposure, and cost control need further study.

The decision to biopsy in a lung cancer screening program: Potential impact of risk calculators

OBJECTIVE

The National Lung Screening Trial demonstrated the benefits of lung cancer screening, but the potential high incidence of unnecessary invasive testing for ultimately benign radiologic findings causes concern. We aimed to review current biopsy patterns and outcomes in our community-based program, and retrospectively apply malignancy prediction models in a lung cancer screening population, to identify the potential impact these calculators could have on biopsy decisions.

METHODS

Retrospective review of lung cancer-screening program participants from 2013 to 2016. Demographic, biopsy, and outcome data were collected. Malignancy risk calculators were retrospectively applied and results compared in patients with positive imaging findings.

RESULTS

From 520 individuals enrolled in the screening program, pulmonary nodule(s) ≥6 mm were identified in 166, with biopsy in 30. Malignancy risk probabilities were significantly higher (Brock p < 0.00001; Mayo p < 0.00001) in those undergoing diagnostic sampling than those not undergoing sampling. However, there was no difference in the Brock ( p = 0.912) or Mayo ( p = 0.435) calculators when discriminating a final diagnosis of cancer from not cancer in those undergoing sampling.

CONCLUSIONS

In our screening program, 5.7% of individuals undergo invasive testing, comparable with the National Lung Screening Trial (6.1%). Both Brock and Mayo calculators perform well in indicating who may be at risk of malignancy, based on clinical and radiologic factors. However, in our invasive testing group, the Brock and Mayo calculators and Lung Cancer Screening Program clinical assessment all lacked clarity in distinguishing individuals who have a cancer from those with a benign abnormality.

Clinical Databases for Chest Physicians

A clinical database is a repository of patient medical and sociodemographic information focused on one or more specific health condition or exposure. Although clinical databases may be used for research purposes, their primary goal is to collect and track patient data for quality improvement, quality assurance, and/or actual clinical management. This article aims to provide an introduction and practical advice on the development of small-scale clinical databases for chest physicians and practice groups. Through example projects, we discuss the pros and cons of available technical platforms, including Microsoft Excel and Access, relational database management systems such as Oracle and PostgreSQL, and Research Electronic Data Capture. We consider approaches to deciding the base unit of data collection, creating consensus around variable definitions, and structuring routine clinical care to complement database aims. We conclude with an overview of regulatory and security considerations for clinical databases.