Explore the vast range of titles available.

Machine learning (ML) holds great promise for impacting healthcare delivery; however, to date most methods are tested in ‘simulated’ environments that cannot recapitulate factors influencing real-world clinical practice. We prospectively deployed and evaluated a random forest algorithm for therapeutic curative-intent radiation therapy (RT) treatment planning for prostate cancer in a blinded, head-to-head study with full integration into the clinical workflow. ML- and human-generated RT treatment plans were directly compared in a retrospective simulation with retesting ( n  = 50) and a prospective clinical deployment ( n  = 50) phase. Consistently throughout the study phases, treating physicians assessed ML- and human-generated RT treatment plans in a blinded manner following a priori defined standardized criteria and peer review processes, with the selected RT plan in the prospective phase delivered for patient treatment. Overall, 89% of ML-generated RT plans were considered clinically acceptable and 72% were selected over human-generated RT plans in head-to-head comparisons. RT planning using ML reduced the median time required for the entire RT planning process by 60.1% (118 to 47 h). While ML RT plan acceptability remained stable between the simulation and deployment phases (92 versus 86%), the number of ML RT plans selected for treatment was significantly reduced (83 versus 61%, respectively). These findings highlight that retrospective or simulated evaluation of ML methods, even under expert blinded review, may not be representative of algorithm acceptance in a real-world clinical setting when patient care is at stake. An artificial intelligence system prospectively deployed to design radiation therapy plans for patients with prostate cancer illustrates the real-world impact of machine learning in clinical practice and identifies factors influencing human–algorithm interaction

We sought to quantify contribution of radiomics and SUVmax at PET/CT to predict clinical outcome in lung cancer patients treated with stereotactic body radiotherapy (SBRT). 150 patients with 172 lung cancers, who underwent SBRT were retrospectively included. Radiomics were applied on PET/CT. Principal components (PC) for 42 CT and PET-derived features were examined to determine which ones accounted for most of variability. Survival analysis quantified ability of radiomics and SUVmax to predict outcome. PCs including homogeneity, size, maximum intensity, mean and median gray level, standard deviation, entropy, kurtosis, skewness, morphology and asymmetry were included in prediction models for regional control (RC) [PC4-HR:0.38, p = 0.02], distant control (DC) [PC4-HR:0.51, p = 0.02 and PC1-HR:1.12, p = 0.01], recurrence free probability (RFP) [PC1-HR:1.08, p = 0.04], disease specific survival (DSS) [PC2-HR:1.34, p = 0.03 and PC3-HR:0.64, p = 0.02] and overall survival (OS) [PC4-HR:0.45, p = 0.004 and PC3-HR:0.74, p = 0.02]. In combined analysis with SUVmax, PC1 lost predictive ability over SUVmax for RFP [HR:1.1, p = 0.04] and DC [HR:1.13, p = 0.002], while PC4 remained predictive of DC independent of SUVmax [HR:0.5, p = 0.02]. Radiomics remained the only predictors of OS, DSS and RC. Neither SUVmax nor radiomics predicted recurrence free survival. Radiomics on PET/CT provided complementary information for prediction of control and survival in SBRT-treated lung cancer patients.

Randomised controlled trials comparing surgery with non-surgical treatment for cancer have been notoriously difficult to complete, owing to challenges in both equipoise and preference in patients and providers alike.1 Debate on the relative merit of stereotactic ablative radiotherapy (SABR) versus surgery for early-stage non-small-cell lung cancer (NSCLC) is no exception. Prospective randomised controlled trials designed to identify a so-called winner between surgery and SABR have not been able to accrue, and the pooled analysis from the prematurely closed original STARS and ROSEL studies has been a lightning rod for discussion among thoracic oncologists.2 Even with other comparative effectiveness studies attempting to adjust for confounding, inherent limitations engender polarising opinions.3 In The Lancet Oncology, Joe Chang and colleagues present the results of the new revised STARS cohort of an additional 80 patients with medically operable early-stage NSCLC treated with SABR.4 The authors should be congratulated on the robust study conduct. Ultra-central tumours were not included; both lobectomy and SABR are challenging in this cohort and further comparative data are required.9 Furthermore, biomarker data were not available in STARS, and have implications for both prognostication and salvage therapies.10 Until randomised controlled trials are completed, for younger, fitter patients presenting with stage IA NSCLC, it seems that there are two outstanding treatment options available for long-term survival.

To the Editor: Both intravenous antibody–drug conjugates and oral tyrosine kinase inhibitors targeting receptor tyrosine-protein kinase erbB-2 (ERBB2 or HER2) are under late-stage development for lung cancers with ERBB2 mutations. Li et al. (Jan. 20 issue) 1 report the initial data from the DESTINY-Lung01 trial of trastuzumab deruxtecan, including for 9 patients with a response who had previously received an ERBB2 tyrosine kinase inhibitor. However, the specific tyrosine kinase inhibitor was not provided. The majority of clinically available ERBB2 tyrosine kinase inhibitors (afatinib, dacomitinib, lapatinib, and neratinib) do not have an effective therapeutic window against either common ERBB2 exon 20 insertion . . .

Purpose Patients with lung cancer can experience significant psychological morbidities including depression. We characterize patterns and factors associated with interventions for symptoms of depression in stage IV non-small cell lung cancer (NSCLC). Methods We conducted a population-based cohort study using health services administrative data in Ontario, Canada of stage IV NSCLC diagnosed from January 2007 to September 2018. A positive symptom of depression score was defined by reporting at least one ESAS (Edmonton Symptom Assessment System) depression score ≥ 2 following diagnosis until the end of follow-up (September 2019). Patient factors included age, sex, comorbidity burden, rurality of residence, and neighbourhood income quintile. Interventions included psychiatry assessment, psychology referral, social work referral and anti-depressant medical therapy (for patients ≥ 65 years with universal drug coverage). Multivariable modified Poisson regression models were used to examine the association between patient factors and intervention use for patients who reported symptoms of depression. Results In the cohort of 13,159 patients with stage IV NSCLC lung cancer, symptoms of depression were prevalent (71.4%, n  = 9,397). Patients who reported symptoms of depression were more likely to receive psychiatry assessment/psychology referral (7.8% vs 3.5%; SD [standardized difference] 0.19), social work referral (17.4% vs 11.9%; SD 0.16) and anti-depressant prescriptions (23.8% vs 13.8%; SD 0.26) when compared to patients who did not report symptoms of depression respectively. In multivariable analyses, older patients were less likely to receive any intervention. Females were more likely to obtain a psychiatry assessment/psychology referral or social work referral. In addition, patients from non-major urban or rural residences were less likely to receive psychiatry assessment/psychology referral or social work referral, however patients from rural residences were more likely to be prescribed anti-depressants. Conclusions There is high prevalence of symptoms of depression in stage IV NSCLC. We identify patient populations, including older patients and rural patients, who are less likely to receive interventions that will help identifying and screening for symptoms of depression.

BackgroundTo investigate the relationship between attendance to a pre-treatment psychoeducational intervention (prehab) with treatment outcomes and toxicities in patients receiving radiotherapy for head and neck cancers (HNCs).MethodsPatients were included from prehab inception in 2013 to 2017, comparing overall survival (OS), locoregional recurrence-free survival (LRFS), and locoregional recurrence (LRR) between prehab attendees (PA) and non-attendees (PNA). Multivariable analysis was performed for OS and LRFS.ResultsAmong 864 PA and 1128 PNA, 2-year OS was 88% vs 80% (p < 0.001), and LRFS was 84% vs 75% (p < 0.001). On multivariable analysis (MVA), OS and LRFS were independently and unfavourably associated with PNA. The PA cohort had a lower frequency of a “rocky treatment course” compared with the PNA cohort (52/150, 35% vs 71/150, 47%; p = 0.034).ConclusionsPrehab at our institution is associated with improved long-term oncologic outcomes. Prospective data is needed to better understand this association.

We explored perspectives of patients with metastatic non-small cell lung cancer (mNSCLC) on symptom screening and population-level patient-reported outcome (PRO) data regarding common symptom trajectories in the year after diagnosis. A qualitative study of patients with mNSCLC was conducted at a Canadian tertiary cancer centre. English-speaking patients diagnosed ≥ 6 months prior to study invitation were recruited, and semi-structured one-on-one interviews were conducted. Patient and treatment characteristics were obtained via chart review. Anonymized interview transcripts underwent deductive-inductive coding and thematic content analysis. Among ten participants (5 (50%) females; median (range) age, 68 (56–77) years; median (range) time since diagnosis, 28.5 (6–72) months; 6 (60%) with smoking histories), six themes were identified in total. Two themes were identified regarding symptom screening: (1) screening is useful for symptom self-monitoring and disclosure to the healthcare team, (2) screening of additional quality-of-life (QOL) domains (smoking-related stigma, sexual dysfunction, and financial toxicity) is desired. Four themes were identified regarding population-level symptom trajectory PRO data: (1) data provide reassurance and motivation to engage in symptom self-management, (2) data should be disclosed after an oncologic treatment plan is developed, (3) data should be communicated via in-person discussion with accompanying patient-education resources, and (4) communication of data should include reassurance about symptom stabilization, acknowledgement of variability in patient experience, and strategies for symptom self-management. The themes and recommendations derived from the patient experience with mNSCLC provide guidance for enhanced symptom screening and utilization of population-level symptom trajectory data for patient education.

This study explored older women’s perceptions and expectations of the prospective Senior Women’s Breast Cancer Clinic (SWBCC) at Sunnybrook Odette Cancer Centre (SOCC) in Toronto, Ontario, Canada. In our previous studies, older breast cancer patients had expressed a greater need for informational, decisional, and post-treatment support. This study also assessed women’s perspectives on the involvement of geriatricians and incorporation of geriatric assessment in their cancer care. Twelve breast cancer patients aged 68 years or older who were treated at the SOCC participated in the study. We recorded and transcribed 11 interviews and analyzed them using qualitative thematic analysis methods to identify major themes; one interview was excluded due to recording defect. Eight major themes were identified: transportation issues, service, communication between patient and healthcare professionals, communication between healthcare professionals, support during treatment, support after treatment, informational resources, and patient suggestions. Important issues were raised by participants, such as difficulties in arranging transportation to the clinic, barriers in accessing family physician service, and communication breakdown that result in treatment delay and unaddressed complications. In conclusion, there were important gaps in the cancer care of older women with breast cancer that could be detected earlier and better addressed in the new multidisciplinary SWBCC. The participating women were highly supportive of the initiative and made several suggestions on how the clinic could better accommodate their specific needs during and after breast cancer treatment.

Lung cancer is still the leading cause of cancer mortality worldwide. Most patients with lung cancer such as non-small cell lung cancer (NSCLC) present with advanced stage of the disease. Patients with metastatic NSCLC experience a higher degree of distressing pain and symptoms compared to other types of cancer. Distressing pain is associated with lower quality of life (QoL), depression, and worse health status due to pain fatigue. A randomized trial by Temel et al in 2010 demonstrated that early palliative care, which focuses on alleviating distressing symptoms and pain, leads to a better QoL, depression status, and overall survival compared to standard treatment. As the lung palliative patients in this cohort were interviewed in focus group setting, patients emphasized symptoms and pain management as an important objective to improve patient functional status. In addition, excellent symptoms and pain control builds trust and good rapport with the patients, which in turn helps them to disclose other health issues that may arise during the palliative care.