Predicting which patients with cancer will see a psychiatrist or counsellor from their initial oncology consultation document using natural language processing.

BACKGROUND: Patients with cancer often have unmet psychosocial needs. Early detection of who requires referral to a counsellor or psychiatrist may improve their care. This work used natural language processing to predict which patients will see a counsellor or psychiatrist from a patient's initial oncology consultation document. We believe this is the first use of artificial intelligence to predict psychiatric outcomes from non-psychiatric medical documents. METHODS: This retrospective prognostic study used data from 47,625 patients at BC Cancer. We analyzed initial oncology consultation documents using traditional and neural language models to predict whether patients would see a counsellor or psychiatrist in the 12 months following their initial oncology consultation. RESULTS: Here, we show our best models achieved a balanced accuracy (receiver-operating-characteristic area-under-curve) of 73.1% (0.824) for predicting seeing a psychiatrist, and 71.0% (0.784) for seeing a counsellor. Different words and phrases are important for predicting each outcome. CONCLUSION: These results suggest natural language processing can be used to predict psychosocial needs of patients with cancer from their initial oncology consultation document. Future research could extend this work to predict the psychosocial needs of medical patients in other settings.

Patients with cancer often need support for their mental health. Early detection of who requires referral to a counsellor or psychiatrist may improve their care. This study trained a type of artificial intelligence (AI) called natural language processing to read the consultation report an oncologist writes after they first see a patient to predict which patients will see a counsellor or psychiatrist. The AI predicted this with performance similar to other uses of AI in mental health, and used different words and phrases to predict who would see a psychiatrist compared to seeing a counsellor. We believe this is the first use of AI to predict mental health outcomes from medical documents written by clinicians outside of mental health. This study suggests this type of AI can predict the mental health needs of patients with cancer from this widely-available document.

Cancer type and histology influence cutaneous immunotherapy toxicities: a multi-institutional cohort study.

BACKGROUND: Cutaneous immune-related adverse events (cirAEs) are the most common toxicities to occur in the setting of immune checkpoint inhibitor (ICI) therapy. Identifying patients who are at increased risk of developing cirAEs may improve quality of life and outcomes. OBJECTIVES: To investigate the influence of cancer type and histology on the development of cirAEs in the setting of ICI therapy and survival outcomes. METHODS: This retrospective cohort study included patients recruited between 1 December 2011 and 30 October 2020. They received ICI from 2011 to 2020 with follow-up of outcomes through October 2021. We identified 3668 recipients of ICI therapy who were seen at Massachusetts General Brigham and Dana-Farber. Of these, 669 developed cirAEs. Records that were incomplete or categories of insufficient sample size were excluded from the study cohort. Multivariate Cox proportional hazards models were used to investigate the impact of cancer organ system and histology on cirAE development, after adjusting for demographics, Charlson Comorbidity Index, ICI type, cancer stage at ICI initiation, and year of ICI initiation. Time-varying Cox proportional hazards modelling was used to examine the impact of cirAE development on mortality. RESULTS: Compared with other nonepithelial cancers (neuroendocrine, leukaemia, lymphoma, myeloma, sarcoma and central nervous system malignancies), cutaneous squamous cell carcinoma [cSCC; hazard ratio (HR) 3.57, P < 0.001], melanoma (HR 2.09, P < 0.001), head and neck adenocarcinoma (HR 2.13, P = 0.009), genitourinary transitional cell carcinoma (HR 2.15, P < 0.001) and genitourinary adenocarcinoma (HR 1.53, P = 0.037) were at significantly higher risk of cirAEs in multivariate analyses. The increased risk of cirAEs translated into an adjusted survival benefit for melanoma (HR 0.37, P < 0.001) and cSCC (HR 0.51, P = 0.011). CONCLUSIONS: The highest rate of cirAEs and subsequent survival benefits were observed in cutaneous malignancies treated with ICI therapies. This study improves our understanding of patients who are at highest risk of developing cirAEs and would, therefore, benefit from appropriate counselling and closer monitoring by their oncologists and dermatologists throughout their ICI therapy. Limitations include its retrospective nature and cohort from one geography.

Cutaneous immune-related adverse events (cirAEs) are the most common complications to occur for oncology patients treated with immune checkpoint inhibitors (ICIs). cirAEs can lead to increased use of healthcare resources and significant morbidity. Identifying patients who are at increased risk of developing cirAEs may improve quality of life and outcomes. In this study, we aimed to investigate the influence of cancer organ system and histology on the development of cirAEs and survival outcomes. To do this, we included a cohort of patients retrospectively between 1 December 2011 and 30 October 2020. We identified 3668 ICI recipients who were seen at Massachusetts General Brigham and Dana-Farber in Boston, Massachusetts. Of these, 669 people developed cirAEs. Multivariate Cox proportional hazards models were used to investigate the impact of cancer organ system and histology on cirAE development, after adjusting for demographics, Charlson Comorbidity Index, ICI type, cancer stage at ICI start, and year of ICI initiation. Time-varying Cox proportional hazards modelling was used to examine the impact of cirAE development on mortality. We found that, compared with other nonepithelial cancers, patients with cutaneous squamous cell carcinoma (cSCC) and melanoma were at significantly higher risk of cirAEs. The increased risk of cirAEs translated into an adjusted survival benefit for melanoma and cSCC. This study improves our understanding of patients who are at highest risk of developing cirAEs ­ those with melanoma and cSCC. Therefore, many patients could benefit from appropriate counselling and close monitoring by their oncologists and dermatologists throughout ICI therapy.

Caring for older adults with cancer in Canada: Views from healthcare providers and cancer care allies in the community.

BACKGROUND: Cancer is common and disproportionately impacts older adults. Moreover, cancer care of older adults is complex, and the current Canadian cancer care system struggles to address all of the dimensions. In this project, our goal was to understand the barriers and facilitators to caring for older adults with cancer from perspectives of healthcare professionals and cancer care allies, which included community groups, seniors' centers, and other community-based supports. METHODS: In collaboration with a patient advisory board, we conducted focus groups and interviews with multiple local healthcare professionals and cancer care allies in British Columbia, Canada. We used a descriptive qualitative approach and conducted a thematic analysis using NVivo software. RESULTS: A total of 71 participants of various disciplines and cancer care allies participated. They identified both individual and system-level barriers. Priority system-level barriers for older adults included space and staffing constraints and disconnections within healthcare systems, and between healthcare practitioners and cancer care allies. Individual-level barriers relate to the complex health states of older adults, caregiver/support person needs, and the needs of an increasingly diverse population where English may not be a first or preferable language. CONCLUSIONS: This study identified key barriers and facilitators that demonstrate aligned priorities among a diverse group of healthcare practitioners and cancer care allies. In conjunction with perspectives from patients and caregivers, these findings will inform future improvements in cancer care. Namely, we emphasize the importance of connections among health systems and community networks, given the outpatient nature of cancer care and the needs of older adults.

Reverse Lid Swinging Approach: A Case Series.

In this report, the authors describe the reverse lid swinging approach, which comprises lateral canthotomy, superior lateral cantholysis to free the upper eyelid, and an incision at the superonasal conjunctival fornix for orbital exposure. Four patients underwent orbitotomy using the reverse lid swinging approach for orbital tumor removal (n = 3) or orbital abscess drainage (n = 1). All 4 operations were uneventful, with no optic nerve dysfunction or extraocular dysmotility over the follow-up period. Satisfactory cosmesis was achieved with no visible external scar in all cases. The reverse lid swinging approach provides easy access to medial orbital lesions as demonstrated in the present case series.

Development and validation of time-to-event models to predict metastatic recurrence of localized cutaneous melanoma.

BACKGROUND: The recent expansion of immunotherapy for stage IIB/IIC melanoma highlights a growing clinical need to identify patients at high risk of metastatic recurrence and, therefore, most likely to benefit from this therapeutic modality. OBJECTIVE: To develop time-to-event risk prediction models for melanoma metastatic recurrence. METHODS: Patients diagnosed with stage I/II primary cutaneous melanoma between 2000 and 2020 at Mass General Brigham and Dana-Farber Cancer Institute were included. Melanoma recurrence date and type were determined by chart review. Thirty clinicopathologic factors were extracted from electronic health records. Three types of time-to-event machine-learning models were evaluated internally and externally in the distant versus locoregional/nonrecurrence prediction. RESULTS: This study included 954 melanomas (155 distant, 163 locoregional, and 636 1:2 matched nonrecurrences). Distant recurrences were associated with worse survival compared to locoregional/nonrecurrences (HR: 6.21, P < .001) and to locoregional recurrences only (HR: 5.79, P < .001). The Gradient Boosting Survival model achieved the best performance (concordance index: 0.816; time-dependent AUC: 0.842; Brier score: 0.103) in the external validation. LIMITATIONS: Retrospective nature and cohort from one geography. CONCLUSIONS: These results suggest that time-to-event machine-learning models can reliably predict the metastatic recurrence from localized melanoma and help identify high-risk patients who are most likely to benefit from immunotherapy.

Beyond PACIFIC: Real-World Outcomes of Adjuvant Durvalumab According to Treatment Received and PD-L1 Expression.

Adjuvant durvalumab after chemoradiotherapy (CRT) is the standard of care for unresectable stage III non-small cell lung cancer (NSCLC). A post hoc exploratory analysis of PACIFIC revealed no OS benefit in the PD-L1 < 1% subgroup. This retrospective analysis assesses the real-world impact of durvalumab on OS according to PD-L1 tumor proportion score (TPS). Patients with stage III, unresectable NSCLC treated by CRT, with available PD-L1 TPS, from 1 March 2018 to 31 December 2020, at BC Cancer, British Columbia, Canada were included. Patients were divided into two groups, CRT + durvalumab and CRT alone. OS and PFS were analyzed in the PD-L1 ≥ 1% and <1% subgroups. A total of 134 patients were included in the CRT + durvalumab group and 117, in the CRT alone group. Median OS was 35.9 months in the CRT + durvalumab group and 27.4 months in the CRT alone group [HR 0.59 (95% CI 0.42-0.83), p = 0.003]. Durvalumab improved OS in the PD-L1 ≥ 1% [HR 0.53 (95% CI 0.34-0.81), p = 0.003, n = 175], but not in the <1% subgroup [HR 0.79 (95% CI 0.44-1.42), p = 0.4, n = 76]. This retrospective study demonstrates a statistically significant improvement in OS associated with durvalumab after CRT in PD-L1 ≥ 1%, but not PD-L1 < 1% NSCLC. Variables not accounted for may have biased the survival analysis. A prospective study would bring more insight.

Cancer treatment-related decision-making among culturally and linguistically diverse older adults with cancer: A scoping review by the International Society of Geriatric Oncology Nursing and Allied Health Interest Group.

INTRODUCTION: Countries with large economies are observing a growing number of culturally and linguistically diverse (CALD) older adults, many of whom will be affected by cancer. Little is known about the experiences and factors that influence cancer treatment decision-making in this population. The purposes of this scoping review are: (1) to summarize the published literature on cancer treatment-related decision-making with this population; and (2) to identify potential differences in how cancer treatment decisions are made compared to non-CALD older adults with cancer. MATERIALS AND METHODS: We conducted a scoping review following Arksey and O'Malley and Levac methods, Preferred Reporting Items for Systematic Reviews and Meta-Analyses Scoping Review Guidelines. We conducted a comprehensive multidatabase search, screening 1,139 titles/abstracts. Following data abstraction, we analyzed the data using tabular and narrative summary. RESULTS: We extracted data from six studies that met the inclusion criteria: four quantitative and two qualitative; five from the United States and one from Canada. Three themes were identified: (1) barriers to decision-making, (2) the influence of family and friends on decisionmaking, and (3) differences in uptake and types of treatment received between CALD and non-CALD older adults. DISCUSSION: This comprehensive review of treatment decision-making among CALD older adults with cancer highlights the paucity of research in this area. The findings are limited to North American populations and may not represent experiences in other regions of the world. Future research should focus on studying their treatment-related decision-making experiences to improve the quality of care for this vulnerable population.

Evaluating the childcare needs of cancer patients undergoing radiation therapy.

PURPOSE: About one-fifth of newly diagnosed cancer patients are parents to young children. These patients are at higher risk of psychosocial stress and inability to attend treatment due to having to balance their own healthcare needs with childcare duties. This study aims to explore the impact of childcare on cancer parents and elicit their perspectives on potential supports. The results could help inform the implementation of suitable childcare programs to remove this barrier in accessing care. METHODS: Patients at a large Canadian cancer treatment center were screened by oncologists for having minor children at home. Secure electronic surveys were then distributed to consenting participants. Domains surveyed included patient demographics, childcare burden, impact on treatment, and preference for childcare supports. RESULTS: The mean age of correspondents was 43.9 (range 33-54), 46 patients (92%) were female, and breast cancer was the most common primary tumor. The median number of children per correspondent was two, and their mean age was 8.4. Balancing childcare with cancer treatment had a significant impact on self-reported stress levels for most correspondents. Twenty (40%) participants had to reschedule and 7 (14%) participants missed at least one appointment due to childcare conflicts. During the COVID-19 pandemic, access to childcare resources decreased while childcare responsibilities increased. Three-quarters of correspondents reported that a flexible childcare would make it easier for them to adhere to appointment schedules. CONCLUSION: Childcare is a significant psychosocial barrier for patients accessing cancer care. Our results indicate that most parents undergoing treatment may benefit from hospital-based childcare services.

Real-World Outcomes of Stage IV NSCLC with PD-L1 ≥ 50% Treated with First-Line Pembrolizumab: Uptake of Second-Line Systemic Therapy.

INTRODUCTION: Platinum-based chemotherapy was compared to single-agent pembrolizumab in advanced non-small cell lung cancer (NSCLC) with PDL1 > 50% in KEYNOTE-024. In this trial, it was found that patients who received single-agent pembrolizumab had improved progression-free survival in addition to overall survival (OS). Based on KEYNOTE-024, only 53% of patients treated originally with pembrolizumab received second-line anticancer systemic therapy with an OS of 26.3 months. Based on these results, the objective of this study was to characterize real-world NSCLC patients who received second-line therapy after single-agent pembrolizumab. METHODS: This was a retrospective cohort study considering stage IV NSCLC patients diagnosed with BC Cancer between 2018 and 2021 with PD-L1 ≥ 50% who received first-line single agent pembrolizumab. Patient demographics, cancer history, treatment administered, and survival were collected retrospectively. Descriptive statistics were produced. OS was calculated using Kaplan-Meier curves and compared using the log rank test. A multivariate model evaluated characteristics associated with the receipt of second-line therapy. RESULTS: A total of 718 patients were diagnosed with Stage IV NSCLC and received at least one cycle of pembrolizumab. The median duration of treatment was 4.4 months, and the follow-up duration was 16.0 months. There were 567 (79%) patients who had disease progression, of whom 21% received second-line systemic therapy. Within the subset of patients with disease progression, the median duration of treatment was 3.0 months. It would be found that patients who received second-line therapy had better baseline ECOG performance status, were younger at diagnosis, and had a longer duration of pembrolizumab. Within the full population, the OS from the treatment initiation date was 14.0 months. OS was 5.6 months in patients who did not receive additional therapy after progression and 22.2 months in patients who received subsequent therapy. Baseline ECOG performance status was associated with improved OS in multivariate analysis. CONCLUSION: Based on this real-world Canadian population, 21% of patients received second-line systemic therapy, despite second-line therapy being associated with prolonged survival. In this real-world population, we found that 60% fewer patients received second-line systemic therapy when compared to KEYNOTE-024. Although differences always exist when comparing a clinical and non-clinical trial population, our findings suggest undertreating stage IV NSCLC patients.

Improved uptake and survival with systemic treatments for metastatic non-small cell lung cancer: younger versus older adults.

BACKGROUND: Over the past decade, there has been increasing availability of novel therapeutics with improved tolerability and efficacy for advanced non-small cell lung cancer (NSCLC). The study goals were: to compare the uptake of systemic therapy (ST) before and after the availability of targeted tyrosine kinase inhibitors (TKI) and immunotherapy and to examine the changes in overall survival (OS) over time between younger and older adults with advanced NSCLC. METHODS: All patients with advanced NSCLC referred to British Columbia (BC) Cancer in 2009, 2011, 2015 and 2017 were included. One-year time points were based on molecular testing implementation and funded drug availability: baseline (2009), epidermal growth factor receptor TKI (2011), anaplastic lymphoma kinase TKI (2015) and Programed Death-1 (PD-1) inhibitors (2017). Age groups were <70years and ≥70years. Baseline demographics, simplified comorbidity scores (SCS), disease characteristics, and ST details were collected retrospectively. Variables were compared using X2, Fisher's exact tests and logistic-regression analysis. OS was calculated using the Kaplan-Meier method and compared using the log-rank test. RESULTS: 3325 patients were identified. Baseline characteristics were compared between ages < 70 years and ≥ 70 years for each time cohort with significant differences noted in baseline Eastern Cooperative Oncology Group (ECOG) performance status and SCS. The rate of ST delivery trended upwards over time with age <70 years: 2009 44%, 2011 53%, 2015 50% and 2017 52% and age ≥70 years: 22%, 25%, 28% and 29% respectively. Predictors for decreased use of ST for age <70 years: ECOG ≥2, SCS ≥9, year 2011, and smoking history; and age ≥70 years: ECOG ≥2, years 2011 and 2015, and smoking history. The median OS of patients who received ST improved from 2009 to 2017: age <70 years 9.1 m vs. 15.5 m and age ≥70 years 11.4 m vs. 15.0 m. CONCLUSIONS: There was an increased uptake of ST for both age groups with the introduction of novel therapeutics. Although a smaller proportion of older adults received ST, those who received treatment had comparable OS to their young counterpart. The benefit of ST in both age groups was seen across the different types of treatments. With careful assessment and selection of appropriate candidates, older adults with advanced NSCLC appear to benefit from ST.

Increased risk of cutaneous immune-related adverse events in patients treated with talimogene laherparepvec and immune checkpoint inhibitors: A multi-hospital cohort study.

BACKGROUND: Previous studies have shown that combining immune checkpoint inhibitors (ICIs) with talimogene laherparepvec (TVEC) may improve antitumor responses. However, the risk of developing cutaneous immune-related adverse events (cirAEs) in patients treated with ICI and TVEC has not been studied. OBJECTIVE: To evaluate the differences in cirAE development between patients treated with ICI alone and both ICI and TVEC (ICI + TVEC). METHODS: Patients with cutaneous malignancy receiving ICI with or without TVEC therapy at the Massachusetts General Brigham healthcare system were included. CirAE development, time from ICI initiation to cirAE, cirAE grade, cirAE morphology, and survival were analyzed. Pearson's χ2 test or Fisher's exact test for categorical variables and t test or Kruskal-Wallis test for continuous variables were used. To account for immortal time bias, we performed adjusted time-varying Cox proportional hazards modeling. RESULTS: The rate of cirAE development was 32.3% and 38.7% for ICI only and ICI + TVEC, respectively. After adjusting for covariates, ICI + TVEC was associated with a 2-fold increased risk of cirAE development (hazard ratio: 2.03, P = .006) compared to patients receiving ICI therapy alone. LIMITATIONS: The retrospective nature and limited sample size from a tertiary-level academic center. CONCLUSION: These findings underscore potential opportunities for dermatologists and oncologists in counseling and monitoring patients.

Predicting the Survival of Patients With Cancer From Their Initial Oncology Consultation Document Using Natural Language Processing.

Importance: Predicting short- and long-term survival of patients with cancer may improve their care. Prior predictive models either use data with limited availability or predict the outcome of only 1 type of cancer. Objective: To investigate whether natural language processing can predict survival of patients with general cancer from a patient's initial oncologist consultation document. Design, Setting, and Participants: This retrospective prognostic study used data from 47 625 of 59 800 patients who started cancer care at any of the 6 BC Cancer sites located in the province of British Columbia between April 1, 2011, and December 31, 2016. Mortality data were updated until April 6, 2022, and data were analyzed from update until September 30, 2022. All patients with a medical or radiation oncologist consultation document generated within 180 days of diagnosis were included; patients seen for multiple cancers were excluded. Exposures: Initial oncologist consultation documents were analyzed using traditional and neural language models. Main Outcomes and Measures: The primary outcome was the performance of the predictive models, including balanced accuracy and receiver operating characteristics area under the curve (AUC). The secondary outcome was investigating what words the models used. Results: Of the 47 625 patients in the sample, 25 428 (53.4%) were female and 22 197 (46.6%) were male, with a mean (SD) age of 64.9 (13.7) years. A total of 41 447 patients (87.0%) survived 6 months, 31 143 (65.4%) survived 36 months, and 27 880 (58.5%) survived 60 months, calculated from their initial oncologist consultation. The best models achieved a balanced accuracy of 0.856 (AUC, 0.928) for predicting 6-month survival, 0.842 (AUC, 0.918) for 36-month survival, and 0.837 (AUC, 0.918) for 60-month survival, on a holdout test set. Differences in what words were important for predicting 6- vs 60-month survival were found. Conclusions and Relevance: These findings suggest that models performed comparably with or better than previous models predicting cancer survival and that they may be able to predict survival using readily available data without focusing on 1 cancer type.

Influence of melanoma type on incidence and downstream implications of cutaneous immune-related adverse events in the setting of immune checkpoint inhibitor therapy.

BACKGROUND: Emerging evidence suggests that cutaneous immune-related adverse events (cirAEs) are associated with a survival benefit in the setting of advanced melanoma treated with immune checkpoint inhibitor (ICI) therapy. Previous studies have not examined the role of melanoma subtypes on cirAE development and downstream therapeutic outcomes. OBJECTIVE: Examine the impact of melanoma subtypes on cirAE onset and survival among ICI recipients. METHODS: Retrospective multi-institutional cohort study. Multivariate time-series regressions were utilized to assess relationships between melanoma subtype, cirAE development, and survival. RESULTS: Among 747 ICI recipients, 236 (31.6%) patients developed a cirAE. Patients with acral melanoma were less likely to develop a cirAE (hazard ratio [HR] = 0.41, P = .016) compared to patients with nonacral cutaneous melanoma. Across all melanoma subtypes, cirAEs were associated with reduced mortality (HR = 0.76, P = .042). Patients with acral (HR = 2.04, P = .005), mucosal (HR = 2.30, P < .001), and uveal (HR = 4.09, P < .001) primaries exhibited the worst survival. LIMITATIONS: Retrospective cohort study. CONCLUSION: This is the first study to demonstrate differences in cirAE development among melanoma subtypes. The presence of cirAEs was associated with better survival. Further, the lower incidence of cirAEs may be a marker of immunotherapy response, which is reflected in the association between acral melanoma and mortality.