The Impact of Radiologist Screening Mammogram Reading Volume on Performance in the Ontario Breast Screening Program.

PURPOSE: Although some studies have shown increasing radiologists' mammography volumes improves performance, there is a lack of evidence specific to digital mammography and breast screening program performance targets. This study evaluates the relationship between digital screening volume and meeting performance targets. METHODS: This retrospective cohort study included 493 radiologists in the Ontario Breast Screening Program who interpreted 1,762,173 screening mammograms in participants ages 50-90 between 2014 and 2016. Associations between annual screening volume and meeting performance targets for abnormal call rate, positive predictive value (PPV), invasive cancer detection rate (CDR), sensitivity, and specificity were modeled using mixed-effects multivariate logistic regression. RESULTS: Most radiologists read 500-999 (36.7%) or 1,000-1,999 (31.0%) screens annually, and 18.5% read ≥2,000. Radiologists who read ≥2,000 annually were more likely to meet abnormal call rate (OR = 3.85; 95% CI: 1.17-12.61), PPV (OR = 5.36; 95% CI: 2.53-11.34), invasive CDR (OR = 4.14; 95% CI: 1.50-11.46), and specificity (OR = 4.07; 95% CI: 1.89-8.79) targets versus those who read 100-499 screens. Radiologists reading 1,000-1,999 screens annually were more likely to meet PPV (OR = 2.32; 95% CI: 1.22-4.40), invasive CDR (OR = 3.36; 95% CI: 1.49-7.59) and specificity (OR = 2.00; 95% CI: 1.04-3.84) targets versus those who read 100-499 screens. No significant differences were observed for sensitivity. CONCLUSIONS: Annual reading volume requirements of 1,000 in Canada are supported as screening volume above 1,000 was strongly associated with achieving performance targets for nearly all measures. Increasing the minimum volume to 2,000 may further reduce the potential limitations of screening due to false positives, leading to improvements in overall breast screening program quality.

Pathways to Acceptance in Participants of Advanced Cancer Online Support Groups.

Background and Objectives: Individuals with cancer, especially advanced cancer, are faced with numerous difficulties associated with the disease, including an earlier death than expected. Those who are able to confront and accept the hardships associated with the disease in a way that aligns with their beliefs benefit from more positive psychological outcomes compared to those who are aware of their diagnosis but are unable to accept it. To date, there is limited research exploring factors contributing to illness and death acceptance in the context of advanced cancer in group therapy settings. Materials and Methods: The current study used a Directed Content Analysis approach on transcripts of online advanced cancer support groups to investigate if and how Yalom's existential factors played a role in the emergence of acceptance. Results: The online support group platform, combined with the help of facilitators, offered supportive environments for individuals seeking help with cancer-related distress by helping patients move towards acceptance. Some participants had already begun the process of accepting their diagnosis before joining the group, others developed acceptance during the group process, while a few continued to be distressed. Our analysis revealed the emergence of four themes related to illness acceptance: (1) Facilitator-Initiated Discussion, including sub-themes of Mindfulness, Relaxation and Imagery, Changing Ways of Thinking, and Spirituality; (2) Personal attitudes, including sub-themes of Optimism and Letting Go of Control; (3) Supportive Environment, including the sub-themes of Providing Support to Others and Receiving Support from Others; and (4) Existential Experience, which included sub-themes of Living with the Diagnosis for an Extended Amount of Time, Legacy and Death Preparations, and Appreciating life. Conclusions: With a paradigm shift to online delivery of psychological services, recognizing factors that contribute to acceptance when dealing with advanced cancer may help inform clinical practices. Future studies should explore patient acceptance longitudinally to inform whether it emerges progressively, which has been suggested by Kübler-Ross.

Telephone versus in-person colorectal cancer risk and screening intervention for first-degree relatives: A randomized controlled trial.

BACKGROUND: Having a first-degree relative (FDR) with colorectal cancer (CRC) is a significant risk factor for CRC. Counseling for FDRs regarding CRC risk factors and personalized risk is important to improve knowledge and screening compliance. METHODS: A 3-arm randomized controlled trial compared tailored in-person and telephone CRC counseling interventions with controls among FDRs who were not mutation carriers for known hereditary cancer syndromes, but who were considered to be at an increased risk based on family history. It was hypothesized that both telephone and in-person approaches would increase CRC knowledge, screening adherence, perceived risk accuracy, and psychosocial functioning compared with controls. The authors anticipated greater satisfaction with the in-person approach. CRC knowledge, risk perception, psychosocial functioning, and intention to screen were assessed at baseline and at 2-week and 2-month follow-ups (primary endpoint). RESULTS: A total of 278 FDRs (mean age, 47.4 years, standard deviation, 11.38 years) participated. At baseline, participants reported low to moderate CRC knowledge and overestimations of risk. Screening adherence was 73.7%. At 2 months, participants in the in-person arm and telephone arm demonstrated improvements in knowledge and perceived risk and were not found to be statistically different from each other. However, when comparing each intervention with controls, knowledge in the in-person arm was found to be statistically significantly higher, but the difference between the telephone and control arms was not. Cancer-related stress reduced over time in all groups. Intervention benefits were maintained at 1 year. Baseline screening intent/adherence were high, and therefore did not reach statistically significant improvement. CONCLUSIONS: Tailored in-person or telephone formats for providing CRC risk counseling, incorporating behavioral interventions, appear to improve knowledge and risk perceptions, with high client satisfaction.

Symptom screening for constipation in oncology: getting to the bottom of the matter.

PURPOSE: This study seeks to determine whether specific screening for constipation will increase the frequency of clinician response within the context of an established symptom screening program. METHODS: A "constipation" item was added to routine Edmonton Symptom Assessment System (ESAS) screening in gynecologic oncology clinics during a 7-week trial period, without additional constipation-specific training. Chart audits were then conducted to determine documentation of assessment and intervention for constipation in three groups of patients, those who completed (1) ESAS (n = 477), (2) ESAS-C with constipation (n = 435), and (3) no ESAS (n = 511). RESULTS: Among patients who were screened for constipation, 17% reported moderate to severe symptoms. Greater constipation severity increased the likelihood of documented assessment (Z = 2.37, p = .018) and intervention (Z = 1.99, p = .048). Overall rates of documented assessment were 36%, with the highest assessment rate in the no ESAS group (χ2 = 9.505, p = .006), a group with the highest proportion of late-stage disease. No difference in the rate of assessment was found between the ESAS and ESAS-C groups. Overall rates for documentation of intervention were low, and did not differ between groups. CONCLUSIONS: Specific screening for constipation within an established screening program did not increase the documentation rate for constipation assessment or intervention. The inclusion of specific symptoms in multi-symptom screening initiatives should be carefully evaluated in terms of added value versus patient burden. Care pathways should include guidance on triaging results from multi-symptom screening, and clinicians should pay particular attention to patients who are missed from screening altogether, as they may be the most symptomatic group.

A randomized controlled trial of a supportive expressive group intervention for women with a family history of breast cancer.

OBJECTIVE: Women with a family history of breast cancer (BC) often overestimate their BC risk. Heightened psychological distress may interfere with risk comprehension and screening adherence. The primary purpose of this study was to test the efficacy of a 12-week manual-based supportive-expressive (SE) group intervention for this population. METHODS: Using a randomized control trial design, this study compared two interventions: a standard risk-counseling arm (RC) compared with that plus SE group intervention. The primary study outcome was BC anxiety. Secondary outcomes included psychosocial functioning, risk comprehension, BC knowledge, and screening behaviors. RESULTS: A total of 161 women with a family history of BC were randomized into SE (N = 108) or RC (N = 53). Participants in both study arms significantly improved on measures of BC anxiety, psychosocial functioning, risk comprehension, and BC knowledge, with no statistical difference between study arms. Benefits were sustained at 1 year. BC screening rates were high in both arms at baseline and follow-up. CONCLUSIONS: SE group therapy as an added intervention to the risk counseling was well-received, however, did not demonstrate superiority to RC alone. Future studies on treatment matching are needed to further our understanding of interventions that can support women with a family history of BC to work through residual issues, including loss and grief.

Feasibility and diagnostic accuracy of the Patient-Reported Outcomes Measurement Information System (PROMIS) item banks for routine surveillance of sleep and fatigue problems in ambulatory cancer care.

BACKGROUND: Routine screening for problematic symptoms is emerging as a best practice in cancer systems globally. The objective of this observational study was to assess the feasibility and diagnostic accuracy of Patient-Reported Outcomes Measurement Information System (PROMIS) computerized adaptive testing (CAT) for fatigue and sleep-disturbance items compared with legacy measures in routine ambulatory cancer care. METHODS: Patients who attended outpatient clinics at the Princess Margaret Cancer Center completed PROMIS CAT item banks and legacy measures (the Functional Assessment of Chronic Illness Therapy [FACIT]-Fatigue scale and the Insomnia Severity Index [ISI]) using tablet computers during clinic visits. The completion rates, patient acceptability, and diagnostic accuracy of PROMIS CAT were evaluated against legacy measures using receiver operating characteristic (ROC) curve analysis. RESULTS: Participants consisted of 336 patients (mean age ± standard deviation, 57.4 ± 15.7 years; 55% females; 75% Caucasian). Over 98% of patients did not find symptom screening was burdensome, although only 65% were willing to complete the survey at every visit. PROMIS CAT scores were significantly correlated with both FACIT-Fatigue scores (r = -0.83) and ISI scores (r = -0.57; p < 0.0001 for all). Areas under the curve (AUC) by ROC analysis for fatigue were 0.946 using the FACIT-Fatigue cutoff ≤30, 0.910 for sleep disturbance, and 0.922 for sleep impairment using the ISI cutoff ≥15. The recommended T-score cut-off for PROMIS CAT Fatigue was 57, Sleep Disturbance was 57, and Sleep Impairment was 57. CONCLUSIONS: The current results support the feasibility and accuracy of PROMIS CAT and its potential for use in routine ambulatory cancer care. Future research will assess feedback of these data to clinicians and evaluate effects on earlier identification of and intervention for these problems. Cancer 2016. © 2016 American Cancer Society. Cancer 2016;122:2906-2917. © 2016 American Cancer Society.

Employment needs of and barriers for Chinese youth and young adults with Autism Spectrum Conditions in Ontario, Canada.

BACKGROUND: Cultural-based literature focusing on Asian autistic immigrants living in Western countries is very limited. AIMS: The present study is a quality improvement exercise aiming to fill the gap by investigating the employment needs of and barriers for Chinese autistic youth and young adults in Ontario, Canada. METHODS & PROCEDURES: 71 individuals diagnosed with autism and 24 diagnosed with other mental illnesses, aged 12-29, participated in an online survey regarding their work readiness, work skills, interests, health and cultural concerns. Analyses were conducted to compare the autistic group and the mental health group. OUTCOMES & RESULTS: Results show that the autistic sample has inferior (1) work habits related skills, (2) work style related skills, (3) level of independence, (4) skills to perform routine daily activities, (5) interpersonal skills at work, and (6) ability to tolerate visual and moving stimuli in the work environment. It is also found that the autistic group has more symptoms of depression, anxiety, and autism than that of the non-autistic group. CONCLUSIONS & IMPLICATIONS: The study shed light into the unique needs and barriers of Chinese autistic young adults and the service gap in supporting their transition to employment.

Understanding Elderly Chinese Cancer Patients in a Multicultural Clinical Setting: Embracing Mortality and Addressing Misperceptions of Vulnerability.

Chinese patients face higher risks of gastrointestinal (GI) cancers and greater cancer-related deaths than Canadian-born patients. The older population encounters barriers to quality healthcare, impacting their well-being and survival. Previous studies highlighted Chinese immigrant perceptions of not requiring healthcare support. During the COVID-19 pandemic, their underutilization of healthcare services garnered attention. The present study explores the experiences of older Chinese cancer patients to improve culturally sensitive cancer care. A total of twenty interviews carried out in Cantonese and Mandarin were conducted with Chinese immigrants, aged 60 or above, diagnosed with Stage 3 or 4 GI cancer. These interviews were transcribed verbatim, translated, and subjected to qualitative descriptive analysis. Among older Chinese immigrant patients, a phenomenon termed "Premature Acceptance: Normalizing Death and Dying" was observed. This involved four key themes: 1. acceptance and letting go, 2. family first, 3. self-sufficiency, and 4. barriers to supportive care. Participants displayed an early acceptance of their own mortality, prioritizing family prosperity over their own quality of life. Older Chinese patients normalize the reality of facing death amidst cancer. They adopt a pragmatic outlook, acknowledging life-saving treatments while willingly sacrificing their own support needs to ease family burdens. Efforts to enhance health literacy require culturally sensitive programs tailored to address language barriers and differing values among this population. A strengths-based approach emphasizing family support and practical aspects of care may help build resilience and improve symptom management, thereby enhancing their engagement with healthcare services.

Artificial Intelligence-Based Co-Facilitator (AICF) for Detecting and Monitoring Group Cohesion Outcomes in Web-Based Cancer Support Groups: Single-Arm Trial Study.

BACKGROUND: Commonly offered as supportive care, therapist-led online support groups (OSGs) are a cost-effective way to provide support to individuals affected by cancer. One important indicator of a successful OSG session is group cohesion; however, monitoring group cohesion can be challenging due to the lack of nonverbal cues and in-person interactions in text-based OSGs. The Artificial Intelligence-based Co-Facilitator (AICF) was designed to contextually identify therapeutic outcomes from conversations and produce real-time analytics. OBJECTIVE: The aim of this study was to develop a method to train and evaluate AICF's capacity to monitor group cohesion. METHODS: AICF used a text classification approach to extract the mentions of group cohesion within conversations. A sample of data was annotated by human scorers, which was used as the training data to build the classification model. The annotations were further supported by finding contextually similar group cohesion expressions using word embedding models as well. AICF performance was also compared against the natural language processing software Linguistic Inquiry Word Count (LIWC). RESULTS: AICF was trained on 80,000 messages obtained from Cancer Chat Canada. We tested AICF on 34,048 messages. Human experts scored 6797 (20%) of the messages to evaluate the ability of AICF to classify group cohesion. Results showed that machine learning algorithms combined with human input could detect group cohesion, a clinically meaningful indicator of effective OSGs. After retraining with human input, AICF reached an F1-score of 0.82. AICF performed slightly better at identifying group cohesion compared to LIWC. CONCLUSIONS: AICF has the potential to assist therapists by detecting discord in the group amenable to real-time intervention. Overall, AICF presents a unique opportunity to strengthen patient-centered care in web-based settings by attending to individual needs. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/21453.

Risk-based lung cancer screening performance in a universal healthcare setting.

Globally, lung cancer is the leading cause of cancer death. Previous trials demonstrated that low-dose computed tomography lung cancer screening of high-risk individuals can reduce lung cancer mortality by 20% or more. Lung cancer screening has been approved by major guidelines in the United States, and over 4,000 sites offer screening. Adoption of lung screening outside the United States has, until recently, been slow. Between June 2017 and May 2019, the Ontario Lung Cancer Screening Pilot successfully recruited 7,768 individuals at high risk identified by using the PLCOm2012noRace lung cancer risk prediction model. In total, 4,451 participants were successfully screened, retained and provided with high-quality follow-up, including appropriate treatment. In the Ontario Lung Cancer Screening Pilot, the lung cancer detection rate and the proportion of early-stage cancers were 2.4% and 79.2%, respectively; serious harms were infrequent; and sensitivity to detect lung cancers was 95.3% or more. With abnormal scans defined as ones leading to diagnostic investigation, specificity was 95.5% (positive predictive value, 35.1%), and adherence to annual recall and early surveillance scans and clinical investigations were high (>85%). The Ontario Lung Cancer Screening Pilot provides insights into how a risk-based organized lung screening program can be implemented in a large, diverse, populous geographic area within a universal healthcare system.

Routine screening for suicidal intention in patients with cancer.

OBJECTIVES: Suicide rates are elevated in individuals with cancer, although suicidal intention is not typically assessed in cancer centers. We evaluated in a large comprehensive cancer center the utility of an electronic Distress Assessment and Response Tool (DART), in which suicidal intention is assessed with a single item. METHODS: Patients attending cancer clinics completed DART as part of routine care. DART includes measures of physical symptoms, depression, anxiety, social difficulties, and practical concerns. Medical variables were obtained from the Princess Margaret Cancer Registry, the data warehouse of cancer patient statistics. A Generalized Estimating Equation (GEE) model was used to assess factors associated with suicidal intention. RESULTS: Between September 2009 and March 2012, 4822/5461 patients (88.3%) who completed DART consented to the use of their data for research. Amongst the latter, 280 (5.9%) of the 4775 patients who answered the question reported suicidal ideation, which was related to physical and psychological distress, and social difficulties (ps < 0.0001). Amongst those with ideation who responded to the intention question, 20/186 (10.8%) reported suicidal intention. Of respondents with more severe suicidal ideation, 12/49 (24.5%) reported suicidal intention. Using a GEE model, suicidal intention in those with ideation was significantly associated with male sex, difficulty making treatment decisions, and with everyday living concerns. CONCLUSIONS: Suicidal ideation is reported on an electronic distress screening tool (DART) by almost 6% of cancer patients, of whom almost 11% report suicidal intention and 33% decline to indicate intention. DART demonstrated utility in identifying patients who may be at highest risk of completed suicide and who require urgent clinical assessment.

Cocreating Meaning Through Expressive Writing and Reading for Cancer Caregivers.

PURPOSE: Caregivers of patients with cancer cope with socioemotional challenges, which can adversely affect their well-being. We developed an intervention, expressive writing and reading (EWR), to promote emotional processing and social connectedness among caregivers. In a single-arm pilot study, we assessed its feasibility and perceived usefulness. METHODS: Caregivers participated in weekly 1.5-hour EWR workshops offered over 20 weeks. After 4 sessions, they completed semistructured interviews, which were analyzed using qualitative descriptive analysis. FINDINGS: Of 65 caregivers approached, 25 were eligible, 18 consented, and 9 (50%) caregivers completed at least 4 workshops and the interview. Their responses revealed 3 themes: "inner processing," "interpersonal learning," and "enhanced processing and preparedness." Perceived benefits of EWR included emotional and cognitive processing (individual and collaborative), learning from the emotions and experiences of other caregivers, and preparing for upcoming challenges. CONCLUSIONS: Expressive writing and reading can be a safe and cost-effective supportive intervention for caregivers of patients with cancer.

Therapist Feedback and Implications on Adoption of an Artificial Intelligence-Based Co-Facilitator for Online Cancer Support Groups: Mixed Methods Single-Arm Usability Study.

BACKGROUND: The recent onset of the COVID-19 pandemic and the social distancing requirement have created an increased demand for virtual support programs. Advances in artificial intelligence (AI) may offer novel solutions to management challenges such as the lack of emotional connections within virtual group interventions. Using typed text from online support groups, AI can help identify the potential risk of mental health concerns, alert group facilitator(s), and automatically recommend tailored resources while monitoring patient outcomes. OBJECTIVE: The aim of this mixed methods, single-arm study was to evaluate the feasibility, acceptability, validity, and reliability of an AI-based co-facilitator (AICF) among CancerChatCanada therapists and participants to monitor online support group participants' distress through a real-time analysis of texts posted during the support group sessions. Specifically, AICF (1) generated participant profiles with discussion topic summaries and emotion trajectories for each session, (2) identified participant(s) at risk for increased emotional distress and alerted the therapist for follow-up, and (3) automatically suggested tailored recommendations based on participant needs. Online support group participants consisted of patients with various types of cancer, and the therapists were clinically trained social workers. METHODS: Our study reports on the mixed methods evaluation of AICF, including therapists' opinions as well as quantitative measures. AICF's ability to detect distress was evaluated by the patient's real-time emoji check-in, the Linguistic Inquiry and Word Count software, and the Impact of Event Scale-Revised. RESULTS: Although quantitative results showed only some validity of AICF's ability in detecting distress, the qualitative results showed that AICF was able to detect real-time issues that are amenable to treatment, thus allowing therapists to be more proactive in supporting every group member on an individual basis. However, therapists are concerned about the ethical liability of AICF's distress detection function. CONCLUSIONS: Future works will look into wearable sensors and facial cues by using videoconferencing to overcome the barriers associated with text-based online support groups. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/21453.

Integrating Smoking Cessation Into Low-Dose Computed Tomography Lung Cancer Screening: Results of the Ontario, Canada Pilot.

INTRODUCTION: Low-dose computed tomography screening in high-risk individuals reduces lung cancer mortality. To inform the implementation of a provincial lung cancer screening program, Ontario Health undertook a Pilot study, which integrated smoking cessation (SC). METHODS: The impact of integrating SC into the Pilot was assessed by the following: rate of acceptance of a SC referral; proportion of individuals who were currently smoking cigarettes and attended a SC session; the quit rate at 1 year; change in the number of quit attempts; change in Heaviness of Smoking Index; and relapse rate in those who previously smoked. RESULTS: A total of 7768 individuals were recruited predominantly through primary care physician referral. Of these, 4463 were currently smoking and were risk assessed and referred to SC services, irrespective of screening eligibility: 3114 (69.8%) accepted referral to an in-hospital SC program, 431 (9.7%) to telephone quit lines, and 50 (1.1%) to other programs. In addition, 4.4% reported no intention to quit and 8.5% were not interested in participating in a SC program. Of the 3063 screen-eligible individuals who were smoking at baseline low-dose computed tomography scan, 2736 (89.3%) attended in-hospital SC counseling. The quit rate at 1 year was 15.5% (95% confidence interval: 13.4%-17.7%; range: 10.5%-20.0%). Improvements were also observed in Heaviness of Smoking Index (p < 0.0001), number of cigarettes smoked per day (p < 0.0001), time to first cigarette (p < 0.0001), and number of quit attempts (p < 0.001). Of those who reported having quit within the previous 6 months, 6.3% had resumed smoking at 1 year. Furthermore, 92.7% of the respondents reported satisfaction with the hospital-based SC program. CONCLUSIONS: On the basis of these observations, the Ontario Lung Screening Program continues to recruit through primary care providers, to assess risk for eligibility using trained navigators, and to use an opt-out approach to referral for cessation services. In addition, initial in-hospital SC support and intensive follow-on cessation interventions will be provided to the extent possible.

The impact of premorbid and postmorbid depression onset on mortality and cardiac morbidity among patients with coronary heart disease: meta-analysis.

BACKGROUND: Depression is associated with increased cardiac morbidity and mortality in the general population and in patients with coronary heart disease (CHD). Recent evidence suggests that patients with new-onset depression post-CHD diagnosis have worse outcomes than do those who had previous or recurrent depression. This meta-analysis investigated the timing of depression onset in established CHD and CHD-free cohorts to determine what time frame is associated with greater mortality and cardiac morbidity. METHODOLOGY/PRINCIPAL FINDINGS: The MEDLINE, EMBASE, and PsycINFO databases were searched systematically to identify articles examining a depression time frame that specified an end point of all-cause mortality, cardiac mortality, rehospitalization, or major adverse cardiac events. A meta-analysis was conducted to estimate effect sizes by time frame of depression. Twenty-two prospective cohort studies were identified. Nine studies investigated premorbid depression in CHD-free cohorts in relation to cardiac death. Thirteen studies in patient samples with CHD examined new-onset depression in comparison with previous or recurrent depression. The pooled effect size (risk ratio) was 0.76 (95% confidence interval (CI) = 0.48-1.19) for history of depression only, 1.79 (95% CI = 1.45-2.21) for premorbid depression onset, 2.11 (95% CI = 1.66-2.68) for postmorbid or new depression onset, and 1.59 (95% CI = 1.08-2.34) for recurrent depression. CONCLUSIONS/SIGNIFICANCE: Both premorbid and postmorbid depression onsets are potentially hazardous, and the question of timing may be irrelevant with respect to adverse cardiac outcomes. However, the combination of premorbid depression with the absence of depression at the time of a cardiac event (i.e., historical depression only) is not associated with such outcomes and deserves further investigation.

Providing Care Beyond Therapy Sessions With a Natural Language Processing-Based Recommender System That Identifies Cancer Patients Who Experience Psychosocial Challenges and Provides Self-care Support: Pilot Study.

BACKGROUND: The negative psychosocial impacts of cancer diagnoses and treatments are well documented. Virtual care has become an essential mode of care delivery during the COVID-19 pandemic, and online support groups (OSGs) have been shown to improve accessibility to psychosocial and supportive care. de Souza Institute offers CancerChatCanada, a therapist-led OSG service where sessions are monitored by an artificial intelligence-based co-facilitator (AICF). The AICF is equipped with a recommender system that uses natural language processing to tailor online resources to patients according to their psychosocial needs. OBJECTIVE: We aimed to outline the development protocol and evaluate the AICF on its precision and recall in recommending resources to cancer OSG members. METHODS: Human input informed the design and evaluation of the AICF on its ability to (1) appropriately identify keywords indicating a psychosocial concern and (2) recommend the most appropriate online resource to the OSG member expressing each concern. Three rounds of human evaluation and algorithm improvement were performed iteratively. RESULTS: We evaluated 7190 outputs and achieved a precision of 0.797, a recall of 0.981, and an F1 score of 0.880 by the third round of evaluation. Resources were recommended to 48 patients, and 25 (52%) accessed at least one resource. Of those who accessed the resources, 19 (75%) found them useful. CONCLUSIONS: The preliminary findings suggest that the AICF can help provide tailored support for cancer OSG members with high precision, recall, and satisfaction. The AICF has undergone rigorous human evaluation, and the results provide much-needed evidence, while outlining potential strengths and weaknesses for future applications in supportive care.

Natural Language Processing-Based Virtual Cofacilitator for Online Cancer Support Groups: Protocol for an Algorithm Development and Validation Study.

BACKGROUND: Cancer and its treatment can significantly impact the short- and long-term psychological well-being of patients and families. Emotional distress and depressive symptomatology are often associated with poor treatment adherence, reduced quality of life, and higher mortality. Cancer support groups, especially those led by health care professionals, provide a safe place for participants to discuss fear, normalize stress reactions, share solidarity, and learn about effective strategies to build resilience and enhance coping. However, in-person support groups may not always be accessible to individuals; geographic distance is one of the barriers for access, and compromised physical condition (eg, fatigue, pain) is another. Emerging evidence supports the effectiveness of online support groups in reducing access barriers. Text-based and professional-led online support groups have been offered by Cancer Chat Canada. Participants join the group discussion using text in real time. However, therapist leaders report some challenges leading text-based online support groups in the absence of visual cues, particularly in tracking participant distress. With multiple participants typing at the same time, the nuances of the text messages or red flags for distress can sometimes be missed. Recent advances in artificial intelligence such as deep learning-based natural language processing offer potential solutions. This technology can be used to analyze online support group text data to track participants' expressed emotional distress, including fear, sadness, and hopelessness. Artificial intelligence allows session activities to be monitored in real time and alerts the therapist to participant disengagement. OBJECTIVE: We aim to develop and evaluate an artificial intelligence-based cofacilitator prototype to track and monitor online support group participants' distress through real-time analysis of text-based messages posted during synchronous sessions. METHODS: An artificial intelligence-based cofacilitator will be developed to identify participants who are at-risk for increased emotional distress and track participant engagement and in-session group cohesion levels, providing real-time alerts for therapist to follow-up; generate postsession participant profiles that contain discussion content keywords and emotion profiles for each session; and automatically suggest tailored resources to participants according to their needs. The study is designed to be conducted in 4 phases consisting of (1) development based on a subset of data and an existing natural language processing framework, (2) performance evaluation using human scoring, (3) beta testing, and (4) user experience evaluation. RESULTS: This study received ethics approval in August 2019. Phase 1, development of an artificial intelligence-based cofacilitator, was completed in January 2020. As of December 2020, phase 2 is underway. The study is expected to be completed by September 2021. CONCLUSIONS: An artificial intelligence-based cofacilitator offers a promising new mode of delivery of person-centered online support groups tailored to individual needs. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/21453.

Timing of depressive symptom onset and in-hospital complications among acute coronary syndrome inpatients.

BACKGROUND: Recent research has reported an association between in-hospital depression and poorer long-term prognosis and a greater risk of in-hospital complications. OBJECTIVE: The purpose of the current study was to examine the relationship between past and incident depressive symptoms and in-hospital complications in acute coronary syndrome (ACS) inpatients. METHOD: A group of 906 ACS inpatients from 12 coronary-care units participated in the study. Incident depressive symptoms were assessed through the Beck Depression Inventory, and participants' were asked about past history of prolonged depressed mood. In-hospital complications were noted as present or absent by nurses, and authors conducted logistic-regression analyses. RESULTS: A subset of 492 patients (58.4%) experienced an in-hospital complication, the most common being ischemia (48.8%) and cardiac arrest (7.2%). After adjusting for prognostic indicators, incident and past-combined-with-incident depressive symptoms were significantly associated with an increased risk of experiencing an in-hospital complication. CONCLUSION: Incident symptoms, in particular, seem to be prognostic. This finding suggests that acute emotions may be triggering cardiac complications, and early identification of emotional symptoms is warranted.

Access to cardiac rehabilitation among South-Asian patients by referral method: a qualitative study.

People of South-Asian origin have an increased prevalence of coronary artery disease. Although cardiac rehabilitation (CR) is effective, South Asians are among the least likely people to participate in these programs. Automatic referral increases CR use and may reduce access inequalities. This study qualitatively explored whether CR referral knowledge and access varied among South-Asian patients. Participants were South-Asian cardiac patients receiving treatment at hospitals in Ontario, Canada. Each hospital refers to CR via one offour methods: automatically through paper or electronically, through discussion with allied health professionals (liaison referral), or through referral at the physician's discretion. Data were collected via interviews and analyzed using interpretive-descriptive analysis. Four themes emerged: the importance of predischarge CR discussions with healthcare providers, limited knowledge of CR, ease of the referral process for facilitators of CR attendance, and participants'needs for personal autonomy regarding their decision to attend CR. Liaison referral was perceived to be the most suitable referral method for participants. It facilitated communication between patients and providers, ensuring improved understanding of CR. Automatic referral may not be as well suited to this population because of reduced patient-provider communication.

Addressing Educational Needs in Managing Complex Pain in Cancer Populations: Evaluation of APAM: An Online Educational Intervention for Nurses.

CONTEXT: Cancer-related pain is associated with significant suffering and is one of the most challenging symptoms to manage. Studies indicate that front-line clinicians often lack the knowledge on best practices in cancer pain management. OBJECTIVES: The current project, a quality improvement (QI) initiative, evaluated the outcome of an online educational intervention for nurses on complex cancer pain management. METHODS: An online 7-module educational intervention, Advanced Pain Assessment and Management, was offered from 2012 to 2017. Pre-post course evaluations included self-reported knowledge and confidence across cancer pain management domains. In-course competency assessments included knowledge examination, online discussion forum participation, opioid dosage calculation assignment, and small-group-based case study. A mixed-model statistical analysis was used to assess pre-post course change in pain management confidence level. RESULTS: In all, 306 nurses from 89 hospitals in Ontario, Canada, were enrolled in the course; 81.4% returned the precourse survey and 71.9% successfully completed the course. The average confidence level on pain management was low at baseline (57.5%) but improved significantly post-course. In-course competency assessments ranged from 81% to 89%. Mixed-model results showed post-course improvements in confidence levels, independent of sociodemographic background, clinical role, and professional educational level. Nurses with longer years of practice and more cancer cases reported greater confidence. CONCLUSION: A facilitator-led online educational intervention focusing on complex cancer pain management can significantly improve nurses' knowledge, confidence, and skills. Low baseline knowledge among nurses highlights the pressing need for health-care organizations to implement cancer pain management training as an integral part of health-care QI initiative.