Role of sex in lung cancer risk prediction based on single low-dose chest computed tomography.

A validated open-source deep-learning algorithm called Sybil can accurately predict long-term lung cancer risk from a single low-dose chest computed tomography (LDCT). However, Sybil was trained on a majority-male cohort. Use of artificial intelligence algorithms trained on imbalanced cohorts may lead to inequitable outcomes in real-world settings. We aimed to study whether Sybil predicts lung cancer risk equally regardless of sex. We analyzed 10,573 LDCTs from 6127 consecutive lung cancer screening participants across a health system between 2015 and 2021. Sybil achieved AUCs of 0.89 (95% CI: 0.85-0.93) for females and 0.89 (95% CI: 0.85-0.94) for males at 1 year, p = 0.92. At 6 years, the AUC was 0.87 (95% CI: 0.83-0.93) for females and 0.79 (95% CI: 0.72-0.86) for males, p = 0.01. In conclusion, Sybil can accurately predict future lung cancer risk in females and males in a real-world setting and performs better in females than in males for predicting 6-year lung cancer risk.

Patients' experiences undergoing breast evaluation in Rwanda's Women's Cancer Early Detection Program.

PURPOSE: There is urgent need for interventions to facilitate earlier diagnosis of breast cancer in low- and middle-income countries where mammography screening is not widely available. Understanding patients' experiences with early detection efforts, whether they are ultimately diagnosed with cancer or benign disease, is critical to optimize interventions and maximize community engagement. We sought to understand the experiences of patients undergoing breast evaluation in Rwanda's Women's Cancer Early Detection Program (WCEDP). METHODS: We conducted in-person semi-structured interviews with 30 patients in two districts of Rwanda participating in the WCEDP. Patients represented a range of ages and both benign and malignant diagnoses. Interviews were recorded, transcribed, translated, and thematically analyzed. RESULTS: Participants identified facilitators and barriers of timely care along the breast evaluation pathway. Community awareness initiatives were facilitators to care-seeking, while persistent myths and stigma about cancer were barriers. Participants valued clear clinician-patient communication and emotional support from clinicians and peers. Poverty was a major barrier for participants who described difficulty paying for transport, insurance premiums, and other direct and indirect costs of hospital referrals in particular. COVID-19 lockdowns caused delays for referred patients. Although false-positive clinical breast exams conferred financial and emotional burdens, participants nonetheless voiced appreciation for their experience and felt empowered to monitor their own breast health and share knowledge with others. CONCLUSION: Rwandan women experienced both benefits and burdens as they underwent breast evaluation. Enthusiasm for participation was not reduced by the experience of a false-positive result. Reducing financial, logistical and emotional burdens of the breast diagnostic pathway through patient navigation, peer support and decentralization of diagnostic services could improve patients' experience.

Implementation research: including breast examinations in a cervical cancer screening programme, Rwanda.

Objective: To evaluate whether integrating breast and cervical cancer screening in Rwanda's Women's Cancer Early Detection Program led to early breast cancer diagnoses in asymptomatic women. Methods: Launched in three districts in 2018-2019, the early detection programme offered clinical breast examination screening for all women receiving cervical cancer screening, and diagnostic breast examination for women with breast cancer symptoms. Women with abnormal breast examinations were referred to district hospitals and then to referral hospitals if needed. We examined how often clinics were held, patient volumes and number of referrals. We also examined intervals between referrals and visits to the next care level and, among women diagnosed with cancer, their initial reasons for seeking care. Findings: Health centres held clinics > 68% of the weeks. Overall, 9763 women received cervical cancer screening and clinical breast examination and 7616 received breast examination alone. Of 585 women referred from health centres, 436 (74.5%) visited the district hospital after a median of 9 days (interquartile range, IQR: 3-19). Of 200 women referred to referral hospitals, 179 (89.5%) attended after a median of 11 days (IQR: 4-18). Of 29 women diagnosed with breast cancer, 19 were ≥ 50 years and 23 had stage III or stage IV disease. All women with breast cancer whose reasons for seeking care were known (23 women) had experienced breast cancer symptoms. Conclusion: In the short-term, integrating clinical breast examination with cervical cancer screening was not associated with detection of early-stage breast cancer among asymptomatic women. Priority should be given to encouraging women to seek timely care for symptoms.

Integrating Breast Cancer Early Detection Into a Resource-Constrained Primary Health Care System: Health Care Workers' Experiences in Rwanda.

PURPOSE: There is limited evidence to guide incorporation of breast cancer early detection into resource-constrained health systems where mammography screening is not yet available. To inform such strategies, we sought to understand health care workers' perspectives on a breast cancer early detection initiative integrated into community, primary, and secondary levels of care in Rwanda. METHODS: We conducted a qualitative study using semistructured interviews with 33 community health workers, clinicians, and administrators at health facilities participating in the Women's Cancer Early Detection Program (WCEDP), through which women received clinical breast examination if they were receiving cervical cancer screening, or had breast concerns. Through thematic analysis, we identified dynamics and patterns associated with successes and challenges of the program's breast health services. RESULTS: Successes and challenges identified by participants corresponded with the community- and primary care-based steps of cancer early diagnosis identified by the WHO. Regarding step 1 (community awareness/access), participants noted increases in awareness and care-seeking. Challenges included difficulty overcoming stigma and engaging older women. Regarding step 2 (clinical evaluation), all participants described increased breast health knowledge, skills, and confidence. Integrating the WCEDP with other services was challenging because of inadequate staffing; offering WCEDP services on a designated day/week had advantages and disadvantages. Although participants appreciated WCEDP referral mechanisms, they desired more communication from referral facilities. Patients' poverty was the most consistently identified impediment to referral completion. CONCLUSION: Rwandan health care workers identified real-world successes and challenges of implementing principles of early cancer diagnosis for breast cancer early detection. Future interventions should focus on engagement of older women, community awareness, patient socioeconomic support, and optimizing integration into primary care.