Artificial Intelligence Algorithm for Subclinical Breast Cancer Detection.

Importance: Early breast cancer detection is associated with lower morbidity and mortality. Objective: To examine whether a commercial artificial intelligence (AI) algorithm for breast cancer detection could estimate the development of future cancer. Design, Setting, and Participants: This retrospective cohort study of 116 495 women aged 50 to 69 years with no prior history of breast cancer before they underwent at least 3 consecutive biennial screening examinations used scores from an AI algorithm (INSIGHT MMG, version 1.1.7.2; Lunit Inc; used September 28, 2022, to April 5, 2023) for breast cancer detection and screening data from multiple, consecutive rounds of mammography performed from September 13, 2004, to December 21, 2018, at 9 breast centers in Norway. The statistical analyses were performed from September 2023 to August 2024. Exposure: Artificial intelligence algorithm score indicating suspicion for the presence of breast cancer. The algorithm provided a continuous cancer detection score for each examination ranging from 0 to 100, with increasing values indicating a higher likelihood of cancer being present on the current mammogram. Main Outcomes and Measures: Maximum AI algorithm score for cancer detection and absolute difference in score among breasts of women developing screening-detected cancer, women with interval cancer, and women who screened negative. Results: The mean (SD) age at the first study round was 58.5 (4.5) years for 1265 women with screening-detected cancer in the third round, 57.4 (4.6) years for 342 women with interval cancer after 3 negative screening rounds, and 56.4 (4.9) years for 116 495 women without breast cancer all 3 screening rounds. The mean (SD) absolute differences in AI scores among breasts of women developing screening-detected cancer were 21.3 (28.1) at the first study round, 30.7 (32.5) at the second study round, and 79.0 (28.9) at the third study round. The mean (SD) differences prior to interval cancer were 19.7 (27.0) at the first study round, 21.0 (27.7) at the second study round, and 34.0 (33.6) at the third study round. The mean (SD) differences among women who did not develop breast cancer were 9.9 (17.5) at the first study round, 9.6 (17.4) at the second study round, and 9.3 (17.3) at the third study round. Areas under the receiver operating characteristic curve for the absolute difference were 0.63 (95% CI, 0.61-0.65) at the first study round, 0.72 (95% CI, 0.71-0.74) at the second study round, and 0.96 (95% CI, 0.95-0.96) at the third study round for screening-detected cancer and 0.64 (95% CI, 0.61-0.67) at the first study round, 0.65 (95% CI, 0.62-0.68) at the second study round, and 0.77 (95% CI, 0.74-0.79) at the third study round for interval cancers. Conclusions and Relevance: In this retrospective cohort study of women undergoing screening mammography, mean absolute AI scores were higher for breasts developing vs not developing cancer 4 to 6 years before their eventual detection. These findings suggest that commercial AI algorithms developed for breast cancer detection may identify women at high risk of a future breast cancer, offering a pathway for personalized screening approaches that can lead to earlier cancer diagnosis.

Breast cancer-specific survival among immigrants and non-immigrants invited to BreastScreen Norway.

Introduction: We have previously shown that immigrants have lower attendance in BreastScreen Norway than non-immigrants and that non-Western immigrants have lower incidence of breast cancer, but more advanced disease. Purpose: To compare breast cancer-specific survival for immigrants versus non-immigrants diagnosed with screen-detected or symptomatic breast cancer. Material and methods: We analyzed data from 28,320 women aged 50-69 diagnosed with breast cancer after being invited to BreastScreen Norway. We divided women into three groups; non-immigrants, immigrants from Western countries and immigrants from non-Western countries. We stratified our analyses according to detection mode (screen-detected breast cancer, interval cancer and cancer detected outside screening), and used cox regression to model the association between immigrants/non-immigrants and time to breast cancer death. Results: Among screen-detected breast cancers, 28.7% were histologic grade 3 among immigrants from non-Western countries compared to 21.3% among non-immigrants. Interval cancers and cancers detected outside screening had larger tumor diameter and a higher percentage were histologic grade 3 and lymph node positive among immigrants from non-Western countries compared to non-immigrants. Hazard ratio (95% confidence interval) adjusted for age and year of diagnosis for time to breast cancer death compared to non-immigrants was 0.70 (0.39-1.27) for immigrants from Western countries and 0.52 (0.23-1.17) for immigrants from non-Western countries. Conclusion: Despite more advanced histopathological tumor characteristics among immigrants from non-Western countries compared to non-immigrants, we did not observe statistically significant differences in breast-cancer specific survival between the two groups. Keeping in mind the low number of breast cancer deaths and possible overestimation of survival among immigrants, this might imply that equity in outcome can be achieved through adequate follow-up and treatment despite inequal access.

All-cause mortality and hospital admissions for nursing home residents during the COVID-19 pandemic: a Norwegian register-based cohort study.

BACKGROUND: This paper investigates the consequences of the COVID-19 pandemic on mortality and hospitalization among nursing home residents in Norway. While existing evidence shows that nursing home residents were overrepresented among COVID-19-related deaths, suggesting inadequate protection measures, this study argues that the observed overrepresentation in mortality and hospitalization may partly stem from the inherent frailty of this demographic. Using nationwide administrative data, we assessed excess deaths and hospitalization by comparing pandemic-era rates to those of a pre-pandemic cohort. METHODS: We compared mortality and hospitalization rates between a pandemic cohort of nursing home residents as of September 2019 (N = 30,052), and a pre-pandemic cohort as of September 2017 (N = 30,429). Both cohorts were followed monthly for two years, beginning in September 2019 and 2017, respectively. This analysis was conducted at the national level and separately for nursing home residents in areas with low, medium, and high SARS-CoV-2 community transmission. Event studies and difference-in-difference models allowed us to separate the impact of the pandemic on mortality and hospitalization from secular and seasonal changes. RESULTS: The pandemic cohort experienced a non-significant 0.07 percentage points (95% confidence interval (CI): - 0.081 to 0.221) increase in all-cause mortality during the 18 months following pandemic onset, compared to the pre-pandemic cohort. Moreover, our findings indicate a substantial reduction in hospitalizations of 0.27 percentage points (95% CI: - 0.464 to - 0.135) and a non-significant decrease of 0.80 percentage points (95% CI: - 2.529 to 0.929) in the proportion of nursing home residents hospitalized before death. The effect on mortality remained consistent across regions with both high and low levels of SARS-CoV-2 community transmission. CONCLUSIONS: Our findings indicate no clear evidence of excess all-cause mortality in Norway during the pandemic, neither nationally nor in areas with high infection rates. This suggests that early implementation of nationwide and nursing home-specific infection control measures during the pandemic effectively protected nursing home residents. Furthermore, our results revealed a decrease in hospitalizations, both overall and prior to death, suggesting that nursing homes adhered to national guidelines promoting on-site treatment for residents.

Associations between psychiatric comorbid disorders and executive dysfunctions in hypocretin-1 deficient pediatric narcolepsy type1.

OBJECTIVE/BACKGROUND: Psychiatric symptoms and cognitive deficits add significantly to impairment in academic achievement and quality of life in patients with narcolepsy. The primary aim of this study was to evaluate the prevalence of psychiatric disorders and executive dysfunctions, secondly to explore the association between psychiatric comorbidity, executive dysfunctions, subjective and objective sleep measures, and severity of cerebrospinal fluid (CSF) hypocretin-1 deficiency in pediatric narcolepsy type 1 (PNT1). PATIENTS/METHODS: Cross-sectional study of 59 consecutively included PNT1 patients (age: 6-20 years; 34:25 girls: boys; 54/59 H1N1 (Pandemrix®)-vaccinated). Core narcolepsy symptoms including subjective sleepiness, polysomnography and multiple sleep latency test results, CSF hypocretin-1 levels, psychiatric disorders (by semistructured diagnostic interview Kaufmann Schedule for Affective Disorders and Schizophrenia Present and Lifetime version (KSADS)), and executive dysfunction (by Behavior Rating of Executive Function (BRIEF)) were assessed. RESULTS: 52.5% of the patients had one or more psychiatric comorbid disorder, and 64.7% had executive dysfunction in a clinically relevant range, with no sex difference in prevalence, while older age was associated with poorer executive function (p=0.013). Having any psychiatric comorbid disorder was associated with poorer executive functions (p=0.001). CSF hypocretin-1 deficiency severity was significantly associated with presence of psychiatric comorbidity (p=0.022) and poorer executive functions (p=0.030), and poorer executive functions was associated with subjective sleepiness (p=0.009). CONCLUSIONS: The high occurrence of, and association between, psychiatric comorbidity and executive dysfunction underlines the importance of close attention to both these comorbidities in clinical care of NT1.