| 1. |
|
|
| 2. |
|
|
| 3. |
- Salim, Mattie, et al.
(författare)
-
External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms
- 2020
-
Ingår i: JAMA Oncology. - : American Medical Association (AMA). - 2374-2437 .- 2374-2445. ; 6:10, s. 1581-
-
Tidskriftsartikel (refereegranskat)abstract
- Importance: A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening. Objective: To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. Design, Setting, and Participants: This retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). Main Outcomes and Measures: Positive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). Results: The median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. Conclusions and Relevance: To our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers.
|
|
| 4. |
|
|
| 5. |
- Yang, Jae Jeong, et al.
(författare)
-
Association of Dietary Fiber and Yogurt Consumption With Lung Cancer Risk : A Pooled Analysis
- 2020
-
Ingår i: JAMA Oncology. - : American Medical Association. - 2374-2437 .- 2374-2445. ; 6:2
-
Tidskriftsartikel (refereegranskat)abstract
- Importance: Dietary fiber (the main source of prebiotics) and yogurt (a probiotic food) confer various health benefits via modulating the gut microbiota and metabolic pathways. However, their associations with lung cancer risk have not been well investigated.Objective: To evaluate the individual and joint associations of dietary fiber and yogurt consumption with lung cancer risk and to assess the potential effect modification of the associations by lifestyle and other dietary factors.Design, Setting, and Participants: This pooled analysis included 10 prospective cohorts involving 1 445 850 adults from studies that were conducted in the United States, Europe, and Asia. Data analyses were performed between November 2017 and February 2019. Using harmonized individual participant data, hazard ratios and 95% confidence intervals for lung cancer risk associated with dietary fiber and yogurt intakes were estimated for each cohort by Cox regression and pooled using random-effects meta-analysis. Participants who had a history of cancer at enrollment or developed any cancer, died, or were lost to follow-up within 2 years after enrollment were excluded.Exposures: Dietary fiber intake and yogurt consumption measured by validated instruments.Main Outcomes and Measures: Incident lung cancer, subclassified by histologic type (eg, adenocarcinoma, squamous cell carcinoma, and small cell carcinoma).Results: The analytic sample included 627 988 men, with a mean (SD) age of 57.9 (9.0) years, and 817 862 women, with a mean (SD) age of 54.8 (9.7) years. During a median follow-up of 8.6 years, 18 822 incident lung cancer cases were documented. Both fiber and yogurt intakes were inversely associated with lung cancer risk after adjustment for status and pack-years of smoking and other lung cancer risk factors: hazard ratio, 0.83 (95% CI, 0.76-0.91) for the highest vs lowest quintile of fiber intake; and hazard ratio, 0.81 (95% CI, 0.76-0.87) for high vs no yogurt consumption. The fiber or yogurt associations with lung cancer were significant in never smokers and were consistently observed across sex, race/ethnicity, and tumor histologic type. When considered jointly, high yogurt consumption with the highest quintile of fiber intake showed more than 30% reduced risk of lung cancer than nonyogurt consumption with the lowest quintile of fiber intake (hazard ratio, 0.67 [95% CI, 0.61-0.73] in total study populations; hazard ratio 0.69 [95% CI, 0.54-0.89] in never smokers), suggesting potential synergism.Conclusions and Relevance: Dietary fiber and yogurt consumption was associated with reduced risk of lung cancer after adjusting for known risk factors and among never smokers. Our findings suggest a potential protective role of prebiotics and probiotics against lung carcinogenesis.
|
|
| 6. |
- Joensuu, Heikki, et al.
(författare)
-
Survival Outcomes Associated with 3 Years vs 1 Year of Adjuvant Imatinib for Patients with High-Risk Gastrointestinal Stromal Tumors : An Analysis of a Randomized Clinical Trial after 10-Year Follow-up
- 2020
-
Ingår i: JAMA Oncology. - : American Medical Association (AMA). - 2374-2437. ; 6:8, s. 1241-1246
-
Tidskriftsartikel (refereegranskat)abstract
- Importance: Adjuvant imatinib is associated with improved recurrence-free survival (RFS) when administered after surgery to patients with operable gastrointestinal stromal tumor (GIST), but its influence on overall survival (OS) has remained uncertain. Objective: To evaluate the effect of adjuvant imatinib on OS of patients who have a high estimated risk for GIST recurrence after macroscopically complete surgery. Design, Setting, and Participants: In this open-label, randomized (1:1), multicenter phase 3 clinical trial conducted in Finland, Germany, Norway, and Sweden, 400 patients who had undergone macroscopically complete surgery for GIST with a high estimated risk for recurrence according to the modified National Institutes of Health Consensus Criteria were enrolled between February 2004 and September 2008. Data for this follow-up analysis were analyzed from September to November, 2019. Interventions: Imatinib 400 mg/d administered orally for either 12 months or 36 months after surgery. Main Outcomes And Measures: The primary end point was RFS; the secondary objectives included OS and treatment safety. Results: The intention-to-treat cohort consisted of 397 patients (12-month group, 199; 36-month group, 198; 201 men and 196 women; median [IQR] age, 62 (51-69) years and 60 (51-67) years, during a median follow-up time of 119 months after the date of randomization, 194 RFS events and 96 OS events were recorded in the intention-to-treat population. Five-year and 10-year RFS was 71.4% and 52.5%, respectively, in the 36-month group and 53.0% and 41.8% in the 12-month group (hazard ratio [HR], 0.66; 95% CI, 0.49-0.87; P =.003). In the 36-month group, 5-year OS and 10-year OS rates were 92.0% and 79.0%, respectively, and in the 12-month group 85.5% and 65.3% (HR, 0.55; 95% CI, 0.37-0.83; P =.004). The results were similar in the efficacy population, from which 15 patients who did not have GIST in central pathology review and 24 patients who had intra-abdominal metastases removed at surgery were excluded (36-month group, 10-year OS 81.6%; 12-month group, 66.8%; HR, 0.50; 95% CI, 0.32-0.80; P =.003). No new safety signals were detected. Conclusions and Relevance: Three years of adjuvant imatinib is superior in efficacy compared with 1 year of imatinib. Approximately 50% of deaths may be avoided during the first 10 years of follow-up after surgery with longer adjuvant imatinib treatment. Trial Registration: ClinicalTrials.gov Identifier: NCT00116935.
|
|
| 7. |
|
|
