| 1. |
- Sharma, R., et al.
(författare)
-
Global, regional, and national burden of colorectal cancer and its risk factors, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019
- 2022
-
Ingår i: Lancet Gastroenterology & Hepatology. - : Elsevier BV. - 2468-1253. ; 7:7, s. 627-647
-
Tidskriftsartikel (refereegranskat)abstract
- Background Colorectal cancer is the third leading cause of cancer deaths worldwide. Given the recent increasing trends in colorectal cancer incidence globally, up-to-date information on the colorectal cancer burden could guide screening, early detection, and treatment strategies, and help effectively allocate resources. We examined the temporal patterns of the global, regional, and national burden of colorectal cancer and its risk factors in 204 countries and territories across the past three decades. Methods Estimates of incidence, mortality, and disability-adjusted life years (DALYs) for colorectal cancer were generated as a part of the Global Burden of Diseases, Injuries and Risk Factors Study (GBD) 2019 by age, sex, and geographical location for the period 1990-2019. Mortality estimates were produced using the cause of death ensemble model. We also calculated DALYs attributable to risk factors that had evidence of causation with colorectal cancer. Findings Globally, between 1990 and 2019, colorectal cancer incident cases more than doubled, from 842 098 (95% uncertainty interval [UI] 810 408-868 574) to 2.17 million (2.00-2.34), and deaths increased from 518 126 (493 682-537 877) to 1.09 million (1.02-1.15). The global age-standardised incidence rate increased from 22.2 (95% UI 21.3-23.0) per 100 000 to 26.7 (24.6-28.9) per 100 000, whereas the age-standardised mortality rate decreased from 14.3 (13.5-14.9) per 100 000 to 13.7 (12.6-14.5) per 100 000 and the age-standardised DALY rate decreased from 308.5 (294.7-320.7) per 100 000 to 295.5 (275.2-313.0) per 100 000 from 1990 through 2019. Taiwan (province of China; 62.0 [48.9-80.0] per 100 000), Monaco (60.7 [48.5-73.6] per 100 000), and Andorra (56.6 [42.8-71.9] per 100 000) had the highest age-standardised incidence rates, while Greenland (31.4 [26.0-37.1] per 100 000), Brunei (30.3 [26.6-34.1] per 100 000), and Hungary (28.6 [23.6-34.0] per 100 000) had the highest age-standardised mortality rates. From 1990 through 2019, a substantial rise in incidence rates was observed in younger adults (age <50 years), particularly in high Socio-demographic Index (SDI) countries. Globally, a diet low in milk (15.6%), smoking (13.3%), a diet low in calcium (12.9%), and alcohol use (9.9%) were the main contributors to colorectal cancer DALYs in 2019. Interpretation The increase in incidence rates in people younger than 50 years requires vigilance from researchers, clinicians, and policy makers and a possible reconsideration of screening guidelines. The fast-rising burden in low SDI and middle SDI countries in Asia and Africa calls for colorectal cancer prevention approaches, greater awareness, and cost-effective screening and therapeutic options in these regions. Copyright (C) 2022 The Author(s). Published by Elsevier Ltd.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Shiri, I, et al.
(författare)
-
High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms
- 2022
-
Ingår i: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 12:1, s. 14817-
-
Tidskriftsartikel (refereegranskat)abstract
- We aimed to construct a prediction model based on computed tomography (CT) radiomics features to classify COVID-19 patients into severe-, moderate-, mild-, and non-pneumonic. A total of 1110 patients were studied from a publicly available dataset with 4-class severity scoring performed by a radiologist (based on CT images and clinical features). The entire lungs were segmented and followed by resizing, bin discretization and radiomic features extraction. We utilized two feature selection algorithms, namely bagging random forest (BRF) and multivariate adaptive regression splines (MARS), each coupled to a classifier, namely multinomial logistic regression (MLR), to construct multiclass classification models. The dataset was divided into 50% (555 samples), 20% (223 samples), and 30% (332 samples) for training, validation, and untouched test datasets, respectively. Subsequently, nested cross-validation was performed on train/validation to select the features and tune the models. All predictive power indices were reported based on the testing set. The performance of multi-class models was assessed using precision, recall, F1-score, and accuracy based on the 4 × 4 confusion matrices. In addition, the areas under the receiver operating characteristic curves (AUCs) for multi-class classifications were calculated and compared for both models. Using BRF, 23 radiomic features were selected, 11 from first-order, 9 from GLCM, 1 GLRLM, 1 from GLDM, and 1 from shape. Ten features were selected using the MARS algorithm, namely 3 from first-order, 1 from GLDM, 1 from GLRLM, 1 from GLSZM, 1 from shape, and 3 from GLCM features. The mean absolute deviation, skewness, and variance from first-order and flatness from shape, and cluster prominence from GLCM features and Gray Level Non Uniformity Normalize from GLRLM were selected by both BRF and MARS algorithms. All selected features by BRF or MARS were significantly associated with four-class outcomes as assessed within MLR (All p values < 0.05). BRF + MLR and MARS + MLR resulted in pseudo-R2 prediction performances of 0.305 and 0.253, respectively. Meanwhile, there was a significant difference between the feature selection models when using a likelihood ratio test (p value = 0.046). Based on confusion matrices for BRF + MLR and MARS + MLR algorithms, the precision was 0.856 and 0.728, the recall was 0.852 and 0.722, whereas the accuracy was 0.921 and 0.861, respectively. AUCs (95% CI) for multi-class classification were 0.846 (0.805–0.887) and 0.807 (0.752–0.861) for BRF + MLR and MARS + MLR algorithms, respectively. Our models based on the utilization of radiomic features, coupled with machine learning were able to accurately classify patients according to the severity of pneumonia, thus highlighting the potential of this emerging paradigm in the prognostication and management of COVID-19 patients.
|
|
| 6. |
|
|
