| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Haenssle, H A, et al.
(författare)
-
Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.
- 2018
-
Ingår i: Annals of Oncology. - : Elsevier BV. - 1569-8041 .- 0923-7534. ; 29:8, s. 1836-1842
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking.Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge.In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P=0.19) and specificity to 75.7% (±11.7%, P<0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P<0.01) and level-II (75.7%, P<0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P<0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge.For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification.This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).
|
|
| 5. |
- Kappos, Ludwig, et al.
(författare)
-
Siponimod versus placebo in secondary progressive multiple sclerosis (EXPAND): a double-blind, randomised, phase 3 study
- 2018
-
Ingår i: The Lancet. - 0140-6736 .- 1474-547X. ; 391, s. 1263-1273
-
Tidskriftsartikel (refereegranskat)abstract
- © 2018 Elsevier Ltd Background: No treatment has consistently shown efficacy in slowing disability progression in patients with secondary progressive multiple sclerosis (SPMS). We assessed the effect of siponimod, a selective sphingosine 1-phosphate (S1P) receptor 1,5 modulator, on disability progression in patients with SPMS. Methods: This event-driven and exposure-driven, double-blind, phase 3 trial was done at 292 hospital clinics and specialised multiple sclerosis centres in 31 countries. Using interactive response technology to assign numbers linked to treatme nt arms, patients (age 18–60 years) with SPMS and an Expanded Disability Status Scale score of 3·0–6·5 were randomly assigned (2:1) to once daily oral siponimod 2 mg or placebo for up to 3 years or until the occurrence of a prespecified number of confirmed disability progression (CDP) events. The primary endpoint was time to 3-month CDP. Efficacy was assessed for the full analysis set (ie, all randomly assigned and treated patients); safety was assessed for the safety set. This trial is registered with ClinicalTrials.gov, number NCT01665144. Findings: 1651 patients were randomly assigned between Feb 5, 2013, and June 2, 2015 (1105 to the siponimod group, and 546 to the placebo group). One patient did not sign the consent form, and five patients did not receive study drug, all of whom were in the siponimod group. 1645 patients were included in the analyses (1099 in the siponimod group and 546 in the placebo). At baseline, the mean time since first multiple sclerosis symptoms was 16·8 years (SD 8·3), and the mean time since conversion to SPMS was 3·8 years (SD 3·5); 1055 (64%) patients had not relapsed in the previous 2 years, and 918 (56%) of 1651 needed walking assistance. 903 (82%) patients receiving siponimod and 424 (78%) patients receiving placebo completed the study. 288 (26%) of 1096 patients receiving siponimod and 173 (32%) of 545 patients receiving placebo had 3-month CDP (hazard ratio 0·79, 95% CI 0·65–0·95; relative risk reduction 21%; p=0·013). Adverse events occurred in 975 (89%) of 1099 patients receiving siponimod versus 445 (82%) of 546 patients receiving placebo; serious adverse events were reported for 197 (18%) patients in the siponimod group versus 83 (15%) patients in the placebo group. Lymphopenia, increased liver transaminase concentration, bradycardia and bradyarrhythmia at treatment initiation, macular oedema, hypertension, varicella zoster reactivation, and convulsions occurred more frequently with siponimod than with placebo. Initial dose titration mitigated cardiac first-dose effects. Frequencies of infections, malignancies, and fatalities did not differ between groups. Interpretation: Siponimod reduced the risk of disability progression with a safety profile similar to that of other S1P modulators and is likely to be a useful treatment for SPMS. Funding: Novartis Pharma AG.
|
|
