|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Deep learning vs conventional learning algorithms for clinical prediction in Crohn's disease: A proof-of-concept study显示文摘BACKGROUND Traditional methods of developing predictive models in inflammatory bowel diseases(IBD)rely on using statistical regression approaches to deriving clinical scores such as the Crohn's disease(CD)activity index.However,traditional approaches are unable to take advantage of more complex data structures such as repeated measurements.Deep learning methods have the potential ability to automatically find and learn complex,hidden relationships between predictive markers and outcomes,but their application to clinical prediction in CD and IBD has not been explored previously.AIM To determine and compare the utility of deep learning with conventional algorithms in predicting response to anti-tumor necrosis factor(anti-TNF)therapy in CD.METHODS This was a retrospective single-center cohort study of all CD patients who commenced anti-TNF therapy(either adalimumab or infliximab)from January 1,2010 to December 31,2015.Remission was defined as a C-reactive protein(CRP)<5 mg/L at 12 mo after anti-TNF commencement.Three supervised learning algorithms were compared:(1)A conventional statistical learning algorithm using multivariable logistic regression on baseline data only;(2)A deep learning algorithm using a feed-forward artificial neural network on baseline data only;and(3)A deep learning algorithm using a recurrent neural network on repeated data.Predictive performance was assessed using area under the receiver operator characteristic curve(AUC)after 10×repeated 5-fold cross-validation.RESULTS A total of 146 patients were included(median age 36 years,48%male).Concomitant therapy at anti-TNF commencement included thiopurines(68%),methotrexate(18%),corticosteroids(44%)and aminosalicylates(33%).After 12 mo,64%had CRP<5 mg/L.The conventional learning algorithm selected the following baseline variables for the predictive model:Complex disease behavior,albumin,monocytes,lymphocytes,mean corpuscular hemoglobin concentration and gamma-glutamyl transferase,and had a cross-validated AUC of 0.659,95%confidence interval(CI):0.562-0.756.A feed-forward artificial neural network using only baseline data demonstrated an AUC of 0.710(95%CI:0.622-0.799;P=0.25 vs conventional).A recurrent neural network using repeated biomarker measurements demonstrated significantly higher AUC compared to the conventional algorithm(0.754,95%CI:0.674-0.834;P=0.036).CONCLUSION Deep learning methods are feasible and have the potential for stronger predictive performance compared to conventional model building methods when applied to predicting remission after anti-TNF therapy in CD. | Danny Con Daniel R van Langenberg Abhinav Vasudevan | 2021 | World Journal of Gastroenterology2021，27，38： | 2 |
| 2 | Type A Behavior,Experience and Salesperson Performance显示文摘 | Bartkus Kenneth R Mark F Peterson Danny N Bellenger | 1989 | Journal of Personal Selling&Sales Management1989，，： | 1 |
| 3 | Multi-delay multi-parametric aerial spin-labeled perfusian MRI in acute is- chemic stroke-comparison with dynamic susceptibility contrast en- hanced perfusion imaging 显示文摘 | Danny JJ Wang /effry R Alger Joe X Qiao | 2013 | Neurolmage: Clinical2013，3，1： | 1 |
| 4 | An Evaluation of Divergent Perspectives on Customer Relationship Management: Towards a Common Understanding of an Emerging Phenomenon显示文摘 | Danny N Bellenger Wesley J Johnston | 2004 | Industrial Marketing Management2004，33，： | 1 |
| 5 | Genome mapping of soybean cyst nematode resistance genes in ‘Peking’, PI9076 and PI88788 using DNA markers 显示文摘 | Concibido V C Lange D A Danny R L | 1997 | Crop Sci1997，37，： | 1 |
| 6 | Short-term human prostate primary xenografts:an in vivo model of human prostate cancer vasculature and angiogenesis显示文摘 | Danny R Gray I Wendy J | 2004 | Cancer Res2004，64，3： | 1 |
| 7 | Using AVL Trees for Fault-Tolerant Group Key Management显示文摘 | Ohad R Kenneth P B Danny D | 2002 | International Journal of Information Security2002，1，2： | 1 |
| 8 | Endogenous biophe- nol, fatty acid and volatile profiles of selected oils 显示文摘 | Zhong Haiyan Danny R Bedgood J | 2007 | Food Chemistry2007，100，4： | 1 |
| 9 | Vairetal and processingef fects on the volatile profile of Auatralian olive oils显示文摘 | Debora T Paul D P Danny R B | 2004 | Food Chemistry2004，，8： | 1 |
| 10 | The local-regionally advanced nasopharyngeal carcinoma jigsaw puzzle:where does the chemotherapy piece fit显示文摘 | Lester J Peters | 2002 | J Clin Oncol2002，20，8： | 1 |
| 11 | Endogenous biophenol, fatty acid and volatile profiles of selected oils显示文摘 | Zhong Haiyan Danny R Bedgood J r | 2007 | Food Chemislry2007，，100： | 1 |
| 12 | Oxidative stressdependent impairment of cardiac-specific transcription factors in experimental diabetes显示文摘 | Aragno M Mastrocola R Medana C Catalano MG Vercellinatto I Danni O | 2006 | Endocrinology2006，147，12： | 1 |
| 13 | Software defect isolation显示文摘 | Faught Danny R Prathibha Tammana | 1998 | High-Performance Computing Users Group1998，，3： | 1 |
| 14 | Bug report:But it's a feature !显示文摘 | Faught Danny R | 2003 | STQE Magazine2003，，3： | 1 |
| 15 | Functional and structural adaptations of skeletal muscle to microgravity显示文摘 | ROBERT H DANNY R JEFFREY J | 2001 | J Exp Biol2001，204，： | 1 |
| 16 | Structural charactefisation and strength evaluation of spray formed ceramic composite near-net shapes 显示文摘 | GOPALAKRISHNAN M V KENNETH M DANNY R | 2003 | Journal of Materials Processing Technology2003，135，： | 1 |
| 17 | Dehydroepiandrosterone modulates nuclear factor-κB activation in hippocampus of diabetic rats显示文摘 | Aragno M Mastrocola R Brignardello E Catalano M Robino G Manti R Parola M Danni O Boccuzzi G | 2002 | Endocrinology2002，143，9： | 1 |
| 18 | Endoge- nous biophenol, fatty acid and volatile profiles of selected oils显示文摘 | ZHANG H Y DANNY R B ANDREA G B | 2007 | Food Chem2007，100，4： | 1 |
| 19 | The control of cell wall single-celled cotton fiber elongation by developmentally reversible gating of plasmodesmata and coordinated expressing of sucrose and K^+ transporters and expansin显示文摘 | Ruan Y L D Danny J L Furbank R T | 2001 | Plant Cell2001，13，： | 1 |
| 20 | Cost-effectiveness of Crohn's disease post-operative care显示文摘AIM: To define the cost-effectiveness of strategies, including endoscopy and immunosuppression, to prevent endoscopic recurrence of Crohn's disease following intestinal resection.METHODS: In the 'POCER' study patients undergoing intestinal resection were treated with post-operative drug therapy. Two thirds were randomized to active care(6 mo colonoscopy and drug intensification for endoscopic recurrence) and one third to drug therapy without early endoscopy. Colonoscopy at 18 mo and faecal calprotectin(FC) measurement were used to assess disease recurrence. Administrative data, chart review and patient questionnaires were collected prospectively over 18 mo.RESULTS: Sixty patients(active care n = 43, standardcare n = 17) were included from one health service. Median total health care cost was $6440 per patient. Active care cost $4824 more than standard care over 18 mo. Medication accounted for 78% of total cost, of which 90% was for adalimumab. Median health care cost was higher for those with endoscopic recurrence compared to those inremission [ $ 26347( IQR 25045-27485) vs $2729(IQR 1182-5215), P < 0.001]. FC to select patients for colonoscopy could reduce cost by $1010 per patient over 18 mo. Active care was associated with 18% decreased endoscopic recurrence, costing $861 for each recurrence prevented. CONCLUSION: Post-operative management strategies are associated with high cost, primarily medication related. Calprotectin use reduces costs. The long term cost-benefit of these strategies remains to be evaluated. | Emily K Wright Michael A Kamm Peter Dr Cruz Amy L Hamilton Kathryn J Ritchie Sally J Bell Steven J Brown William R Connell Paul V Desmond Danny Liew | 2016 | World Journal of Gastroenterology2016，22，14： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员