Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation. Miladinovic, B., Kumar, A., Mhaskar, R., & Djulbegovic, B. BMJ Open, 4(10):e005249, October, 2014. ![Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Objective: To understand how often ‘breakthroughs,’ that is, treatments that significantly improve health outcomes, can be developed. Design: We applied weighted adaptive kernel density estimation to construct the probability density function for observed treatment effects from five publicly funded cohorts and one privately funded group. Data Sources: 820 trials involving 1064 comparisons and enrolling 331 004 patients were conducted by five publicly funded cooperative groups. 40 cancer trials involving 50 comparisons and enrolling a total of 19 889 patients were conducted by GlaxoSmithKline. Results: We calculated that the probability of detecting treatment with large effects is 10% (5–25%), and that the probability of detecting treatment with very large treatment effects is 2% (0.3–10%). Researchers themselves judged that they discovered a new, breakthrough intervention in 16% of trials. Conclusions: We propose these figures as the benchmarks against which future development of ‘breakthrough’ treatments should be measured.
@article{miladinovic_benchmarks_2014-1,
title = {Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation},
volume = {4},
issn = {2044-6055, 2044-6055},
shorttitle = {Benchmarks for detecting ‘breakthroughs’ in clinical trials},
url = {https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2014-005249},
doi = {10.1136/bmjopen-2014-005249},
abstract = {Objective: To understand how often ‘breakthroughs,’ that is, treatments that significantly improve health outcomes, can be developed. Design: We applied weighted adaptive kernel density estimation to construct the probability density function for observed treatment effects from five publicly funded cohorts and one privately funded group. Data Sources: 820 trials involving 1064 comparisons and enrolling 331 004 patients were conducted by five publicly funded cooperative groups. 40 cancer trials involving 50 comparisons and enrolling a total of 19 889 patients were conducted by GlaxoSmithKline. Results: We calculated that the probability of detecting treatment with large effects is 10\% (5–25\%), and that the probability of detecting treatment with very large treatment effects is 2\% (0.3–10\%). Researchers themselves judged that they discovered a new, breakthrough intervention in 16\% of trials. Conclusions: We propose these figures as the benchmarks against which future development of ‘breakthrough’ treatments should be measured.},
language = {en},
number = {10},
urldate = {2021-04-28},
journal = {BMJ Open},
author = {Miladinovic, Branko and Kumar, Ambuj and Mhaskar, Rahul and Djulbegovic, Benjamin},
month = oct,
year = {2014},
pages = {e005249},
file = {Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:/Users/neil.hawkins/Zotero/storage/VWV2AG9K/Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:application/pdf},
}
Downloads: 0
{"_id":"Xji3yPfeeKWsXASse","bibbaseid":"miladinovic-kumar-mhaskar-djulbegovic-benchmarksfordetectingbreakthroughsinclinicaltrialsempiricalassessmentoftheprobabilityoflargetreatmenteffectsusingkerneldensityestimation-2014","downloads":0,"creationDate":"2017-11-23T19:05:20.677Z","title":"Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation","author_short":["Miladinovic, B.","Kumar, A.","Mhaskar, R.","Djulbegovic, B."],"year":2014,"bibtype":"article","biburl":"https://bibbase.org/f/FfNE7kWA6pCvwcJZF/myPubs.bib","bibdata":{"bibtype":"article","type":"article","title":"Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation","volume":"4","issn":"2044-6055, 2044-6055","shorttitle":"Benchmarks for detecting ‘breakthroughs’ in clinical trials","url":"https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2014-005249","doi":"10.1136/bmjopen-2014-005249","abstract":"Objective: To understand how often ‘breakthroughs,’ that is, treatments that significantly improve health outcomes, can be developed. Design: We applied weighted adaptive kernel density estimation to construct the probability density function for observed treatment effects from five publicly funded cohorts and one privately funded group. Data Sources: 820 trials involving 1064 comparisons and enrolling 331 004 patients were conducted by five publicly funded cooperative groups. 40 cancer trials involving 50 comparisons and enrolling a total of 19 889 patients were conducted by GlaxoSmithKline. Results: We calculated that the probability of detecting treatment with large effects is 10% (5–25%), and that the probability of detecting treatment with very large treatment effects is 2% (0.3–10%). Researchers themselves judged that they discovered a new, breakthrough intervention in 16% of trials. Conclusions: We propose these figures as the benchmarks against which future development of ‘breakthrough’ treatments should be measured.","language":"en","number":"10","urldate":"2021-04-28","journal":"BMJ Open","author":[{"propositions":[],"lastnames":["Miladinovic"],"firstnames":["Branko"],"suffixes":[]},{"propositions":[],"lastnames":["Kumar"],"firstnames":["Ambuj"],"suffixes":[]},{"propositions":[],"lastnames":["Mhaskar"],"firstnames":["Rahul"],"suffixes":[]},{"propositions":[],"lastnames":["Djulbegovic"],"firstnames":["Benjamin"],"suffixes":[]}],"month":"October","year":"2014","pages":"e005249","file":"Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:/Users/neil.hawkins/Zotero/storage/VWV2AG9K/Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:application/pdf","bibtex":"@article{miladinovic_benchmarks_2014-1,\n\ttitle = {Benchmarks for detecting ‘breakthroughs’ in clinical trials: empirical assessment of the probability of large treatment effects using kernel density estimation},\n\tvolume = {4},\n\tissn = {2044-6055, 2044-6055},\n\tshorttitle = {Benchmarks for detecting ‘breakthroughs’ in clinical trials},\n\turl = {https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2014-005249},\n\tdoi = {10.1136/bmjopen-2014-005249},\n\tabstract = {Objective: To understand how often ‘breakthroughs,’ that is, treatments that significantly improve health outcomes, can be developed. Design: We applied weighted adaptive kernel density estimation to construct the probability density function for observed treatment effects from five publicly funded cohorts and one privately funded group. Data Sources: 820 trials involving 1064 comparisons and enrolling 331 004 patients were conducted by five publicly funded cooperative groups. 40 cancer trials involving 50 comparisons and enrolling a total of 19 889 patients were conducted by GlaxoSmithKline. Results: We calculated that the probability of detecting treatment with large effects is 10\\% (5–25\\%), and that the probability of detecting treatment with very large treatment effects is 2\\% (0.3–10\\%). Researchers themselves judged that they discovered a new, breakthrough intervention in 16\\% of trials. Conclusions: We propose these figures as the benchmarks against which future development of ‘breakthrough’ treatments should be measured.},\n\tlanguage = {en},\n\tnumber = {10},\n\turldate = {2021-04-28},\n\tjournal = {BMJ Open},\n\tauthor = {Miladinovic, Branko and Kumar, Ambuj and Mhaskar, Rahul and Djulbegovic, Benjamin},\n\tmonth = oct,\n\tyear = {2014},\n\tpages = {e005249},\n\tfile = {Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:/Users/neil.hawkins/Zotero/storage/VWV2AG9K/Miladinovic et al. - 2014 - Benchmarks for detecting ‘breakthroughs’ in clinic.pdf:application/pdf},\n}\n\n","author_short":["Miladinovic, B.","Kumar, A.","Mhaskar, R.","Djulbegovic, B."],"bibbaseid":"miladinovic-kumar-mhaskar-djulbegovic-benchmarksfordetectingbreakthroughsinclinicaltrialsempiricalassessmentoftheprobabilityoflargetreatmenteffectsusingkerneldensityestimation-2014","role":"author","urls":{"Paper":"https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2014-005249"},"metadata":{"authorlinks":{}}},"search_terms":["benchmarks","detecting","breakthroughs","clinical","trials","empirical","assessment","probability","large","treatment","effects","using","kernel","density","estimation","miladinovic","kumar","mhaskar","djulbegovic"],"keywords":[],"authorIDs":[],"dataSources":["ZaHtWavQhcwZqKLNF","iRRNaRs6FkffgErta","v8uQmZsBpiqycmskv"]}