The Assessment of Antiepileptic Drugs: Randomized Controlled Trials, Regulation, Clinical Guidelines and Anecdotal Assessment

10.2196/22422 ◽  
2020 ◽  
Vol 22 (12) ◽  
pp. e22422
Author(s):  
Tomohide Yamada ◽  
Daisuke Yoneoka ◽  
Yuta Hiraike ◽  
Kimihiro Hino ◽  
Hiroyoshi Toyoshiba ◽  
...  

Background Performing systematic reviews is a time-consuming and resource-intensive process. Objective We investigated whether a machine learning system could perform systematic reviews more efficiently. Methods All systematic reviews and meta-analyses of interventional randomized controlled trials cited in recent clinical guidelines from the American Diabetes Association, American College of Cardiology, American Heart Association (2 guidelines), and American Stroke Association were assessed. After reproducing the primary screening data set according to the published search strategy of each, we extracted correct articles (those actually reviewed) and incorrect articles (those not reviewed) from the data set. These 2 sets of articles were used to train a neural network–based artificial intelligence engine (Concept Encoder, Fronteo Inc). The primary endpoint was work saved over sampling at 95% recall (WSS@95%). Results Among 145 candidate reviews of randomized controlled trials, 8 reviews fulfilled the inclusion criteria. For these 8 reviews, the machine learning system significantly reduced the literature screening workload by at least 6-fold versus that of manual screening based on WSS@95%. When machine learning was initiated using 2 correct articles that were randomly selected by a researcher, a 10-fold reduction in workload was achieved versus that of manual screening based on the WSS@95% value, with high sensitivity for eligible studies. The area under the receiver operating characteristic curve increased dramatically every time the algorithm learned a correct article. Conclusions Concept Encoder achieved a 10-fold reduction of the screening workload for systematic review after learning from 2 randomly selected studies on the target topic. However, few meta-analyses of randomized controlled trials were included. Concept Encoder could facilitate the acquisition of evidence for clinical guidelines.


2020 ◽  
Author(s):  
Tomohide Yamada ◽  
Daisuke Yoneoka ◽  
Yuta Hiraike ◽  
Kimihiro Hino ◽  
Hiroyoshi Toyoshiba ◽  
...  

BACKGROUND Performing systematic reviews is a time-consuming and resource-intensive process. OBJECTIVE We investigated whether a machine learning system could perform systematic reviews more efficiently. METHODS All systematic reviews and meta-analyses of interventional randomized controlled trials cited in recent clinical guidelines from the American Diabetes Association, American College of Cardiology, American Heart Association (2 guidelines), and American Stroke Association were assessed. After reproducing the primary screening data set according to the published search strategy of each, we extracted correct articles (those actually reviewed) and incorrect articles (those not reviewed) from the data set. These 2 sets of articles were used to train a neural network–based artificial intelligence engine (Concept Encoder, Fronteo Inc). The primary endpoint was work saved over sampling at 95% recall (WSS@95%). RESULTS Among 145 candidate reviews of randomized controlled trials, 8 reviews fulfilled the inclusion criteria. For these 8 reviews, the machine learning system significantly reduced the literature screening workload by at least 6-fold versus that of manual screening based on WSS@95%. When machine learning was initiated using 2 correct articles that were randomly selected by a researcher, a 10-fold reduction in workload was achieved versus that of manual screening based on the WSS@95% value, with high sensitivity for eligible studies. The area under the receiver operating characteristic curve increased dramatically every time the algorithm learned a correct article. CONCLUSIONS Concept Encoder achieved a 10-fold reduction of the screening workload for systematic review after learning from 2 randomly selected studies on the target topic. However, few meta-analyses of randomized controlled trials were included. Concept Encoder could facilitate the acquisition of evidence for clinical guidelines.


Author(s):  
Milan Milojevic ◽  
Philippe Kolh ◽  
Stephen E. Fremes ◽  
Miguel Sousa-Uva

The development and update of clinical guidelines are based on an evaluation of the latest data from clinical studies. According to the National Academy of Medicine, clinical practice guidelines are ‘statements that include recommendations intended to optimize patient care that is informed by a systematic review of the evidence and an assessment of the benefits and harms of alternative care options’. These expert documents are intended to provide systematically developed statements that include recommendations on how to translate clinical knowledge from scientific evidence into best patient-centred, evidence-based practice. Supplementing the textbook, clinical guidelines are now being increasingly considered decision drivers, and are being used by healthcare providers to choose the most appropriate diagnostic or therapeutic managing strategy, standardize care, reduce variation, and improve outcomes. The core of each of the clinical practice guidelines are the recommendations developed according to an established scale of the hierarchy of evidence. Although randomized controlled trials are at the top of the pyramid of evidence as the preferred study design for assessing the effects of two or more interventions, in many instances, task force members must rely on findings from observational studies. This is particularly so as trial patients may not always be typical of routine clinical practice. Hence, valuable information can be obtained from both randomized controlled trials and observational studies, including subgroup analysis, cohorts, or case series; therefore, each type of scientific research can be a significant complement to the other and contribute to guideline developments.


2021 ◽  
Vol 17 (2) ◽  
pp. 303-309
Author(s):  
A. S. Gerasimenko ◽  
V. S. Gorbatenko ◽  
O. V. Shatalova ◽  
V. I. Petrov

Intracerebral hemorrhage (ICH) is severe and fatal complication of anticoagulant therapy with an incidence 0.3-0.7% per year. For patients with atrial fibrillation (AF) anticoagulants are administered for decreasing risk of stroke and systemic embolism. In this case the occurrence of intracranial bleeding is hard task for doctor. From the one side it is necessary to reverse the action of the drug for preventing the growth of hematoma. At the same time the discontinuation of therapy increases the risk of systemic embolism for patients with AF significantly. Clinical guidelines and studies have been reviewed about ICH during anticoagulant therapy. Nowadays there is no quality evidence about reversal of anticoagulant effects after ICH and optimal time of resumption of anticoagulant therapy. Firstly, we do not have large randomized controlled trials on this issue. The majority of clinical guidelines were based on retrospective studies and opinions of experts. Soon several randomized controlled trials will be finished and new data will be presented.


Sign in / Sign up

Export Citation Format

Share Document