OBJECTIVES: To assess the efficacy and adverse effects of D-cycloserine compared with placebo for social and communication skills in individuals with ASD.
SEARCH METHODS: In November 2020, we searched CENTRAL, MEDLINE, Embase, six other databases and two trials registers. We also searched the reference lists of relevant publications and contacted the authors of the included study, Minshawi 2016, to identify any additional studies. In addition, we contacted pharmaceutical companies, searched manufacturers' websites and sources of reports of adverse events. SELECTION CRITERIA: All randomised controlled trials (RCTs) of any duration and dose of D-cycloserine, with or without adjunct treatment, compared to placebo in individuals with ASD.
DATA COLLECTION AND ANALYSIS: Two review authors independently selected studies for inclusion, extracted relevant data, assessed the risk of bias, graded the certainty of the evidence using the GRADE approach, and analysed and evaluated the data. We provide a narrative report of the findings as only one study is included in this review.
MAIN RESULTS: We included a single RCT (Minshawi 2016) funded by the United States Department of Defense. It was conducted at two sites in the USA: Indiana University School of Medicine and Cincinnati Children's Hospital Medical Centre. In the included study, 67 children with ASD aged between 5 and 11 years were randomised to receive either 10 weeks (10 doses) of (50 mg) D-cycloserine plus social skills training, or placebo plus social skills training. Randomisation was carried out 1:1 between D-cycloserine and placebo arms, and outcome measures were recorded at one-week post-treatment. The 'risk of bias' assessment for the included study was low for five domains and unclear for two domains. The study (67 participants) reported low certainty evidence of little to no difference between the two groups for all outcomes measured at one week post-treatment: social interaction impairment (mean difference (MD) 3.61 (assessed with the Social Responsiveness Scale), 95% confidence interval (CI) -5.60 to 12.82); social communication impairment (MD -1.08 (measured using the inappropriate speech subscale of the Aberrant Behavior Checklist (ABC)), 95% CI -2.34 to 0.18); restricted, repetitive, stereotyped patterns of behaviour (MD 0.12 (measured by the ABC stereotypy subscale), 95% CI -1.71 to 1.95); serious adverse events (risk ratio (RR) 1.11, 95% CI 0.94 to 1.31); non-core symptoms of ASD (RR 0.97 (measured by the Clinical Global Impression-Improvement scale), 95% CI 0.49 to 1.93); and tolerability of D-cycloserine (RR 0.32 (assessed by the number of dropouts), 95% CI 0.01 to 7.68). AUTHORS' CONCLUSIONS: We are unable to conclude with certainty whether D-cycloserine is effective for individuals with ASD. This review included low certainty data from only one study with methodological issues and imprecision. The added value of this review compared to the included study is we assessed the risk of bias and evaluated the certainty of evidence using the GRADE approach. Moreover, if we find new trials in future updates of this review, we could potentially pool the data, which may either strengthen or decrease the evidence for our findings.
OBJECTIVES: By leveraging the power of advanced machine learning schemes and experimental approaches, this research aims to provide valuable insights into CO2 flux prediction in coal fire areas and inform environmental monitoring and management strategies.
METHODS: The study involves the collection of an experimental dataset specific to underground coal fire areas, encompassing various parameters related to CO2 flux and underground coal fire characteristics. Innovative feature engineering techniques are applied to capture the unique characteristics of underground coal fire areas and their impact on CO2 flux. Different machine learning algorithms, including Natural gradient boosting regression (NGRB), Extreme gradient boosting (XGboost), Light gradient boosting (LGRB), and random forest (RF), are evaluated and compared for their predictive capabilities. The models are trained, optimized, and assessed using appropriate performance metrics.
RESULTS: The NGRB model yields the best predictive performances with R2 of 0.967 and MAE of 0.234. The novel contributions of this study include the development of accurate prediction models tailored to underground coal fire areas, shedding light on the underlying factors driving CO2 flux. The findings have practical implications for delineating the spontaneous combustion zone and mitigating CO2 emissions from underground coal fires, contributing to global efforts in combating climate change.