A quality framework for statistical algorithms

2021 ◽  
pp. 1-18
Author(s):  
Wesley Yung ◽  
Siu-Ming Tam ◽  
Bart Buelens ◽  
Hugh Chipman ◽  
Florian Dumpert ◽  
...  
Keyword(s):  
Machine Learning ◽  
Official Statistics ◽  
High Quality ◽  
Machine Learning Methods ◽  
High Level Group ◽  
Black Boxes ◽  
Quality Framework ◽  
Statistical Algorithms ◽  
High Level ◽  
Level Group

As national statistical offices (NSOs) modernize, interest in integrating machine learning (ML) into official statisticians’ toolbox is growing. Two challenges to such an integration are the potential loss of transparency from using “black-boxes” and the need to develop a quality framework. In 2019, the High-Level Group for the Modernisation of Official Statistics (HLG-MOS) launched a project on machine learning with one of the objectives being to address these two challenges. One of the outputs of the HLG-MOS project is a Quality Framework for Statistical Algorithms (QF4SA). While many quality frameworks exist, they have been conceived with traditional methods in mind, and they tend to target statistical outputs. Currently, machine learning methods are being looked at for use in processes producing intermediate outputs, which lead to a final statistical output. Therefore, the QF4SA does not replace existing quality frameworks; it complements them. As the QF4SA targets intermediate outputs and not necessarily the final statistical output, it should be used in conjunction with existing quality frameworks to ensure that high-quality outputs are produced. This paper presents the QF4SA, as well as some recommendations for NSOs considering the use of machine learning in the production of official statistics.

scholarly journals The serum homocysteine level in patients with acute ischemic stroke (AIS) after thrombolysis and its relationship with clinical outcomes

2018 ◽  
Vol 64 (5) ◽  
pp. 438-442 ◽  
Author(s):  
Ling-Cong ◽  
Hong-Zhao ◽  
Yu-Wang ◽  
Yu-Li ◽  
Xin-Sui
Keyword(s):  
Clinical Outcomes ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Thrombolytic Treatment ◽  
Neurological Outcomes ◽  
High Level Group ◽  
Serum Homocysteine ◽  
High Level ◽  
The Relationship ◽  
Level Group

SUMMARY OBJECTIVE The present study aims to investigate whether hyperhomocysteinemia (HHcy) affects the outcomes of the thrombolytic treatment for patients with AIS. METHODS A sample of 120 AIS patients were recruited and grouped according to their serum homocysteine (Hcy) levels. The National Institute of Health Stroke Scale (NIHSS) was obtained before treatment and 7 days after it to evaluate neurological outcomes; modified Rankin Scale (mRS) was obtained 12 weeks later to assess functional outcomes. Receiver operating characteristic curve (ROC) was used to demonstrate the relationship between serum Hcy level and the outcomes after tPA treatment. RESULTS The serum Hcy level of 120 patients was of 27.57±20.17μmol/L. The NIHSS scores of the patients in the low Hcy level group were remarkably lower compared to those in the high-level group (p<0.05), after 7 days of treatment. In addition, the mRS scores of the patients in the low Hcy level group, after 12 weeks, were remarkably lower compared to those in the high-level group (p<0.01). ROC demonstrated that the serum Hcy level is related to the clinical outcomes of thrombolytic treatment with moderate specificity (80.3%) and sensitivity (58.2%). CONCLUSION In conclusion, higher serum Hcy levels can indicate poorer clinical outcomes of thrombolytic treatment in patients with AIS.

A Semi-Automated Term Harmonization Pipeline Applied to Pulmonary Arterial Hypertension Clinical Trials

2021 ◽  
Author(s):  
Ryan J. Urbanowicz ◽  
John H. Holmes ◽  
Dina Appleby ◽  
Vanamala Narasimhan ◽  
Stephen Durborow ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Pulmonary Arterial Hypertension ◽  
Arterial Hypertension ◽  
System Organ Class ◽  
High Level Group ◽  
Fuzzy Matching ◽  
Pulmonary Arterial ◽  
High Level ◽  
Level Group ◽  
System Organ

Abstract Objective Data harmonization is essential to integrate individual participant data from multiple sites, time periods, and trials for meta-analysis. The process of mapping terms and phrases to an ontology is complicated by typographic errors, abbreviations, truncation, and plurality. We sought to harmonize medical history (MH) and adverse events (AE) term records across 21 randomized clinical trials in pulmonary arterial hypertension and chronic thromboembolic pulmonary hypertension. Methods We developed and applied a semi-automated harmonization pipeline for use with domain-expert annotators to resolve ambiguous term mappings using exact and fuzzy matching. We summarized MH and AE term mapping success, including map quality measures, and imputation of a generalizing term hierarchy as defined by the applied Medical Dictionary for Regulatory Activities (MedDRA) ontology standard. Results Over 99.6% of both MH (N = 37,105) and AE (N = 58,170) records were successfully mapped to MedDRA low-level terms. Automated exact matching accounted for 74.9% of MH and 85.5% of AE mappings. Term recommendations from fuzzy matching in the pipeline facilitated annotator mapping of the remaining 24.9% of MH and 13.8% of AE records. Imputation of the generalized MedDRA term hierarchy was unambiguous in 85.2% of high-level terms, 99.4% of high-level group terms, and 99.5% of system organ class in MH, and 75% of high-level terms, 98.3% of high-level group terms, and 98.4% of system organ class in AE. Conclusion This pipeline dramatically reduced the burden of manual annotation for MH and AE term harmonization and could be adapted to other data integration efforts.

scholarly journals Winter Androgen Levels and Wattle Size in Male Common Pheasants

The Condor ◽  
2000 ◽  
Vol 102 (1) ◽  
pp. 193-197 ◽  
Author(s):  
Anna Papeschi ◽  
Federica Briganti ◽  
Francesco DessÌ-Fulgheri
Keyword(s):  
Breeding Season ◽  
Phasianus Colchicus ◽  
Hormone Levels ◽  
Male Trait ◽  
High Level Group ◽  
High Level ◽  
Level Group ◽  
Androgen Levels ◽  
Normally Distributed

Abstract We report the results of morphological and hormonal measurements of 101 male Common Pheasants (Phasianus colchicus) captured during winter and at the beginning of the breeding season in order to identify correlates of ornament size. Androgen levels in January were bimodally distributed with one group with low hormone levels and a second group with high levels. In February, log transformed androgen levels were normally distributed, with all males showing values similar to the high-level group in January. Wattle size was positively correlated with androgens in January but not in February, suggesting that this male trait can indicate the ability of quality males to start earlier androgen production.

Minimal Residual Disease Status at Day +100 Post Allogeneic Hematopoietic Stem Cell Transplantation Is a Powerful Predictor for Post-Transplant Outcome In Patients with High Risk Acute Leukemia

Blood ◽  
2010 ◽  
Vol 116 (21) ◽  
pp. 3550-3550
Author(s):  
XiaoWen Tang ◽  
Xingwei Sun ◽  
Shengli Xue ◽  
Xiaolan Shi ◽  
Mingqing Zhu ◽  
...  
Keyword(s):  
High Risk ◽  
Residual Disease ◽  
Hematopoietic Stem ◽  
Free Survival ◽  
Post Transplant ◽  
Low Level ◽  
High Level Group ◽  
Risk Patients ◽  
High Level ◽  
Level Group

Abstract Abstract 3550 Background and Objectives Relapse after allogeneic hematopoietic stem cell transplantation (allo-HSCT) is still a major cause for the failure in treatment. It has been shown that there was a closely relationship between the level of minimal residual disease (MRD) and relapse in acute leukemia (AL) patients; However, the application of multiparameter flow cytometry (MFC) for MRD assessment in high risk patients with AL who undergoing allo-HSCT is little concerned. We retrospectively analysed the serial results of MRD of 52 high risk patients with AL to evaluates the prognostic value of MRD pre and post transplantation. Methods 52 patients with a median age of 29 (13–55) years have been enrolled on this study in our hospital from January 2003 to September 2008.Diagnoses included AML (n=27) and ALL (n=25). The patients had been analyzed retrospectively the level of MRD pre-(day-30)and post-HSCT(day+30 and +100)using three color FCM with CD45/SSC gating and a comprehensive panel of monoclonal antibodies, at least one leukemia associated aberrant immunophenotype (LAIP) at diagnosis. According to the cutoff value 0.1%, two groups were defined based on the level of patient's MRD level< (low level group) or >= (high level group) 0.1%. Results The median follow up were 23 (range 1–60) months. 1.MRD level declines significantly (P=0.03) post transplant. 2. There were significantly difference between low level and high level group at day -30 before transplant with 3 years event free survival(EFS) and relapse free survival (RFS)(77.4% and 88.4% vs. 22.3% and 25.7%, p=0.007and p=0.001 respectively). 3. Concerning about MRD at day +100 after transplant, outcome was significantly better among patients with low level MRD group versus high group including 3 years OS,EFS and RFS(84.2%, 79.5% and 89.5% versus 22.9%, 9.5% and 11.2%).4. The median time from high level MRD detected first time to clinical relapse was 2.5 (range from 1 to 33) months in relapsed patients. 5. The patients with cGVHD had better 3 years OS and EFS than that without cGVHD(86.3% vs 12.1%, p<0.001 and 65.3% vs.14.8%, p< 0.001 respectively). 6. Multivariate Cox regression analysis revealed that MRD on day +100 as well as chronic GVHD were independent parameters predictive for OS and EFS. Conclusions MRD monitoring pre- and post-transplant is an important tool to predict the outcome of transplantation for patients with high risk AL. The MRD check point at day +100 should be considered crucial for subsequent therapeutic decisions after allogeneic transplantation. Disclosures: No relevant conflicts of interest to declare.

scholarly journals Development of Teaching Materials of Poetry Writing Using Pictures for the Elementary Students

2020 ◽  
Author(s):  
Satinem ◽  
Juwati
Keyword(s):  
Group Level ◽  
Teaching Materials ◽  
Average Value ◽  
High Level Group ◽  
Significant Difference ◽  
Poetry Writing ◽  
High Level ◽  
Value Of Learning ◽  
Level Group ◽  
Test Result

The research aims to develop the product of Teaching Materials of Poetry Writing Using Pictures. This developed teaching material result is expected to be used by the students of grade V of SD Xaverius Lubuklinggau, SD Negeri 44 Lubuklinggau, and SD Negeri 20 Lubuklinggau in learning to write poetry.The method used in research is research and development or better known as R &amp; D.If the calculation of the data is smaller than the alpha value (0.05), it means that there has been a significant difference before it is used after the use of poetry writing materials compared to the KKM of each school, so that the Teaching Materials of Poetry Writing Using Pictures is declared effective. From the calculation bySPSS, the results obtained for the test value tcount 11.219 and ttable 2.045 for (d) 30 and alpa 0.05 in high level group students of SD Xaverius. While for the average level group shows the value of tcount 9,416 and ttable 2.042 for (d) 30 and alpha 0.05. For the low group level, gained the tcount value of 4.859 and ttable 2,110 for (d) 17 and alpha 0.05, thus it can be concluded that tcount&gt; ttable, so H0 is rejected, and H1 is accepted. In the other word, it can be concluded that tcount&gt; ttable, so that H0 is rejected.Based on t test result from three schools, it can be concluded that tcount&gt; ttable, so H0 is rejected, and Ha accepted. The average value of learning completeness after using writing materials is the same or greater with the Minimal Completeness Criteria (KKM) in each school, meaning that the teaching materials is effective used to improve the students’ ability in writing poetry.

scholarly journals Development of Teaching Materials of Poetry Writing Using Pictures for the Elementary Students

2018 ◽  
Vol 9 (3) ◽  
pp. 1 ◽  
Author(s):  
Satinem ◽  
Juwati
Keyword(s):  
Group Level ◽  
Teaching Materials ◽  
Average Value ◽  
High Level Group ◽  
Significant Difference ◽  
Poetry Writing ◽  
High Level ◽  
Value Of Learning ◽  
Level Group ◽  
Test Result

The research aims to develop the product of Teaching Materials of Poetry Writing Using Pictures. This developed teaching material result is expected to be used by the students of grade V of SD Xaverius Lubuklinggau, SD Negeri 44 Lubuklinggau, and SD Negeri 20 Lubuklinggau in learning to write poetry.The method used in research is research and development or better known as R & D.If the calculation of the data is smaller than the alpha value (0.05), it means that there has been a significant difference before it is used after the use of poetry writing materials compared to the KKM of each school, so that the Teaching Materials of Poetry Writing Using Pictures is declared effective. From the calculation bySPSS, the results obtained for the test value tcount 11.219 and ttable 2.045 for (d) 30 and alpa 0.05 in high level group students of SD Xaverius. While for the average level group shows the value of tcount 9,416 and ttable 2.042 for (d) 30 and alpha 0.05. For the low group level, gained the tcount value of 4.859 and ttable 2,110 for (d) 17 and alpha 0.05, thus it can be concluded that tcount> ttable, so H0 is rejected, and H1 is accepted. In the other word, it can be concluded that tcount> ttable, so that H0 is rejected.Based on t test result from three schools, it can be concluded that tcount> ttable, so H0 is rejected, and Ha accepted. The average value of learning completeness after using writing materials is the same or greater with the Minimal Completeness Criteria (KKM) in each school, meaning that the teaching materials is effective used to improve the students’ ability in writing poetry.

scholarly journals After ‘HLEG’: EU Banks, Climate Change Abatement and the Precautionary Principle

2018 ◽  
Vol 20 ◽  
pp. 61-87 ◽  
Author(s):  
Jay CULLEN
Keyword(s):  
Climate Change ◽  
Carbon Footprint ◽  
Capital Requirements ◽  
External Financing ◽  
High Level Group ◽  
Sustainable Finance ◽  
Structural Uncertainties ◽  
High Level ◽  
Level Group ◽  
The Eu

AbstractThe EU is making progress in reducing its carbon footprint. The creation of a High-Level Group on Sustainable Finance has supplemented recent market-led initiatives and provided some recommendations for future reform. This article argues that more remains to be achieved. In particular, in light of the fundamental structural uncertainties attached to climate change, precautionary approaches to the funding of GHG-intensive industries are worth contemplating. Such measures include raising the capital requirements on assets with ‘brown’ credentials. The high dependence on banks for external financing in the EU makes these reforms particularly appropriate for implementation within the bloc.

Sign in / Sign up

Export Citation Format

Share Document