Detention Decision-Making in Slovenia Using the Computerized Risk Assessment Tool Detention v1.0: Effective Use of Machine Learning Algorithms from the Perspective of the Defendant’s Procedural Rights

2021 ◽  
pp. 127-159
Author(s):  
Primož Križnar ◽  
Katja Piršič
Keyword(s):  
Machine Learning ◽  
Risk Assessment ◽  
Decision Making ◽  
Assessment Tool ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Risk Assessment Tool ◽  
Effective Use ◽  
Procedural Rights

scholarly journals Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Alan Brnabic ◽  
Lisa M. Hess
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Real World ◽  
Learning Algorithms ◽  
External Validation ◽  
Machine Learning Algorithms ◽  
Learning Methods ◽  
Machine Learning Methods

Abstract Background Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making. Methods This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified; study quality was assessed using a modified version of the Luo checklist. Results A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies. Conclusions A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

scholarly journals Algorithmic Opacity: Making Algorithmic Processes Transparent through Abstraction Hierarchy

2018 ◽  
Vol 62 (1) ◽  
pp. 192-196
Author(s):  
Pragya Paudyal ◽  
B.L. William Wong
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Ethical Decision Making ◽  
Ethical Issues ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Intelligence Analysis ◽  
Functional Relationships ◽  
Decomposition Space ◽  
Criminal Intelligence

In this paper we introduce the problem of algorithmic opacity and the challenges it presents to ethical decision-making in criminal intelligence analysis. Machine learning algorithms have played important roles in the decision-making process over the past decades. Intelligence analysts are increasingly being presented with smart black box automation that use machine learning algorithms to find patterns or interesting and unusual occurrences in big data sets. Algorithmic opacity is the lack visibility of computational processes such that humans are not able to inspect its inner workings to ascertain for themselves how the results and conclusions were computed. This is a problem that leads to several ethical issues. In the VALCRI project, we developed an abstraction hierarchy and abstraction decomposition space to identify important functional relationships and system invariants in relation to ethical goals. Such explanatory relationships can be valuable for making algorithmic process transparent during the criminal intelligence analysis process.

An Economic Perspective on Algorithmic Fairness

2020 ◽  
Vol 110 ◽  
pp. 91-95 ◽  
Author(s):  
Ashesh Rambachan ◽  
Jon Kleinberg ◽  
Jens Ludwig ◽  
Sendhil Mullainathan
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Decision Making Under Uncertainty ◽  
Economic Perspective ◽  
Optimal Regulation ◽  
Economic Framework ◽  
Computer Scientists ◽  
Algorithmic Bias

There are widespread concerns that the growing use of machine learning algorithms in important decisions may reproduce and reinforce existing discrimination against legally protected groups. Most of the attention to date on issues of “algorithmic bias” or “algorithmic fairness” has come from computer scientists and machine learning researchers. We argue that concerns about algorithmic fairness are at least as much about questions of how discrimination manifests itself in data, decision-making under uncertainty, and optimal regulation. To fully answer these questions, an economic framework is necessary--and as a result, economists have much to contribute.

scholarly journals Improving VTE risk assessment and prophylaxis prescribing rate in medical patients: integrating risk assessment tool into the workflow

2020 ◽  
Vol 9 (2) ◽  
pp. e000903
Author(s):  
Hannah Preston ◽  
Iain Swan ◽  
Lauren Davies ◽  
Simon Dummer ◽  
Veiraiah Aravindan ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Decision Making ◽  
Assessment Tool ◽  
Qualitative Interviews ◽  
Baseline Period ◽  
Risk Assessment Tool ◽  
Medical Patients ◽  
Seamless Integration ◽  
Pharmacological Prophylaxis ◽  
Vte Prophylaxis

Medical inpatients often have important risk factors for venous thromboembolism (VTE). In our institution, VTE prophylaxis in this group was underused. The main barriers identified were inattention to VTE prophylaxis, competing priorities and lack of confidence in the decision-making. We aimed to improve the rate of VTE prophylaxis use by introducing a paper-based risk assessment tool, with actionable management recommendations within the prescription chart. The rationale was that an assessment tool at the point of prescribing can reduce steps between decision-making and prescribing process, thus promoting confidence and acting as a reminder. A total of 552 prescription charts completed over a period of 29 weeks were examined during the baseline period. In the postintervention period, 871 charts completed over 40 weeks period were examined. The risk assessment tool was completed in 51% of the cases examined in the postintervention period. The introduction of the risk assessment tool was associated with a significant change in the pattern of VTE pharmacological prophylaxis use. The change occurred when the form was made highly visible and enclosed in the prescription chart. The pharmacological prophylaxis use was higher with a completed assessment form than without (mean (SD) 97.5% (7.6%) vs 70.1% (19.4%); p<0.0001). The rate of appropriate prophylaxis decision was 98.2% (SD 5.2%) with a completed assessment form, and 80.7% (SD 17.9%) when it was not used. The qualitative interviews revealed positive themes; many users found it useful, easy and convenient to use. Our data have shown that a paper-based VTE risk assessment tool placed within the prescription chart could substantially improve the rate of appropriate assessment and VTE prophylaxis implementation. This suggests that tool clearly needs to be a seamless integration into the workflow to capture users’ attention and mitigate the influence of time perception.

Autonomous Interpretation Methods of Ultrasonic Data Through Machine Learning Facilitates Novel and Reliable Casing Annulus Characterization

2021 ◽  
Author(s):  
Ram Sunder Kalyanraman ◽  
Xiaoli Chen ◽  
Po-Yen Wu ◽  
Kevin Constable ◽  
Amit Govil ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Complex Task ◽  
Wireline Logs ◽  
Cement Sheath ◽  
Sonic Logs ◽  
Correct Processing

Abstract Ultrasonic and sonic logs are increasingly used to evaluate the quality of cement placement in the annulus behind the pipe and its potential to perform as a barrier. Wireline logs are carried out in widely varying conditions and attempt to evaluate a variety of cement formulations in the annulus. The annulus geometry is complex due to pipe standoff and often affects the behavior (properties) of the cement. The transformation of ultrasonic data to meaningful cement evaluation is also a complex task and requires expertise to ensure the processing is correctly carried out as well interpreted correctly. Cement formulations can vary from heavy weight cement to ultralight foamed cements. The ultrasonic log-based evaluation, using legacy practices, works well for cements that are well behaved and well bonded to casing. In such cases, a lightweight cement and heavyweight cement, when bonded, can be easily discriminated from gas or liquid (mud) through simple quantitative thresholds resulting in a Solid(S) - Liquid(L) - Gas(G) map. However, ultralight and foamed cements may overlap with mud in quantitative terms. Cements may debond from casing with a gap (that is either wet or dry), resulting in a very complex log response that may not be amenable to simple threshold-based discrimination of S-L-G. Cement sheath evaluation and the inference of the cement sheath to serve as a barrier is complex. It is therefore imperative that adequate processes mitigate errors in processing and interpretation and bring in reliability and consistency. Processing inconsistencies are caused when we are unable to correctly characterize the borehole properties either due to suboptimal measurements or assumptions of the borehole environment. Experts can and do recognize inconsistencies in processing and can advise appropriate resolution to ensure correct processing. The same decision-making criteria that experts follow can be implemented through autonomous workflows. The ability for software to autocorrect is not only possible but significantly enables the reliability of the product for wellsite decisions. In complex situations of debonded cements and ultralight cements, we may need to approach the interpretation from a data behavior-based approach, which can be explained by physics and modeling or through observations in the field by experts. This leads a novel seven-class annulus characterization [5S-L-G] which we expect will bring improved clarity on the annulus behavior. We explain the rationale for such an approach by providing a catalog of log response for the seven classes. In addition, we introduce the ability to carry out such analysis autonomously though machine learning. Such machine learning algorithms are best carried out after ensuring the data is correctly processed. We demonstrate the capability through a few field examples. The ability to emulate an "expert" through software can lead to an ability to autonomously correct processing inconsistencies prior to an autonomous interpretation, thereby significantly enhancing the reliability and consistency of cement evaluation, ruling out issues related to subjectivity, training, and competency.

Sign in / Sign up

Export Citation Format

Share Document