Dataset Information

A data-driven methodology to discover similarities between cocaine samples.

ABSTRACT: Machine learning has been used for distinct purposes in the science field but no applications on illegal drug have been done before. This study proposes a new web-based system for cocaine classification, profiling relations and comparison, that is capable of producing meaningful output based on a large amount of chemical profiling's data. In particular, the Profiling Relations In Drug trafficking in Europe (PRIDE) system, offers several advantages to intelligence actions across Europe. Thus, it provides a standardized, broad methodology which uses machine learning algorithms to classify and compare drug profiles, highlight how similar drug samples are, and how probable it is that they share a common origin, batch, or preparation process. We evaluated the proposed algorithms using precision and recall metrics and analyzed the quality of predictions performed by the algorithms, with respect to our gold standard. In our experiments, we reached a value of 88% for F_0.5-measure, 91% for precision, and 78% for recall, confirming our main hypothesis: machine learning can learn and be applied to have an automatic classification of cocaine profiles.

SUBMITTER: Cascini F

PROVIDER: S-EPMC7525495 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A data-driven methodology to discover similarities between cocaine samples.

Cascini Fidelia F De Giovanni Nadia N Inserra Ilaria I Santaroni Federico F Laura Luigi L

Scientific reports 20200929 1

Machine learning has been used for distinct purposes in the science field but no applications on illegal drug have been done before. This study proposes a new web-based system for cocaine classification, profiling relations and comparison, that is capable of producing meaningful output based on a large amount of chemical profiling's data. In particular, the Profiling Relations In Drug trafficking in Europe (PRIDE) system, offers several advantages to intelligence actions across Europe. Thus, it ...[more]

PMID: 32994485

Similar Datasets

Project description:BackgroundSeveral studies have focused on stratifying patients according to their level of readmission risk, fueled in part by incentive programs in the U.S. that link readmission rates to the annual payment update by Medicare. Patient-specific predictions about readmission have not seen widespread use because of their limited accuracy and questions about the efficacy of using measures of risk to guide clinical decisions. We construct a predictive model for readmissions for congestive heart failure (CHF) and study how its predictions can be used to perform patient-specific interventions. We assess the cost-effectiveness of a methodology that combines prediction and decision making to allocate interventions. The results highlight the importance of combining predictions with decision analysis.MethodsWe construct a statistical classifier from a retrospective database of 793 hospital visits for heart failure that predicts the likelihood that patients will be rehospitalized within 30 days of discharge. We introduce a decision analysis that uses the predictions to guide decisions about post-discharge interventions. We perform a cost-effectiveness analysis of 379 additional hospital visits that were not included in either the formulation of the classifiers or the decision analysis. We report the performance of the methodology and show the overall expected value of employing a real-time decision system.FindingsFor the cohort studied, readmissions are associated with a mean cost of $13,679 with a standard error of $1,214. Given a post-discharge plan that costs $1,300 and that reduces 30-day rehospitalizations by 35%, use of the proposed methods would provide an 18.2% reduction in rehospitalizations and save 3.8% of costs.ConclusionsClassifiers learned automatically from patient data can be joined with decision analysis to guide the allocation of post-discharge support to CHF patients. Such analyses are especially valuable in the common situation where it is not economically feasible to provide programs to all patients.

Project description:BackgroundThe NHS is facing substantial pressures to recover from the COVID-19 pandemic. Optimising workforce modelling is a fundamental component of the recovery plan. The Clinically Lead workforcE and Activity Redesign (CLEAR) programme is a unique methodology that trains clinicians to redesign services, building intrinsic capacity and capability, optimising patient care and minimising the need for costly external consultancy. This paper describes the CLEAR methodology and the evaluation of previous CLEAR projects, including the return on investment.MethodsCLEAR is a work-based learning programme that combines qualitative techniques with data analytics to build innovations and new models of care. It has four unique stages: (1) Clinical engagement- used to gather rich insights from stakeholders and clinicians. (2) Data interrogation- utilising clinical and workforce data for cohort analysis. (3) Innovation- using structured innovation methods to develop new models of care. (4) Recommendations- report writing, impact assessment and presentation of key findings to executive boards. A mixed-methods formative evaluation was carried out on completed projects, which included semi-structured interviews and surveys with CLEAR associates and stakeholders, and a health economic logic model that was developed to link the inputs, processes, outputs and the outcome of CLEAR as well as the potential impacts of the changes identified from the projects.ResultsCLEAR provides a more cost-effective delivery of complex change programmes than the alternatives - resulting in a cost saving of £1.90 for every £1 spent independent of implementation success. Results suggest that CLEAR recommendations are more likely to be implemented compared to other complex healthcare interventions because of the levels of clinical engagement and have a potential return on investment of up to £14 over 5 years for every £1 invested. CLEAR appears to have a positive impact on staff retention and wellbeing, the cost of a CLEAR project is covered if one medical consultant remains in post for a year.ConclusionsThe unique CLEAR methodology is a clinically effective and cost-effective complex healthcare innovation that optimises workforce and activity design, as well as improving staff retention. Embedding CLEAR methodology in the NHS could have substantial impact on patient care, staff well-being and service provision.

Dataset Information

A data-driven methodology to discover similarities between cocaine samples.

Publications

A data-driven methodology to discover similarities between cocaine samples.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets