Cost-based quality measures in subgroup discovery

Konijn, Rob M.; Duivesteijn, Wouter; Meeng, Marvin; Knobbe, Arno

doi:10.1007/s10844-014-0313-8

Cited by 8 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, Atzmueller et al describes a combination of quality measures for rules concerning the validity, that is, the accuracy and the simplicity of the contained patterns. Furthermore, cost‐based quality functions, e.g., Ref and cost‐sensitive approaches allow the modeling of costs for the quality assessment.…”

Section: Fundamentals Of Subgroup Discoverymentioning

confidence: 99%

Subgroup discovery

Atzmueller

2015

WIREs Data Min & Knowl

194

102

View full text Add to dashboard Cite

Subgroup discovery is a broadly applicable descriptive data mining technique for identifying interesting subgroups according to some property of interest. This article summarizes fundamentals of subgroup discovery, before that it also reviews algorithms and further advanced methodological issues. In addition, we briefly discuss tools and applications of subgroup discovery approaches. In that context, we also discuss experiences and lessons learned and outline some of the future directions in order to show the advantages and benefits of subgroup discovery.

show abstract

Section: Fundamentals Of Subgroup Discoverymentioning

confidence: 99%

Subgroup discovery

Atzmueller

2015

WIREs Data Min & Knowl

194

102

View full text Add to dashboard Cite

show abstract

“…There are number of quality measures used in subgroup discovery (Herrera, Carmona, Gonzalez, & Jose del Jesus, 2011) to quantify the statistical novelty of a subgroup or rule (Konijn, Duivesteijn, Meeng & Knobbe, 2014). Duivesteijn and Arno (2011) note that selecting the right quality measure is often a difficult task; this choice is either driven by familiarity with the measures or based on default choice.…”

Section: Associated Symptoms Include Nausea Mild Epigastric Tendernementioning

confidence: 99%

Using Learning Analytics to Identify Medical Student Misconceptions in an Online Virtual Patient Environment

Poitras

Naismith

Doleck

et al. 2015

OLJ

View full text Add to dashboard Cite

This study aimed to identify misconceptions in medical student knowledge by mining user interactions in the MedU online learning environment. Data from 13000 attempts at a single virtual patient case were extracted from the MedU MySQL database. A subgroup discovery method was applied to identify patterns in learner-generated annotations and responses to multiple-choice items on the diagnosis and management of acute myocardial infarction (i.e., heart attack). First, the algorithm generated rules where single terms from the learner annotations were used to predict incorrect answers to the multiple-choice items. Second, the possible combinations of terms and their relevant synonyms were used to determine whether their inclusion led to better rates of prediction. The second step was found to significantly increase prediction precision and weighted relative accuracy, uncovering four misconceptions at a rate greater than 70%. These findings serve to inform the design of an adaptive system that tailors the delivery of formative feedback to promote better learning outcomes in the domain of clinical reasoning.

show abstract

“…A small number of studies tried to tackle fraud detection by adopting supervised techniques [9][10][11][12], which despite their undeniable potential and predictive power, exhibit the risk of focusing on old patterns and losing predictive capability as new records are evaluated over time [13]. Due to these considerations, most of the available literature in the field focuses on unsupervised techniques [3,5,[14][15][16][17][18][19][20][21][22][23], with the limitation of spotting providers with very high claiming episodes, which distinguish themselves as evident outliers [23]. However, types of fraud are growing increasingly sophisticated.…”

Section: Introductionmentioning

confidence: 99%

Data mining application to healthcare fraud detection: a two-step unsupervised clustering method for outlier detection with administrative databases

Massi

Ieva

Lettieri

2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background: The healthcare sector is an interesting target for fraudsters. The availability of a great amount of data makes it possible to tackle this issue with the adoption of data mining techniques, making the auditing process more efficient and effective. This research has the objective of developing a novel data mining model devoted to fraud detection among hospitals using Hospital Discharge Charts (HDC) in Administrative Databases. In particular, it is focused on the DRG upcoding practice, i.e., the tendency of registering codes for provided services and inpatients health status so to make the hospitalization fall within a more remunerative DRG class. Methods: We propose a two-step algorithm: the first step entails kmeans clustering of providers to identify locally consistent and locally similar groups of hospitals, according to their characteristics and behavior treating a specific disease, in order to spot outliers within this groups of peers. An initial grid search for the best number of features to be selected (through Principal Feature Analysis) and the best number of local groups makes the algorithm extremely flexible. In the second step, we propose a human-decision support system that helps auditors cross-validating the identified outliers, analyzing them w.r.t. fraud-related variables, and the complexity of patients' casemix they treated. The proposed algorithm was tested on a database relative to HDC collected by Regione Lombardia (Italy) in a time period of three years (2013-2015), focusing on the treatment of Heart Failure. Results: The model identified 6 clusters of hospitals and 10 outliers among the 183 units. Out of those providers, we report the in depth the application of Step Two on three Hospitals (two private and one public). Cross-validating with the patients' population and the hospitals' characteristics, the public hospital seemed justified in its outlierness, while the two private providers were deemed interesting for a further investigation by auditors.

show abstract

Cost-based quality measures in subgroup discovery

Cited by 8 publications

References 14 publications

Subgroup discovery

Subgroup discovery

Using Learning Analytics to Identify Medical Student Misconceptions in an Online Virtual Patient Environment

Data mining application to healthcare fraud detection: a two-step unsupervised clustering method for outlier detection with administrative databases

Contact Info

Product

Resources

About