Physicians and healthcare organizations always collect large amounts of data during patient care. These large and high-dimensional datasets are usually characterized by an inherent sparseness. Hence, the analysis of these datasets to gure out interesting and hidden knowledge is a challenging task. This paper proposes a new data mining framework based on generalized association rules to discover multiple-level correlations among patient data. Specically, correlations among prescribed examinations, drugs, and patient proles are discovered and analyzed at different abstraction levels. The rule extraction process is driven by a taxonomy to generalize examinations and drugs into their corresponding categories. To ease the manual inspection of the result, a worthwhile subset of rules, i.e., the non-redundant generalized rules, is considered. Furthermore, rules are classied according to the involved data features (medical treatments or patient proles) and then explored in a top-down fashion, i.e., from the small subset of high-level rules a drill-down is performed to target more specic rules. The experiments, performed on a real diabetic patient dataset, demonstrate the effectiveness of the proposed approach in discovering interesting rule groups at different abstraction levels.

MeTA: Characterization of medical treatments at different abstraction levels / Antonelli, Dario; Baralis, ELENA MARIA; Bruno, Giulia; Cagliero, Luca; Cerquitelli, Tania; Chiusano, SILVIA ANNA; Garza, Paolo; Mahoto, NAEEM AHMED. - In: ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY. - ISSN 2157-6904. - STAMPA. - 6:4(2015), pp. 1-25. [10.1145/2700479]

MeTA: Characterization of medical treatments at different abstraction levels

ANTONELLI, DARIO;BARALIS, ELENA MARIA;BRUNO, GIULIA;CAGLIERO, LUCA;CERQUITELLI, TANIA;CHIUSANO, SILVIA ANNA;GARZA, PAOLO;MAHOTO, NAEEM AHMED
2015

Abstract

Physicians and healthcare organizations always collect large amounts of data during patient care. These large and high-dimensional datasets are usually characterized by an inherent sparseness. Hence, the analysis of these datasets to gure out interesting and hidden knowledge is a challenging task. This paper proposes a new data mining framework based on generalized association rules to discover multiple-level correlations among patient data. Specically, correlations among prescribed examinations, drugs, and patient proles are discovered and analyzed at different abstraction levels. The rule extraction process is driven by a taxonomy to generalize examinations and drugs into their corresponding categories. To ease the manual inspection of the result, a worthwhile subset of rules, i.e., the non-redundant generalized rules, is considered. Furthermore, rules are classied according to the involved data features (medical treatments or patient proles) and then explored in a top-down fashion, i.e., from the small subset of high-level rules a drill-down is performed to target more specic rules. The experiments, performed on a real diabetic patient dataset, demonstrate the effectiveness of the proposed approach in discovering interesting rule groups at different abstraction levels.
File in questo prodotto:
File Dimensione Formato  
AntonellietAl.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 389.62 kB
Formato Adobe PDF
389.62 kB Adobe PDF Visualizza/Apri
2700479.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 509.28 kB
Formato Adobe PDF
509.28 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2570938
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo