Carlo Cerra

Mining Healthcare Data with Temporal Association Rules: Improvements and Assessment for a Practical Use

The Regional Healthcare Agency (ASL) of Pavia has been maintaining a central data repository which stores healthcare data about the population of Pavia area. The analysis of such data can be fruitful for the assessment of healthcare activities. Given the crucial role of time in such databases, we developed a general methodology for the mining of Temporal Association Rules on sequences of hybrid events. In this paper we show how the method can be extended to suitably manage the integration of both clinical and administrative data. Moreover, we address the problem of developing an automated strategy for the filtering of output rules, exploiting the taxonomy underlying the drug coding system and considering the relationships between clinical variables and drug effects. The results show that the method could find a practical use for the evaluation of the pertinence of the care delivery flow for specific pathologies.

Mining Health Care Administrative Data with Temporal Association Rules on Hybrid Events

OBJECTIVE The analysis of administrative health care data can be helpful to conveniently assess health care activities. In this context temporal data mining techniques can be suitably exploited to get a deeper insight into the processes underlying health care delivery. In this paper we present an algorithm for the extraction of temporal association rules (TARs) on sequences of hybrid events and its application on health care administrative databases. METHODS We propose a method that extends TAR mining by managing hybrid events, namely events characterized by a heterogeneous temporal nature. Hybrid events include both point-like events (e.g. ambulatory visits) and interval-like events (e.g. drug consumption). The definition of user-defined rule templates can be optionally used to constrain the search only to the extraction of a subset of interesting rules. A TAR post-pruning strategy, based on a case-control approach, is also presented. RESULTS We analyzed the administrative database of diabetic patients in charge to the regional health care agency (ASL) of Pavia. TAR mining allowed to find patterns specifically related to the diabetic population in comparison with a control group, as well as to check the compliance of the actual clinical careflow with the ASL recommendations. CONCLUSION The experimental results highlighted the main potentials of the algorithm, such as the opportunity to detect interesting temporal relationships between diagnostic or therapeutic patterns, or to check the adherence of past temporal behaviors to specific expected paths (e.g. guidelines) or to discover new knowledge that could be implicitly hidden in the data.

Mining administrative and clinical diabetes data with temporal association rules.

The Regional Healthcare Agency (ASL) of Pavia has been collecting and maintaining a central data repository which stores both administrative and clinical healthcare data about the population of Pavia area. The analysis of such integrated databases could greatly help to extract useful information for the assessment of health care delivery process. In this paper we focus our attention on the care delivery flow of Diabetes Mellitus, and we show the application of an algorithm for the extraction of Temporal Association Rules on sequences of hybrid events. This method allows to properly exploit the integration of different healthcare information sources, and can be used to evaluate the pertinence of the care delivery flow for specific pathologies, in order to reassess or refine the inappropriate practices which lead to unsatisfactory outcomes.

Integration of Administrative, Clinical, and Environmental Data to Support the Management of Type 2 Diabetes Mellitus: From Satellites to Clinical Care.

A very interesting perspective of “big data” in diabetes management stands in the integration of environmental information with data gathered for clinical and administrative purposes, to increase the capability of understanding spatial and temporal patterns of diseases. Within the MOSAIC project, funded by the European Union with the goal to design new diabetes analytics, we have jointly analyzed a clinical-administrative dataset of nearly 1.000 type 2 diabetes patients with environmental information derived from air quality maps acquired from remote sensing (satellite) data. Within this context we have adopted a general analysis framework able to deal with a large variety of temporal, geo-localized data. Thanks to the exploitation of time series analysis and satellite images processing, we studied whether glycemic control showed seasonal variations and if they have a spatiotemporal correlation with air pollution maps. We observed a link between the seasonal trends of glycated hemoglobin and air pollution in some of the considered geographic areas. Such findings will need future investigations for further confirmation. This work shows that it is possible to successfully deal with big data by implementing new analytics and how their exploration may provide new scenarios to better understand clinical phenomena.

Analisi di minimizzazione dei costi degli agenti stimolanti l’eritropoiesi nel trattamento dell’anemia indotta da chemioterapia

SummaryIntroductionAdministration of Erythropoietin Receptor Agonists (ERAs) is indicated as standard of care for treatment of anaemia in cancer patients. Considering the Italian setting, only limited information is available on the economic impact of ERAs epoetin alfa, epoetin beta and darbepoetin alfa in the treatment of anaemic cancer patients. So, this analysis was conducted to compare cost per patient of each of these agents.Materials and methodsData for this retrospective study were derived from the administrative database of a middle-sized (half a million beneficiaries) Local Health Unit in Northern Italy. A sample was built by selecting all patients who, between 2005 and 2006, had a cancer diagnosis and had received at least two prescription for ERA. The study evaluated durations of treatments and weekly costs associated with either treatment.ResultsThe original sample consisted of 322 patients (mean age: 65.6 years, 52.5% females). The mean duration of treatment was 7.52 weeks for epoetin alfa and 8.68 weeks for darbepoetin alfa (p = 0.16). The annual mean cost of treatment was €2,413.23/patient treated with epoetin alfa and €3,492.23/patient (+45%) treated with darbepoetin alfa (p < 0.001).Discussion and conclusionsBased on data from an Italian Local Health Unit, we performed an analysis focused on the use of ERAs in the treatment of anemia in cancer patients. Analysis results were interesting, particularly as attempt to estimate the annual mean cost of treatment between epoetin alfa and darbepoetin alfa, which resulted consistent with a previous European study. This evaluation showed that epoetin is a cost-saving strategy compared with darbepoetin alfa in the treatment of cancer patients anaemia. An important limitation was that patient records did not provide an indicator of disease severity.

Analisi dei consumi e dei costi degli agenti stimolanti l’eritropoiesi nel trattamento dell’anemia nei pazienti con insufficienza renale cronica

SummaryIntroductionDuring the maintenance dialysis as well the pre-dialysis period anemia represents one of the most frequent and debilitating diseases associated with chronic kidney disease (CKD). If anemia is untreated, the quality of life is reduced and survival is shortened. Epoetin and darbepoetin alfa are Erythropoietin Receptor Agonists (ERAs) indicated for the treatment of anemia in patients with CKD.Materials and methodsData for this retrospective study were derived from the administrative database of a middle-sized (half a million beneficiaries) Local Health Unit in Northern Italy. A sample was built by selecting all patients who, between 2005 and 2006, had a diagnosis of CKD and had received at least two prescriptions for ERAs. The study evaluated the durations of treatments, the RDDs (Received Daily Doses), the DCR (Dose Conversion Ratio) between epoetin and darbepoetin alfa, and the weekly costs associated with either treatment.ResultsThe original sample consisted of 415 patients (mean age: 72.9 years, 53.7% males). The mean duration of treatment was 25.29 weeks for epoetin and 22.72 weeks for darbepoetin alfa (p = 0.02). The weighted relative mean RDD was 3.72 µg for darbepoetin alfa (weekly mean dosage: 26.04 µg) and 572.57 IU for epoetin (weekly dosage mean: 4008.00 IU), with a DCR between epoetin and darbepoetin alfa of 153.94 IU: 1 µg. The weekly mean cost of treatment was € 43.40 for patients treated with epoetin and € 72.36 for patients treated with darbepoetin alfa (p < 0.001).Discussion and conclusionsAdministrative databases increasingly represent an important data source to conduct drug utilization studies. Based on data from a Local Health Unit, we performed an analysis focused on the use of ERAs in the treatment of anemia in patients with chronic kidney disease. The analysis results were interesting, particularly as attempt to estimate the DCR between epoetin and darbepoetin alfa (153.94 IU: 1 µg), which resulted consistent with other European studies. This evaluation showed that epoetin is a cost-saving strategy compared with darbepoetin alfa in the treatment of anemia in patients with chronic kidney disease. An important limitation was that patient records had not a severity of disease indicator. Probably the presence of a severity disease indicator might have helped to capture more clearly the analysis results.

Observational analysis of antineoplastic and immunomodulating drug expenditure in two Local Health Units in Northern Italy during the period 2009-2011

Background The past few years, the Italian National Health Service (INHS) has faced the challenge of ensuring sustainable costs for antineoplastic and immunomodulating drugs. The aim of this study was to analyse expenditure trends for these drugs in two Local Health Units during the period 2009-2011. Methods Data for this retrospective study were derived from the administrative databases of two Local Health Units in Northern Italy. A sample was built up by selecting all patients with at least one antineoplastic and immunomodulating drug prescription between 2009 and 2011. The study evaluated the annual, per capita and per user drug expenditure. The antineoplastic and immunomodulating drug expenditure was also analysed by therapeutic indication. Results The number of users (annual mean rate: 12.1%) and the antineoplastic and immunomodulating drug expenditure (annual mean rate: 15.7%) were increased in the three-year period. The mean annual per capita cost was €18.40 in the first year (2009), €22.18 in the second year (2010) and €24.23 in the last year (2011). Taking into account the last year of the analysis (2011), monoclonal antibody drugs showed the highest per capita drug spending (€9.36), followed by TNF-alpha inhibitors (€6.61) and tyrosine kinase inhibitors (€5.75). The highest mean annual expenditure was on cancer drugs (€15,046,773), followed by rheumatoid arthritis (€3,596,925), psoriatic arthritis (€925,510), ankylosing spondylitis (€626,050) and psoriasis (€622,332). Conclusions Spending on antineoplastic and immunomodulating drugs increased over the three-year period of the analysis and the oncological disease was the main therapeutic indication.

The experience of the Local Health authority of Pavia (northern Italy) in the management of the diabetic population of its province. An example of good balance between primary and secondary care

Purpose: Since long, the Local Health Authority (LHA) of Pavia (Lombardy, Italy) developed a model for the management of care of its diabetic population, based on a strong integration between Specialists of the hospital diabetes centres, General Practitioners (GPs) and primary care nurses. Achieved results are reported. Context: To ensure an integrated management of diabetes, the LHA has been established a multidisciplinary working-group (Department of Primary Care; Specialists of hospital diabetes centres (12); GPs; Primary Care Nurses; Pharmaceutical Service of LHA), since 2000. State of the art: In the province of Pavia there are 27,000 diabetics (5% of the residents) that account for 11% of the total annual health expenditure of LHA. The average per capita health expenditure of diabetics is € 2,400/year. LHA collects indicators (context , process, outcome) for the monitoring of management of integrated care of the diabetics. The multidisciplinary workinggroup on diabetes has defined diagnostic and treatment pathways, ad hoc protocols, (e.g.: diabetic foot, release of drivers license to diabetics, insertion of diabetic pupils in the school, management of gestational diabetes), a manual for healthy lifestyles for diabetics, treatment plans for the prescription for insulin pumps and other monitoring materials (e.g. lancets), based on pre-defined quarterly requirements. LHA organises training courses, with the aid of specialists of the hospital diabetic centres, to spread knowledge of these care pathways, guidelines and tools among health care professionals.

Cinque anni di utilizzo degli agenti stimolanti l’eritropoiesi nella terapia dell’anemia indotta da insufficienza renale nell’ASL di Pavia

BackgroundAnemia is a frequent and highly debilitating condition associated with chronic kidney disease (CKD). Epoetin (alfa or beta) and darbepoetin alfa are erythropoietin receptor agonists (ERAs) indicated for the treatment of anemia in patients with CKD. Several studies demonstrated that ERAs are effective in the treatment of CKD-related anemia by increasing hemoglobin levels.ObjectivesTo describe consumption and costs trends of ERAs in the Local Health Unit of Pavia during the period 2004–2008. We also calculated the number of patients treated with ERAs, the mean admnistration dose, the mean cost per standard unit, the dose conversion ratio (DCR) between epoetin and darbepoetin alfa and the mean cost per treated patient with epoetin or darbepoetin alfa.MethodsData for this retrospective study were derived from the administrative database of the Local Health Unit of Pavia. A sample was built by selecting all patients who had a diagnosis of CKD and received at least one ERA prescription between 2004 and 2008. The study evaluated the annual pharmaceutical spending for ERAs. We also analysed the pharmaceutical spending in order to point out the possible presence of significant cost-drivers like number of patients, Received Daily Dose or cost per μg/IU. We calculated the DCR between epoetin and darbepoetin alfa and their annual mean treatment costs.ResultsThe number of patients and the pharmaceutical spending for the treatment of CKD with ERAs increased systematically in the five-year period (10% and 12.7% annually, respectively). The number of patients is the most important cost-driver in order to explain the increase of pharmaceutical spending. The mean five-year period DCR between epoetin (alfa or beta) and darbepoetin alfa is 179.10 IU: 1 μg. The annual mean cost of treatment was €1,334.57 for patients treated with epoetin and €1,802.78 for patients treated with darbepoetin alfa.ConclusionsThe number of patients is the most important cost-driver which explains the growth of ERA consumption during the period 2004–2008. Over this five-year period, epoetin (alfa or beta) was a cost-saving strategy compared to darbepoetin alfa in the treatment of anemia in patients with CKD.