R. Bellazzi

Building a Normative Decision Support System for Clinical and Operational Risk Management in Hemodialysis

This paper describes the design and implementation of a decision support system for risk management in hemodialysis (HD) departments. The proposed system exploits a domain ontology to formalize the problem as a Bayesian network. It also relies on a software tool, able to automatically collect HD data, to learn the network conditional probabilities. By merging prior knowledge and the available data, the system allows to estimate risk profiles both for patients and HD departments. The risk management process is completed by an influence diagram that enables scenario analysis to choose the optimal decisions that mitigate a patients risk. The methods and design of the decision support tool are described in detail, and the derived decision model is presented. Examples and case studies are also shown. The tool is one of the few examples of normative system explicitly conceived to manage operational and clinical risks in health care environments.

Quality Assessment of Hemodialysis Services through Temporal Data Mining

This paper describes a research project that deals with the definition of methods and tools for the assessment of the clinical performance of a hemodialysis service on the basis of time series data automatically collected during the monitoring of hemodialysis sessions. While simple statistical summaries are computed to assess basic outcomes, Intelligent Data Analysis and Temporal Data mining techniques are applied to gain insight and to discover knowledge on the causes of unsatisfactory clinical results. In particular, different techniques, comprising multi-scale filtering, Temporal Abstractions, association rules discovery and subgroup discovery are applied on the time series. The paper describes the application domain, the basic goals of the project and the methodological approach applied for time series data analysis. The current results of the project, obtained on the data coming from more than 2500 dialysis sessions of 33 patients monitored for seven months, are also shown.

Acute Effects of Repetitive Hemodialysis on Circulating Immunoreactive Parathyroid Hormone Levels in Uremic Patients Undergoing Vitamin D (Calcitriol) Therapy

The acute effects on parathyroid gland activity of repetitive hemodialysis with a dialysate calcium concentration of between 3.5 and 4 mEq/l were evaluated in 21 hemodialysis patients on calcitriol therapy for 1 year or more. In this study circulating immunoreactive parathyroid hormone (iPTH) levels were measured using radioimmunoassay specific for C-terminal iPTH (C-PTH), middle molecule iPTH (MM-PTH) and intact iPTH (I-PTH), before the dialysis session at the end of the week (I), after 4 h regular hemodialysis (II) and after a further 72 h (III). C-PTH was abnormally high (202 +/- 64 pmol/l) (I) in 18 patients with no documented parathyroid hyperplasia and showed no significant difference in subsequent controls. MM-PTH was also high (379 +/- 125.5 pmol/l) (I), but decreased to 348 +/- 136.7 (II) (p less than 0.05) and returned to predialysis levels (III). I-PTH (I) was 8.2 +/- 5.3 pmol/l (normal levels in 8 patients), fell to 3.4 +/- 2.6 pmol/l (II) (p less than 0.01), and increased (p less than 0.01) with respect to the basal levels of 11.1 +/- 7.5 pmol/l (III). Three patients presented echographically documentable parathyroid hyperplasia and, despite constantly high iPTH levels, showed a similar I-PTH behavior while MM-PTH and C-PTH revealed no constant pattern. The decrease in iPTH levels was accompanied by a significant increase in total calcium and ionized calcium during the hemodialysis session. No significant changes in iCa and Ca together with I-PTH levels were found in 4 volunteers before and after the hemodialysis session with dialysate calcium 2.75 mEq/l. We conclude that I-PTH assay has been shown to capture acute changes in parathyroid gland activity in hemodialyzed patients for both low and high iPTH levels. High calcium dialysate hemodialysis inhibits acutely intradialytic PTH secretion but the effect is just temporary and the 72-hour interdialytic period, despite vitamin D therapy, stimulates parathyroid secretion significantly. Nevertheless, I-PTH fluctuations occur in some patients within the normal range, and high dialysate and calcitriol therapy seem to be capable of controlling parathyroid activity; as regards the remaining population, we suggest that a personalized therapeutic approach should be studied with a view to achieving a better control of interdialytic calcium homeostasis.

Supporting Translational Research on Inherited Cardiomyopathies through Information Technology

OBJECTIVES The INHERITANCE project, funded by the European Commission, is aimed at studying genetic or inherited Dilated cardiomyopathies (DCM) and at understanding the impact and management of the disease within families that suffer from heart conditions that are caused by DCMs. The biomedical informatics research activity of the project aims at implementing information technology solutions to support the project team in the different phases of their research, in particular in genes screening prioritization and new gene-disease association discovery. METHODS In order to manage the huge quantity of scientific, clinical and patient data generated by the project several advanced biomedical informatics tools have been developed. The paper describes a layer of software instruments to support translation of the results of the project in clinical practice as well as to support the scientific discovery process. This layer includes data warehousing, intelligent querying of the phenotype data, integrated search of biological data and knowledge repositories, text mining of the relevant literature, and case based reasoning. RESULTS At the moment, a set of 1,394 patients and 9,784 observations has been stored into the INHERITANCE data warehouse. The literature database contains more than 1,100,000 articles retrieved from the Pubmed and generically related to cardiac diseases, already analyzed for extracting medical concepts and genes. CONCLUSIONS After two years of project the data warehouse has been completely set up and the text mining tools for automatic literature analysis have been implemented and tested. A first prototype of the decision support tool for knowledge discovery and gene prioritization is available, but a more complete release is still under development.

Implementation of an automated system for monitoring adherence to hemodialysis treatment: A report of seven years of experience

OBJECTIVE In this paper we present the clinical deployment and evaluation of a computerized system, EMOSTAT, aimed at improving the quality of hemodialysis sessions. EMOSTAT automatically imports data from the hemodialysis monitoring software tools and analyzes the delivered treatment looking at six clinically relevant parameters. Failures-to-adhere (FtAs) to the planned treatment are detected and reported to the care-givers. METHODS EMOSTAT has been used for more than seven years in the management of a dialysis service located in Mede, Italy. A total of 72 patients were monitored and 21251 dialyses were collected. Data analysis is performed on the periods 2002-2005 and 2005-2008, corresponding to two different software releases. RESULTS The system had been exploited into everyday clinical practice for the entire considered period. The number of FtAs significantly decreased along the first period: the bulk blood flow FtAs decreased after the introduction of the system. Hemodialysis sessions lasted longer in the second period. Co-occurring FtAs, highlighting the presence of complex FtAs patterns, were also detected. CONCLUSIONS EMOSTAT provides an effective way to re-focus the attention of the dialysis department on the treatment plan and on its implementation. The automatic data collection and the design philosophy of EMOSTAT allowed the routine use of the system.

Assessing the quality of care for end stage renal failure patients by means of artificial intelligence methodologies

End Stage Renal Disease is a severe chronic condition that corresponds to the final stage of kidney failure. Hemodialysis (HD) is the most widely used treatment method for ESRD. The HD treatment is costly and demanding from an organizational viewpoint, requiring day hospital beds, specialized nurses and periodical visits and exams of outpatients. In order to assess the performance of HD centers, we are developing an auditing system, which resorts to (i) temporal data mining techniques, to discover relationships between the time patterns of the data automatically collected during HD sessions and the performance outcomes, and to (ii) case based reasoning (CBR) to retrieve similar time series within the HD data, in order to evaluate the frequency of critical patterns. In particular, as regards temporal data mining, two new methods for association rule discovery and temporal rule discovery have been applied to the HD time series. As regards CBR, we have implemented a case-based retrieval system, which resorts to a multi-step architecture, and exploits dimensionality reduction techniques for efficient time series indexing. The overall approach has demonstrated to be suitable for knowledge discovery and critical patterns similarity assessment on real patients’ data, and its use in the context of an auditing system for dialysis management is helping clinicians to improve their understanding of the patients behaviour.

Calcium Mass Balance and Behavior of Intact Immunoreactive Parathyroid Hormone in Acetate-Free Biofiltration: Acute and One-Year Evaluation

The present study evaluated calcium mass balance (MB) during acetate-free biofiltration (AFB) with a dialysate calcium concentration of 2 mmol/l and different ultrafiltration rates (UF; 42.5 ml/min in schedule 1 and 48.5 ml/min in schedule 3), and with a calcium concentration of 1.75 mmol/l but an UF of 43 ml/min (schedule 2). We also examined the effects of these schedules on the behavior of intact parathyroid hormone (I-PTH). AFB according to schedule 1 and 3 achieve a positive calcium MB (8.49 +/- 1.56 and 5.59 +/- 1.06 mmol, respectively), while in schedule 2 calcium MB merely balanced (0.07 +/- 2.29 mmol/l). A significant acute intradialytic I-PTH decrease was observed with all schedules; after 1 month, however, predialytic PTH values were unchanged in schedules 1 and 3, but worsening was noted in schedule 2. Subsequently, AFB was performed for 12 months employing a dialytic schedule (No. 1) involving a positive calcium balance. A year later I-PTH was significantly lower, thus proving that AFB may play an additional part in controlling secondary hyperparathyroidism.

Secondary Hyperparathyroidism, Anemia and Treatment with 1.25(OH)2D3 in Uremia

Tiziano Volpini, MD, Unit of Nephrology and Dialysis, Hospital of Vigevano, Corso Milano 19, I-27029 Vigevano (Italy) Dear Sir, We read with interest the report by Docci et al. [1] in this journal on the role of secondary hyperparathyroidism in the genesis of the hemolytic component of the anemia in uremia. The study allows the conclusion that the osmotic fragility of red blood cells in uremic and dialysis patients is increased but there is a lack of correlation between this abnormality and secondary hyperparathyroidism. To confirm this data they claim that treatment with 1.25(OH)2D3 was effective in controlling blood levels of parathyroid hormone (PTH) but unable to normalize the osmotic fragility of red blood cells in their patients. In a recent paper Docci et al. [2] report a similar failure to ameliorate the platelet function by the treatment with 1.25(OH)2D3 in uremics on conservative therapy. Massry and Akmal [3] criticize Docci et al., among other things, by the fact that their data show ‘... blood levels of PTH almost 14 times the normal value after treatment with this vitamine D metabolite...’. We observe that Docci et al. [1, 2] measured immuno-reactive parathyroid hormone (iPTH) with an antiserum which detects both the intact hormone and the C-terminal fragment and, as they say, there are probably unknown amounts of inactive or active fragments of circulating PTH in the blood of their patients. As reviewed by Massry [4], only the intact PTH and the N3⁄8-terminal fragment but not the C-terminal fragment may have a negative effect on erythropoiesis or survival of red blood cells. Many studies [5–7] have demonstrated that therapy with 1.25(OH)2D3 lowers iPTH in uremic patients; however, only a C-terminal iPTH assay has been used. To specify the effect of 6 months of therapy with 1.25(OH)ιD3 (0.25–0.5 μg daily) on secondary hyperparathyroidism, we have evaluated, before and after the treatment, the blood levels of iPTH in a group of 15 uremic patients on maintenance hemodialysis, not only with C-terminal iPTH assay but also with midregion iPTH assay. The midregion iPTH assay, as shown by Roos et al. [8], specifically reflects the parathyroid secretory activity by the antiserum for 34–64 PTH fragment. In fact midregion iPTH, but not Cterminal iPTH, clearly increases during EDTA hypocalcemia and in all hyperparathyroid sera. Moreover, this fragment is not rapidly metabolized like intact PTH or the N1⁄8-terminal fragment of PTH.