Biomedical subjects

R Bellazzi

Publications and source records attributed to R Bellazzi.

At least 19 recordsLinked to original sources

PubMed1999

Protocol-based reasoning in diabetic patient management.

We propose a system for teleconsultation in Insulin Dependent Diabetes Mellitus (IDDM) management, accessible through the use of the net. The system is able to collect monitoring data, to analyze them through a set of tools, and to suggest a therapy adjustment in order to tackle the identified metabolic problems and to fit the patient's needs. The therapy revision has been implemented through the Episodic Skeletal Planning Methodi, it generates an advice and employs it to modify the current therapeutic protocol, presenting to the physician a set of feasible solutions, among which she can choose the new one.

Adult↗

PubMed1998

A distributed system for diabetic patient management.

This paper describes a telemedicine system for diabetic patients management, presenting its architecture, the technical solutions adopted and the methodologies on which it is based. The system, designed to provide decision support in a distributed environment, is composed of two modules, a Patient Unit and a Medical Unit, connected by telecommunication services. We outline how the two modules can interact to perform an effective monitoring and a cooperative control of glucose metabolism. In particular, we detail the data analysis tasks performed by the two units and how the results are exploited to assist patients and physicians in revising and adjusting the therapeutic protocol. We will finally describe the current prototypical implementation of the system that uses HTTP as the communication protocol and HTML pages as the graphical user interface.

Diabetes Mellitus, Type 1↗

PubMed1998

A development environment for knowledge-based medical applications on the World-Wide Web.

The World-Wide Web (WWW) is increasingly being used as a platform to develop distributed applications, particularly in contexts, such as medical ones, where high usability and availability are required. In this paper we propose a methodology for the development of knowledge-based medical applications on the web, based on the use of an explicit domain ontology to automatically generate parts of the system. We describe a development environment, centred on the LISPWEB Common Lisp HTTP server, that supports this methodology, and we show how it facilitates the creation of complex web-based applications, by overcoming the limitations that normally affect the adequacy of the web for this purpose. Finally, we present an outline of a system for the management of diabetic patients built using the LISPWEB environment.

Artificial Intelligence↗

PubMed1998

A randomized study comparing methylprednisolone plus chlorambucil versus methylprednisolone plus cyclophosphamide in idiopathic membranous nephropathy.

To assess whether chlorambucil or cyclophosphamide may have a better therapeutic index in patients with idiopathic membranous nephropathy, we compared two regimens based on a 6-mo treatment, alternating every other month methylprednisolone with chlorambucil or methylprednisolone with cyclophosphamide. Patients with biopsy-proven membranous nephropathy and with a nephrotic syndrome were randomized to be given methylprednisolone (1 g intravenously for 3 consecutive days followed by oral methylprednisolone, 0.4 mg/kg per d for 27 d) alternated every other month either with chlorambucil (0.2 mg/kg per d for 30 d) or cyclophosphamide (2.5 mg/kg per d for 30 d). The whole treatment lasted 6 mo; 3 mo with corticosteroids and 3 mo with one cytotoxic drug. Among 87 patients followed for at least 1 yr, 36 of 44 (82%; 95% confidence interval [CI], 67.3 to 91.8%) assigned to methylprednisolone and chlorambucil entered complete or partial remission of the nephrotic syndrome, versus 40 of 43 (93%; 95% CI, 80.9 to 98.5%) assigned to methylprednisolone and cyclophosphamide (P = 0.116). Of patients who attained remission of the nephrotic syndrome, 11 of 36 in the chlorambucil group (30.5%) and 10 of 40 in the cyclophosphamide group (25%) had a relapse of the nephrotic syndrome between 6 and 30 mo. The reciprocal of plasma creatinine improved in the cohort groups followed for 1 yr for both treatment groups (P < 0.01) and remained unchanged when compared with basal values in the cohort groups followed for 2 and 3 yr. Six patients in the chlorambucil group and two in the cyclophosphamide group did not complete the treatment because of side effects. Four patients in the chlorambucil group but none in the cyclophosphamide group suffered from herpes zoster. One patient per group developed cancer. It is concluded that in nephrotic patients with idiopathic membranous nephropathy both treatments may be effective in favoring remission and in preserving renal function for at least 3 yr.

Adolescent↗

PubMed1998

Mining biomedical time series by combining structural analysis and temporal abstractions.

This paper describes the combination of Structural Time Series analysis and Temporal Abstractions for the interpretation of data coming from home monitoring of diabetic patients. Blood Glucose data are analyzed by a novel Bayesian technique for time series analysis. The results obtained are post-processed using Temporal Abstractions in order to extract knowledge that can be exploited "at the point of use" from physicians. The proposed data analysis procedure can be viewed as a Knowledge Discovery in Data Base process that is applied to time-varying data. The work here described is part of a Web-based telemedicine system for the management of Insulin Dependent Diabetes Mellitus patients, called T-IDDM.

Algorithms↗

PubMed1997

DT-Planner: an environment for managing dynamic decision problems.

The problem of formulating plans under uncertainty and coping with dynamic decision problems is a major task of both artificial intelligence and control theory applications in medicine. In this paper we will describe a software package, called DT-Planner, designed to represent and solve dynamic decision problems that can be modelled as Markov decision processes, by exploiting a novel graphical formalism, called influence view. An influence view is a directed acyclic graph that depicts the probabilistic relationships between the problem state variables in a generic time transition; additional variables, called event variables, may be added, in order to describe the conditional independencies between state variables. By using the specified conditional independence structure, an influence view may allow a parsimonious specification of a Markov decision process. DT-Planner lets the user specify and manage models through a user-friendly graphical interface, and implements efficient for policy determination algorithms. DT-Planner is written in C with Open Interface libraries and can be obtained, for non commercial use, via anonymous ftp without charge.

Algorithms↗

PubMed1997

In vivo study of the kinetics of thiamine and its phosphoesters in the deafferented rat cerebellum.

The effects of chemical (CD) and surgical (SD) deafferentation of the cerebellum on different steps of the metabolism of thiamine (Th), thiamine monophosphate (ThMP) and thiamine pyrophosphate (ThPP) were evaluated in vivo in rats. CD was carried out by i.p. injection of 3-acetylpyridine, followed by harmaline and niacinamide. SD was carried out by complete dissection of the peduncles of the left cerebellar hemisphere. Under steady state condition the radioactivity of Th and its phosphoesters was determined in plasma and whole cerebellum after an i.p. injection of thiazole-[2(14)C]-thiamine (30 micrograms:1.25 micro Ci). Analytical data were processed by using an improved mathematical compartmental model, which allowed the calculation of fractional rate constants (FRC), turnover rates (TR) and turnover times (TT). Both CD and SD caused a significant reduction of TR values for Th phosphorylation to ThPP, dephosphorylation of ThPP to ThMP and Th, and ThMP, but not Th, release. TT for all Th compounds were increased compared to controls, indicating a general slowing of thiamine metabolism in the deafferented cerebellum. These results indicate an imbalance in the thiamine metabolism resulting from the impaired activity of cerebellar neurons. The possible implications of the changes in rate of Th compound turnover with respect to biochemical changes in cerebellar ataxia are discussed.

Afferent Pathways↗

PubMed1996

Learning temporal probabilistic causal models from longitudinal data.

Medical problems often require the analysis and interpretation of large collections of longitudinal data in terms of a structural model of the underlying physiological behavior. A suitable way to deal with this problem is to identify a temporal causal model that may effectively explain the patterns observed in the data. Here we will concentrate on probabilistic models, that provide a convenient framework to represent and manage underspecified information; in particular, we will consider the class of Causal Probabilistic Networks (CPN). We propose a method to perform structural learning of CPNs representing time-series through model selection. Starting from a set of plausible causal structures and a collection of possibly incomplete longitudinal data, we apply a learning algorithm to extract from the data the conditional probabilities describing each model. The models are then ranked according to their performance in reconstructing the original time-series, using several scoring functions, based on one-step ahead predictions. In this paper we describe the proposed methodology through an example taken from the diabetes monitoring domain. The selection process is applied to a set of input-output models that generalize the class of ARX models, where the inputs are the insulin and meal intakes and the outputs are the blood glucose levels. Although the physiological process underlying this particular application is characterized by strong non-linearities and low data reliability, we show that it is possible to obtain meaningful results, in terms of conditional probability learning and model ranking power.

Algorithms↗

PubMed1996

Distributed intelligent data analysis in diabetic patient management.

This paper outlines the methodologies that can be used to perform an intelligent analysis of diabetic patients' data, realized in a distributed management context. We present a decision-support system architecture based on two modules, a Patient Unit and a Medical Unit, connected by telecommunication services. We stress the necessity to resort to temporal abstraction techniques, combined with time series analysis, in order to provide useful advice to patients; finally, we outline how data analysis and interpretation can be cooperatively performed by the two modules.

Computer Communication Networks↗

PubMed1995

Adaptive controllers for intelligent monitoring.

The project we describe here is aimed at assisting out-patients affected by Insulin Dependent Diabetes Mellitus. Our approach exploits the usual scheme of diabetic patients management, based on (i) a periodic evaluation of patients' metabolic control performed by the physician, and (ii) patient-tailored tables for self-adjustments of insulin dosages. Following this scheme we have defined a system built on a two-level architecture. The High Level Module exploits both medical knowledge and clinical information in order to assess an insulin protocol, defined in terms of insulin timing, type, and total amount. The High Level Module exchanges information with the Low Level Module in order to define the control actions to be taken at the low level, as well as to periodically evaluate protocol adequacy on the basis of patient data. The goal of the Low Level Module, whose characteristics can be adaptively modified by the High Level Module, is to suggest the next insulin dosage, depending on the actual blood glucose measurement and a certain pre-defined insulin delivery protocol. The Level Control Module is based on an adaptive controller, consisting of a Fuzzy Set Controller and an ARX (Autoregressive eXogenous input) Model. The scheme here presented may be conveniently viewed in a telemedicine context, in which the low level controller is implemented on a portable device communicating to the high level controller, implemented on a remote computer. A preliminary assessment has been performed, analyzing a data set of 60 patients provided by the American Association of Artificial Intelligence, Artificial Intelligence in Medicine Subgroup, and the implementation of the system is currently in progress.

Computer Simulation↗

PubMed1994

Experimental subarachnoid hemorrhage: events related to anti-oxidant enzymatic systems and eicosanoid peroxide enhancement.

Experimental and clinical studies have emphasized the role of free radicals in the pathogenesis of vasospasm and neurological dysfunction after subarachnoid hemorrhage (SAH). Increases in both enzymatic (arachidonic acid cascade and eicosanoid peroxide production) and non-enzymatic (thiobarbituric acid reactive substances production) lipid peroxidation were found, pointing out the key role of arachidonic acid cascade in impairing membrane functionality in the post-hemorrhage brain. The aim of this work is to investigate whether a correlation exists between time-dependent modifications of eicosanoid peroxide production ("ex vivo" release of leukotriene C4 = LTC4) and antioxidant enzymatic systems in the brain after experimental subarachnoid hemorrhage in the rat. The release of the LTC4 is significantly enhanced at 1, 6 and 48 hours after SAH induction. Cu-Zn superoxide dismutase (SOD) activity is significantly reduced at 6 and 48 hours after SAH induction; Mn-SOD activity is significantly affected at 1, 6 and 48 hours after the hemorrhage. GSH-Px activity is significantly reduced only in the late phase (48 hours) after SAH. The linear regression of statistical analysis, performed to investigate any possible relationship among time-dependent modifications shows that the "ex vivo" release of LTC4 is significantly related to the decreasing trend of MnSOD activity (p < 0.001). The present results suggest that after SAH, a deficit in endogenous anti-oxidant defenses may play a role in making the brain more susceptible to lipid peroxidative events.

Animals↗

PubMed1994

Reusable influence diagrams.

Influence Diagrams have been recognized as a suitable formalism for building probabilistic expert systems. Nevertheless, the most part of applications consists in stand-alone systems, concerning a very limited domain. On the other hand, Artificial Intelligence research has outlined Blackboard Architectures as the basis for building expert systems in which several knowledge sources, in general built with different formalisms, cooperate to the solution of a complex task. This paper addresses the use of influence diagrams as knowledge sources of such a system, and particularly faces the problem of reusing the same influence diagram in different inference phases. We will show that, specially in planning tasks, the modularity requirement of keeping the knowledge sources separated, may imply that an influence diagram must call another influence diagram to solve itself and to maintain the coherence of the whole set of decisions underlying the plan. Conditions for the correctness of this concatenation of knowledge sources will be provided, and an example from the medical domain of therapy planning for Acute Myeloid Leukemia will be shown, as an implemented prototype exploiting these ideas.

Acute Disease↗

PubMed1994

Enhanced LDL oxidation in uremic patients: an additional mechanism for accelerated atherosclerosis?

Since oxidized low-density lipoprotein (LDL) is more atherogenic than native LDL, LDL oxidation was investigated in uremic patients who often develop accelerated atherogenesis. Three groups of uremic patients were studied (10 on predialysis conservative therapy, 11 on repetitive hemodialysis, 13 on peritoneal dialysis) and compared with seventy matched controls. LDL oxidation was evaluated in all patients as: (i) the susceptibility to in vitro oxidation (by measuring the resistance to Cu(++)-induced formation of conjugated dienes), (ii) vitamin E concentration in LDL, and (iii) presence of plasma anti-oxidized LDL antibodies, expressed as the ratio anti-oxLDL/anti-nativeLDL antibodies. The lipid profile was studied in all patients. Vitamin E concentration did not differ between the various groups, although LDL from uremic patients appeared more susceptible to in vitro and in vivo oxidation (as demonstrated by an earlier generation of conjugated dienes and by the presence of an higher antibody ratio) compared to control subjects. Subclass analysis of the different patients revealed that peritoneal dialysis treatment ameliorated the oxidation markers. However, a prolonged dialytic treatment caused a decrease in vitamin E concentration in LDL and increased their susceptibility to oxidation.

Arteriosclerosis↗

PubMed1994

Autoantibodies against oxidatively-modified LDL in uremic patients undergoing dialysis.

Target-specific oxidation processes in LDL generate molecular epitopes that are more atherogenic than the native forms and are able to elicit an immunological reaction leading to the formation of anti-oxLDL autoantibodies (oxLDL-Ab) that may participate in the overall process of atherogenesis. Thus, the detection of oxLDLAb, in addition to mirroring the occurrence of in vivo LDL oxidation, will give valuable information on the occurrence of this immune response. Plasma oxLDLAb (IgG and IgM) were measured in 72 control subjects (CS) and in 80 patients with chronic renal failure (CRF), undergoing repetitive hemodialysis (N = 56) or peritoneal dialysis (N = 24), with an ELISA method using native LDL, CuSO4-oxidized LDL (oxLDL) or malondialdehyde-derivatized LDL (MDA-LDL) as antigens. To monitor cross reactivity of the antibodies detected with other oxidatively-modified proteins, human serum albumin (HSA) and MDA-derivatized HSA (MDA-HSA) were also employed as antigens. The antibody titer was calculated as the ratio of antibodies against modified versus native proteins. CRF patients had an antibody ratio significantly higher than CS as concerning anti-oxLDL IgG (1.39 +/- 0.36 vs. 1.05 +/- 0.3, P < 0.05) and IgM (2.15 +/- 0.75 vs. 1.43 +/- 0.43, P < 0.01), and anti-MDA-LDL IgG (3.05 +/- 0.74 vs. 2.04 +/- 0.42, P < 0.01) and IgM (5.55 +/- 1.79 vs. 2.9 +/- 0.85, P < 0.01). The anti-MDA-HSA antibody titer was also higher in CRF patients than in CS (2.49 +/- 0.5 vs. 1.46 +/- 0.39, P < 0.01 for IgG and 2.80 +/- 1.03 vs. 1.26 +/- 0.43, P < 0.01 for IgM).(ABSTRACT TRUNCATED AT 250 WORDS)

Aldehydes↗

PubMed1994

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.

Acetates↗

PubMed1994

High- and low-flux acetate-free biofiltration: experimental assessment of calcium mass balance and intact parathyroid hormone behaviour.

We studied total calcium mass balance and plasma intact parathyroid hormone behaviour in 10 uraemic patients who underwent acetate-free biofiltration carried out in accordance with six different dialytic schedules, where either a polyacrylonitrile or a polysulphone membrane was used. Schedules 1 and 2 involved a reinfusion flow rate of 33.3 ml/min with a dialysate calcium concentration (DCa) of 1.75 and 2 mmol/l respectively; in schedule 3, 4, 5 and 6 reinfusion flow rate amounted to 50 ml/min and DCa was respectively of 1.75, 2, 2.25 and 2.5 mmol/l. Dehydration remained unchanged in all schedules: 700 g/h. Finally high- and low-flux acetate-free biofiltration are able to induce different Ca mass balance which may suit different therapeutic contexts. Ca mass balance was either positive or negative depending on reinfusion flow rate and DCa. With a reinfusion flow rate of 33.3 ml/min a DCa of at least 2 mmol/l was necessary to obtain a positive mass balance, while with a reinfusion flow rate of 50 ml/min DCa had to equal 2.25 mmol/l. In high-flux acetate-free biofiltration, the estimation of predialytic Ca2+ and DCa values, using a simple formula, allows prediction of the mass balance that will be attained. At the end of acetate-free biofiltration, intact parathyroid hormone always decreased when a polyacrylonitrile membrane was employed while it increased, in the presence of negative Ca mass balance with a polysulphone membrane.

Acetates↗

PubMed1994

Long-term effect of oral calcitriol single weekly pulse in CAPD and in HD.

This study was undertaken to evaluate the long-term effect of single weekly oral pulse calcitriol therapy (0.05 mcg/kg) in 16 uremic patients. Eight (5 female, 3 male; aged 51.6 +/- 8.5 years) were on continuous ambulatory peritoneal dialysis (CAPD) for 28.8 +/- 12.7 months with basal intact parathyroid hormone (iPTH) 247 +/- 60 pg/mL. Eight (6 female, 2 male; aged 53 +/- 17.9 years) were on hemodialysis (HD) for 76.3 +/- 55 months with basal iPTH 270.9 +/- 92. Calcium dialysate was 1.75 mmol/L in all patients and serum phosphorus was controlled with CaCO3 2-4 g/day. Ca and P were measured weekly; iPTH and alkaline phosphatase were measured monthly. After two months, iPTH decreased to 132.4 +/- 89 (p < 0.05 vs basal values) in the HD patients and to 158.2 +/- 61 (p < 0.05) in the CAPD group. After six months, iPTH decreased to 108.6 +/- 73.2 (p < 0.01) in the HD patients and to 126.5 +/- 48 (p < 0.01) in the CAPD patients. Two patients (1 HD and 1 CAPD) who were not compliant with phosphate binder therapy were dropped. To control hyperphosphatemia in 1 HD patient we reduced bolus to 0.03 mcg/kg. Two CAPD patients presented hypercalcemia and required calcium dialysate of 1.25 mmol/L. In conclusion, single weekly oral pulse of calcitriol appears to be effective in suppressing mild hyperparathyroidism both in CAPD and in HD patients, even though some variations in the protocols may be required.

Administration, Oral↗

PubMed1993

Drug delivery optimization through Bayesian networks: an application to erythropoietin therapy in uremic anemia.

This paper describes how Bayesian networks can be used in combination with compartmental models to plan recombinant human erythropoietin delivery in the treatment of anemia of chronic uremic patients. Past measurements of hemoglobin concentration in a patient during the therapy can be exploited to adjust the parameters of a compartmental model of erythropoiesis. This adaptive process provides more accurate patient-specific predictions, and hence a more rational dosage planning. Inferences are performed by using a stochastic simulation algorithm called Gibbs sampling. We describe a drug delivery optimization protocol based on our approach. Some results obtained on real data are presented.

Adult↗