Decision trees based on automatic learning and their use in cardiology

Computerized information systems, especially decision support systems, have become an increasingly important role in medical applications, particularly in those where important decision must be made effectively and reliably. But the possibility of using computers in medical decision making is limited by many difficulties, including the complexity of conventional computer languages, methodologies and tools. Thus a conceptual simple decision making model with the possibility of automating learning should be used. In this paper we introduce a cardiological knowledge-based system based on the decision tree approach supporting the mitral valve prolapse determination. Prolapse is defined as the displacement of a bodily part from its normal position. The term mitral valve prolaps (PMV), therefore, implies that the mitral leaflets are displaced relative to some structure, generally taken to be the mitral annulus. The implications of the PMV are the following: disturbed normal laminar blood flow, turbulence of the blood flow, injury of the chordae tendinae, the possibility of thrombus's composition, bacterial endocarditis, and finally hemodynamic changes defined as mitral insufficiency and mitral regurgitation. Uncertainty persists about how it should be diagnosed and about its clinical importance. It is our deep belief that the echocardiography enables properly trained experts armed with proper criteria to evaluate PMV almost 100%. But unfortunately, there are some problems concerned with the use of echocardiography. In that manner we have decided to start a research project aimed at finding new criteria and enabling the general practitioner to evaluate PMV using conventional methods and to select potential patients from the general population. To empower one to perform needed activities we have developed a computer tool called ROSE (computeRised prOlaps Syndrom dEtermination) based on algorithms of automatic learning. This tool supports the definition of new criteria and the selection of potential PMV-patients.     

Intensive retreatment of adults and children with acute lymphoblastic leukemia.

Twenty-three patients (16 adults) failing their first or subsequent (n = 8) intensive treatment for de novo acute lymphoblastic leukemia (ALL) and chronic myeloid leukemia lymphoid blast phase (n = 2) were managed with protocol POG 8201, originally introduced in relapsed ALL of childhood. In this programme, a four-drug induction phase is followed by early consolidation with teniposide-cytarabine, intrathecal chemotherapy, continuation weekly chemotherapy alternating teniposide-cytarabine with vincristine-cyclophosphamide, and periodic reinduction courses. Fourteen adults and five children with ALL achieved a complete response (CR) (86 per cent). The highest response rate (100 per cent) was obtained in 12 patients treated at first relapse after an initial CR of greater than 18 months (p = 0.07). Median duration of CR was 8 months in adults and 11 months in children. A longer than previous one CR (inversion) was obtained in four cases. Four ALL patients were successfully transplanted from a matched sibling after 3-11 months from achievement of CR. Median overall survival in adults with ALL was 11 months, significantly longer than for 40 comparable cases treated intensively but without rotational continuation therapy in previous years (p less than 0.001). This regimen is applicable to adults with relapsed ALL, where prolongation of survival may allow time for effective salvage with bone marrow transplantation.     

Renal effect of anti-hypertensive drugs depends on sodium diet in the excision remnant kidney model.

Angiotensin converting enzyme inhibitors (ACEI) are believed to protect remnant kidney, but all previous studies used the ligation model which causes severe hypertension, and very few have compared drugs in rats having similar control of blood pressure (BP). We compared rats with uremia obtained by 70% excision of total renal mass, a model which causes mild, late hypertension. Study I compared the effects of enalapril (E), cicletanine (C) and placebo (P) in uremic (U) rats fed a 0.50% (normal-high) Na diet. Study II compared the effects of E, C, P, and guanfacine (G) in U rats fed a diet restricted to 0.25% Na (normal-low). In study I, UP rats developed progressive hypertension (140, 146, 160 and 166 mm Hg at 3, 6, 9 and 12 weeks), proteinuria (240 mg/day at 9 and 12 weeks) which were not affected by E or C. The occurrence of end-stage renal disease (ESRD) led to the sacrifice of all rats after three months. All three groups had similar severe renal lesions (over 25% sclerosed glomeruli in 5 of 10 UP, 9 of 14 UE, 7 of 14 UC rats, with huge cystic tubular dilatations). In study II, rats could be sacrificed later (6 months) and had evidence of less severe renal disease. All the drugs tested prevented hypertension throughout the study (P less than 0.001), with lowest values in UE rats. E and G, but not C, reduced proteinuria. Renal damage was reduced with E and G, but not with C, despite similar BP in C and G rats. Thus, in contrast with what was obtained in the ligation model, ACEI affected neither the BP nor the renal lesions of rats made uremic by renal excision and fed a 0.50% Na diet. Moderate Na restriction improved the consequences of nephron loss and restored the anti-hypertensive effect of drugs. However, these drugs had a different effect on renal preservation: it was dramatic with E, good with G, and undetectable with C.     

Somatosensory evoked potential monitoring during intracranial surgery

In the neurosurgical approach to intracranial aneurysms which are often accompanied by arterial spasm and cortical ischaemia, monitoring procedures aim to obtain useful information on cerebral function. SEPs evoked by stimulation of the median nerve at the wrist and of the tibial nerve at the medial malleolus were registered in 45 patients with intracranial aneurysms during neurosurgical procedures. Our results show SEP abnormalities during different stages of neurosurgical procedures in 36 patients out of the monitored 45. Significant abnormalities of SEPs with respect to the control group were decrease of the amplitude of N 20-P 25 complex, lengthening of the absolute latency of the waves N 20- and P 25 and lengthening of the central conduction time (CCT) (N 13-N 20). The greatest SEP abnormalities were registered during the neurosurgical approach to aneurysm and during the clipping procedure. However, the changes were reversible in the majority of the patients. The aim of this paper was to focus on early detection of some cerebral function disturbances during the neurosurgical procedure as well as the prevention of possible brain damage.