Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks

Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome to study gastrointestinal motility and in a surgical setting. This article proposes a novel methodology for the analysis of BS using hybrid convolutional and recursive neural networks. It is one of the first methods of using deep learning to be widely explored. We have developed an experimental pipeline and evaluated our results with a new dataset collected using a device with a dedicated contact microphone. Data have been collected at night-time, which is the most interesting period from a neurogastroenterological point of view. Previous works had ignored this period and instead kept brief records only during the day. Our algorithm can detect bowel sounds with an accuracy >93%. Moreover, we have achieved a very high specificity (>97%), crucial in diagnosis. The results have been checked with a medical professional, and they successfully support clinical diagnosis. We have developed a client-server system allowing medical practitioners to upload the recordings from their patients and have them analyzed online. This system is available online. Although BS research is technologically mature, it still lacks a uniform methodology, an international forum for discussion, and an open platform for data exchange, and therefore it is not commonly used. Our server could provide a starting point for establishing a common framework in BS research.

A case of acute rejection shortly after initiation of lamivudine therapy in a simultaneous pancreas and kidney recipient with viral hepatitis type B

We describe a patient with hepatitis B antigenemia, who received a simultaneous pancreas and kidney transplant, developed reactivation of hepatitis B virus infection with aminotransferase elevation, and unexpectedly suffered an acute rejection episode within a few weeks after initiation of lamivudine therapy. At the time of rejection diagnosis, the cyclosporin A (CyA) trough level was 2 times lower than before the start of lamivudine therapy. Only an improvement in liver CyA metabolism in the course of lamivudine therapy can explain such an essential decline. Thus, it is important to emphasize how crucial it is to frequently monitor the CyA level in the early period of lamivudine therapy in transplanted patients with hepatitis to ensure adequate immunosuppression and to avoid acute rejection episodes.

Plasma leptin concentration in patients with acute renal failure

BACKGROUND

Acute renal failure (ARF) is characterized by impaired excretory, endocrine, homeostatic and metabolic function of the kidneys. It is well-known that leptin is an adipose-derived polypeptide hormone which is predominantly biodegraded by the kidneys. Therefore, plasma leptin concentration is increased in chronic renal failure (CRF). However, its' concentrations in patients with ARF were not investigated until now. The aim of the present study was to evaluate plasma leptin concentration in patients with ARF.

PATIENTS AND METHODS

27 patients with ARF (age 44 +/- 4 years, BMI 26.0 +/- 0.9 kg/m2, means +/- SEM, 17 patients 15 M, 2 F recovered kidney function and 10 patients 7 M, 3 F died during the anuric phase), 27 hemodialysis patients (22 M, 5 F; age 45 +/- 2 years; BMI 26.2 +/- 0.8 kg/m2) with chronic renal failure (CRF) and 27 healthy subjects (HS) (22 M, 5 F; age 42 +/- 3 years; BMI 25.9 +/- 0.6 kg/m2) were examined. In patients with ARF, blood samples for plasma leptin and routinely assessed biochemical parameters were withdrawn before the first HD session (I), and in patients who survived a second time 5 days later during the anuric/oliguric phase (II), and a third one during the polyuric phase before discharge of the patient from hospital (III). In patients with CRF all examined parameters were estimated only once before a subsequent HD session.

RESULTS

Patients with ARF (before the first HD session) and CRF did not differ significantly with respect to BMI, serum creatinine and blood hydrogen ion concentrations. Plasma leptin level in patients with ARF before the first HD session was similar to values obtained in HS, but significantly lower (p < 0.01) than in patients with CRF (2.5 (1.9 - 8.2) vs. 3.4 (2.5 - 8.3) vs. 8.4 (2.9 - 16.9) ng/ml in ARF, HS and CRF, respectively). There was no significant difference in leptinemia between patients with ARF who survived and who died. In patients with ARF who survived, improvement ofrenal function was accompanied by a slightly (not significant) declining tendency in plasma leptin concentration (5.6 +/- 2.2 vs. 4.8 +/- 1.7 vs. 4.5 +/- 1.3 ng/ml; I, II, III phases of ARF, respectively).

CONCLUSIONS

In contrast to hemodialysis patients with chronic renal failure, patients with acute renal failure are characterized by normal plasma leptin concentration. Thus, difference in leptinemia between patients with chronic and acute renal failure seems to be due to preservation of large amounts of active renal parenchyma in ARF patients.

Influence of antihypertensive treatment with perindopril, pindolol or felodipinon plasma leptin concentration in patients with essential hypertension

Leptin - produced predominantly by adipocytes - is presumably also involved in pathogenesis of essential hypertension (EH). In the present study, we addressed the question whether and to what extent antihypertensive monotherapy does influence leptinemia in patients with mild or moderate EH. Forty-two EH patients were enrolled in this randomized, open-labeled study. In all subjects, plasma concentrations of leptin, insulin, glucose, cholesterol, triglycerides and creatinine were estimated twice - before and one month after initiation of monotherapy with perindopril, pindolol or felodipin, respectively. Plasma leptin concentration, in the afternoon and midnight, was significantly higher in patients with essential hypertension than in normotensive healthy subjects (p < 0.01). Therapy with perindopril or felodipin did not influence the daily profile of leptinemia or insulinemia, respectively. However, pindolol monotherapy showed a marked (p < 0.01) suppressive effect on the daily profile of leptinemia, but did not influence insulinemia.

CONCLUSIONS

First, patients with essential hypertension are characterized by higher plasma leptin levels as compared with normotensive healthy subjects; second, suppressive effect of pindolol on leptinemia may be of pathophysiological relevance in the course of weight gain during beta-blocker therapy.