Time series classification for the prediction of dialysis in critically ill patients using echo statenetworks

Objective: Time series often appear in medical databases, but only few machine learning methods exist that process this kind of data properly. Most modeling techniques have been designed with a static data model in mind and are not suitable for coping with the dynamic nature of time series. Recurrent neural networks (RNNs) are often used to process time series, but only a few training algorithms exist for RNNs which are complex and often yield poor results. Therefore, researchers often turn to traditional machine learning approaches, such as support vector machines (SVMs), which can easily be set up and trained and combine them with feature extraction (FE) and selection (FS) to process the high-dimensional temporal data. Recently, a new approach, called echo state networks (ESNs), has been developed to simplify the training process of RNNs. This approach allows modeling the dynamics of a system based on time series data in a straightforwardway.The objective of this study is to explore the advantages of using ESN instead of other traditional classifiers combined with FE and FS in classification problems in the intensive care unit (ICU) when the input data consists of time series. While ESNs have mostly been used to predict the future course of a time series, we use the ESN model for classification instead. Although time series often appear in medical data, little medical applications of ESNs have been studiedyet.Methods and material: ESN is used to predict the need for dialysis between the fifth and tenth day after admission in the ICU. The input time series consist of measured diuresis and creatinine values during the first 3days after admission. Data about 830 patients was used for the study, of which 82 needed dialysis between the fifth and tenth day after admission. ESN is compared to traditional classifiers, a sophisticated and a simple one, namely support vector machines and the naive Bayes (NB) classifier. Prior to the use of the SVM and NB classifier, FE and FS is required to reduce the number of input features and thus alleviate the curse dimensionality. Extensive feature extraction was applied to capture both the overall properties of the time series and the correlation between the different measurements in the time series. The feature selection method consists of a greedy hybrid filter-wrapper method using a NB classifier, which selects in each iteration the feature that improves prediction the best and shows little multicollinearity with the already selected set. Least squares regression with noise was used to train the linear readout function of the ESN to mitigate sensitivity to noise and overfitting. Fisher labeling was used to deal with the unbalanced data set. Parameter sweeps were performed to determine the optimal parameter values for the different classifiers. The area under the curve (AUC) and maximum balanced accuracy are used as performance measures. The required execution time was also measured.Results: The classification performance of the ESN shows significant difference at the 5% level compared to the performance of the SVM or the NB classifier combined with FE and FS. The NB+FE+FS, with an average AUC of 0.874, has the best classification performance. This classifier is followed by the ESN, which has an average AUC of 0.849. The SVM+FE+FS has the worst performance with an average AUC of 0.838. The computation time needed to pre-process the data and to train and test the classifier is significantly less for the ESN compared to the SVM andNB.Conclusion: It can be concluded that the use of ESN has an added value in predicting the need for dialysis through the analysis of time series data. The ESN requires significantly less processing time, needs no domain knowledge, is easy to implement, and can be configured using rules ofthumb.     

Possible dihydroepiandrosterone-induced mania

BACKGROUND: Dehydroepiandrosterone (DHEA) is among the most abundant steroids in the human body and appears to have diverse biochemical activities. This multifunctional hormone has long been a compound of interest to research psychiatrists. Its recent promotion and availability as an over-the-counter supplement to the general public has led to widespread use. Little is known about potential adverse effects of DHEA when consumed on an acute or chronic basis. We report a case of mania in an older man acutely admitted to our psychiatric facility with no previous personal or family history of bipolar disorder that appeared to be related to recent DHEA use. The patient had initiated DHEA use 6 months prior to admission and was taking 200-300 mg/day at the time of presentation. METHODS: He was treated with valproic acid 500 mg twice daily. RESULTS: The patient showed sufficient improvement to be discharged following a 7-day inpatient hospitalization. CONCLUSIONS: A wide range of medications have been associated with the induction of hypomania and mania, and we have provided a brief discussion of the potential for DHEA to trigger manic symptoms.     

Plasmalemmal pH-gradients in drug-sensitive and drug-resistant MCF-7 human breast carcinoma xenografts measured by 31P magnetic resonance spectroscopy

31p Magnetic resonance spectroscopy (MRS) was employed to investigate tumor pH in xenografts of drug-sensitive and drug-resistant MCF-7 human breast carcinoma cells. Measured extracellular pH values were found to be lower than the intracellular pH in all three tumor types investigated. The magnitude of this acid-outside plasmalemmal pH gradient increased with increasing tumor size in tumors of two drug-resistant variants of MCF-7 cells, but not in tumors of the parent (drug-sensitive) cells. The partitioning of weak-base or weak-acid drug molecules across the plasma membrane of a tumor cell is dependent upon the acid-dissociation constant (pKa) of the drug as well as the plasmalemmal pH gradient. A large acid-outside pH gradient, such as those seen in MCF-7 xenografts, can exert a protective effect on the cell from weak-base drugs such as anthracyclines and Vinca alkaloids, which have pKa values of 7.5 to 9.5. The possibility of enhancing the therapeutic efficacy of weak-base drugs by dietary or metabolic manipulation of the extracellular pH, in order to reduce or reverse the plasmalemmal pH gradient, deserves investigation.     

The changing presentation of pyloric stenosis

A triplet pregnancy in a 23-year-old woman was terminated at 15 weeks of gestation because of her severe hypertension, lung edema, and secondary hyperthyroidism. The pregnancy consisted of a hydatidiform mole with a 46,XY karyotype and two fetuses each with 46,XX and a 46,XY karyotype. To determine the zygosity and genetic origin of the mole and fetuses, PCR- and computer-assisted genotyping were performed at 27 CA-repeat marker loci that were distributed evenly over the genome. As a result, genotypes of the three pregnancy products were distinct from each other, indicating that the triplets were trizygotic. The mole lacked any maternal alleles but inherited both of the paternal alleles and/or one paternal allele in duplicate. This, along with the XY sex chromosome constitution, indicated that the mole resulted from dispermic androgenesis. The mother developed a persistent trophoblastic tumor thereafter.     

Amifostine protects normal tissues from paclitaxel toxicity while cytotoxicity against tumour cells is maintained

The objectives of this study were to evaluate the protective effects of amifostine against paclitaxel-induced toxicity to normal and malignant human tissues. Haematopoietic progenitor colony assays were used to establish the number of CFU-GEMM and BFU-E colonies after incubation with WR-1065 alone, Amifostine alone, paclitaxel (2.5 or 5 microM) +/- WR-1065 or amifostine. MTT and alkaline elution assays evaluated the in vitro growth inhibitory and DNA damaging effects, respectively, of paclitaxel with or without amifostine against normal human fibroblasts and human non-small cell lung cancer (NSCLC) cells. This combination was also evaluated in vivo using severe combined immune deficient (scid) mouse models of early (non-palpable tumours) and advanced (palpable tumours) human ovarian cancer. Human 2780 ovarian cancer cells were inoculated subcutaneously while paclitaxel and amifostine were administered intraperitoneally. A brief exposure (15 min) to amifostine not only protected human haematopoietic progenitor colonies from paclitaxel toxicity, but stimulated the growth of CFU-GEMM and BFU-E beyond control values. Amifostine protected normal human lung fibroblasts from paclitaxel-induced cytotoxicity and DNA single-strand breaks. However, paclitaxel cytotoxicity and DNA single-strand breaks were actually enhanced by pretreatment with amifostine in the NSCLC model. Importantly, amifostine did not interfere with paclitaxel antitumour activity even with prolonged exposure (24.5 h) of the lung cancer cells to high concentrations (1.2 mM) in vitro or following five repetitive high doses (200 mg/kg) given to scid mice with human ovarian cancer xenografts. Indeed, under certain circumstances, amifostine resulted in sensitisation of tumour cells to paclitaxel. Our results confirm previous reports of the ability of amifostine to protect normal tissues from the toxic effects of chemotherapy drugs and now extend these observations to paclitaxel.     

Biochemical and molecular changes at the cellular level in response to exposure to environmental estrogen-like chemicals

The pharmacokinetic and pharmacodynamic properties of nonpeptide angiotensin antagonists in humans are reviewed in this paper. Representatives of this new therapeutic class share common features: lipophilia, intermediate bioavailability, high affinity for plasma proteins and liver metabolism; some have active metabolites. Angiotensin II antagonists block the blood pressure response to exogenous angiotensin II in healthy volunteers, decrease baseline blood pressure in both normal and hypertensive patients, produce a marked rise in plasma renin activity and endogenous angiotensin II and increase renal blood flow without altering glomerular filtration rate. These effects are dose-dependent, but their time course varies between the drugs owing to pharmacokinetic and pharmacodynamic differences. Additionally, the extent of blood pressure reduction is dependent on physiological factors such as sodium and water balance. The characterisation of their pharmacokinetic-pharmacodynamic relationships deserves further refinement for designing optimal therapeutic regimens and proposing dosage adaptations in specific conditions.     

Using monoclonal antibodies to characterize a sequential epitope on the group I allergen of Bermuda grass pollen

We measured the incidence of cuff retear and injury to the suprascapular nerve after mobilization and repair of a massive rotator cuff tear. Of one hundred four rotator cuff repairs performed over a 5-year period, 10 patients (7 men and 3 women, age range 22 to 68 years) had primary repairs of massive rotator cuff tears requiring cuff mobilization and an acromioplasty as their only procedure. These patients were evaluated at a mean of 2.5 years (range 2.0 to 3.0 years) after surgery. At follow-up electromyographic examination confirmed that 1 of the 10 patients had an iatrogenic suprascapular nerve injury, whereas ultrasound evaluation revealed that 2 of 10 repairs failed. Pain relief was achieved in the eight patients with intact repairs and not in the two with recurrent tears. All patients had some limitation of active motion or strength, especially in external rotation. Thus 7 of 10 patients had neither evidence of nerve injury nor recurrent rotator cuff tears yet still showed limited active motion or weakness. It appears that operative injury to the suprascapular nerve during cuff mobilization can occur, but other factors such as inadequate cuff muscle function are more frequently responsible for the poor functional outcomes seen after successful repairs of massive rotator cuff tears.