A contrastive learning approach for ICU false arrhythmia alarm reduction

The high rate of false arrhythmia alarms in Intensive Care Units (ICUs) can lead to disruption of care, negatively impacting patients’ health through noise disturbances, and slow staff response time due to alarm fatigue. Prior false-alarm reduction approaches are often rule-based and require hand-crafted features from physiological waveforms as inputs to machine learning classifiers. Despite considerable prior efforts to address the problem, false alarms are a continuing problem in the ICUs. In this work, we present a deep learning framework to automatically learn feature representations of physiological waveforms using convolutional neural networks (CNNs) to discriminate between true vs. false arrhythmia alarms. We use Contrastive Learning to simultaneously minimize a binary cross entropy classification loss and a proposed similarity loss from pair-wise comparisons of waveform segments over time as a discriminative constraint. Furthermore, we augment our deep models with learned embeddings from a rule-based method to leverage prior domain knowledge for each alarm type. We evaluate our method using the dataset from the 2015 PhysioNet Computing in Cardiology Challenge. Ablation analysis demonstrates that Contrastive Learning significantly improves the performance of a combined deep learning and rule-based-embedding approach. Our results indicate that the final proposed deep learning framework achieves superior performance in comparison to the winning entries of the Challenge.

AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017

The PhysioNet/Computing in Cardiology (CinC) Challenge 2017 focused on differentiating AF from noise, normal or other rhythms in short term (from 9-61 s) ECG recordings performed by patients. A total of 12,186 ECGs were used: 8,528 in the public training set and 3,658 in the private hidden test set. Due to the high degree of inter-expert disagreement between a significant fraction of the expert labels we implemented a mid-competition bootstrap approach to expert relabeling of the data, levering the best performing Challenge entrants' algorithms to identify contentious labels. A total of 75 independent teams entered the Challenge using a variety of traditional and novel methods, ranging from random forests to a deep learning approach applied to the raw data in the spectral domain. Four teams won the Challenge with an equal high F1 score (averaged across all classes) of 0.83, although the top 11 algorithms scored within 2% of this. A combination of 45 algorithms identified using LASSO achieved an F1 of 0.87, indicating that a voting approach can boost performance.

An open access database for the evaluation of heart sound algorithms

In the past few decades, analysis of heart sound signals (i.e. the phonocardiogram or PCG), especially for automated heart sound segmentation and classification, has been widely studied and has been reported to have the potential value to detect pathology accurately in clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of high-quality, rigorously validated, and standardized open databases of heart sound recordings. This paper describes a public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016. The archive comprises nine different heart sound databases sourced from multiple research groups around the world. It includes 2435 heart sound recordings in total collected from 1297 healthy subjects and patients with a variety of conditions, including heart valve disease and coronary artery disease. The recordings were collected from a variety of clinical or nonclinical (such as in-home visits) environments and equipment. The length of recording varied from several seconds to several minutes. This article reports detailed information about the subjects/patients including demographics (number, age, gender), recordings (number, location, state and time length), associated synchronously recorded signals, sampling frequency and sensor type used. We also provide a brief summary of the commonly used heart sound segmentation and classification methods, including open source code provided concurrently for the Challenge. A description of the PhysioNet/CinC Challenge 2016, including the main aims, the training and test sets, the hand corrected annotations for different heart sound states, the scoring mechanism, and associated open source code are provided. In addition, several potential benefits from the public heart sound database are discussed.

False alarm reduction in critical care

High false alarm rates in the ICU decrease quality of care by slowing staff response times while increasing patient delirium through noise pollution. The 2015 PhysioNet/Computing in Cardiology Challenge provides a set of 1250 multi-parameter ICU data segments associated with critical arrhythmia alarms, and challenges the general research community to address the issue of false alarm suppression using all available signals. Each data segment was 5 minutes long (for real time analysis), ending at the time of the alarm. For retrospective analysis, we provided a further 30 seconds of data after the alarm was triggered. A total of 750 data segments were made available for training and 500 were held back for testing. Each alarm was reviewed by expert annotators, at least two of whom agreed that the alarm was either true or false. Challenge participants were invited to submit a complete, working algorithm to distinguish true from false alarms, and received a score based on their program's performance on the hidden test set. This score was based on the percentage of alarms correct, but with a penalty that weights the suppression of true alarms five times more heavily than acceptance of false alarms. We provided three example entries based on well-known, open source signal processing algorithms, to serve as a basis for comparison and as a starting point for participants to develop their own code. A total of 38 teams submitted a total of 215 entries in this year's Challenge. This editorial reviews the background issues for this challenge, the design of the challenge itself, the key achievements, and the follow-up research generated as a result of the Challenge, published in the concurrent special issue of Physiological Measurement. Additionally we make some recommendations for future changes in the field of patient monitoring as a result of the Challenge.

MIMIC-III, a freely accessible critical care database

MIMIC-III (‘Medical Information Mart for Intensive Care’) is a large, single-center database comprising information relating to patients admitted to critical care units at a large tertiary care hospital. Data includes vital signs, medications, laboratory measurements, observations and notes charted by care providers, fluid balance, procedure codes, diagnostic codes, imaging reports, hospital length of stay, survival data, and more. The database supports applications including academic and industrial research, quality improvement initiatives, and higher education coursework.

Identification and characterization of CD1-restricted T cells

Most studies of T cells have focused on those that respond to foreign peptides. However, other specialized populations of T cells exist that recognize lipid antigens and make up a substantial component of the human immune system. These lipid reactive T cells recognize antigens presented by antigen presentation molecules from the CD1 family. Four CD1 molecules exist (CD1a, CD1b, CD1c and CD1d), and each is capable of presenting a unique repertoire of lipids antigens to T cells. Much of what we have learned about lipid reactive T cells stems from studies of CD1d restricted NKT cells as these are present is both mice and humans and can be detected using CD1d/α-GalCer tetramers. In contrast, our understanding of the biology of CD1a, CD1b, CD1c restricted T cells is relatively limited. However, the recent generation of CD1a, CD1b and CD1c tetramers is helping with the identification and characterisation of these CD1-restricted T cells.

We have produced CD1 tetramers loaded with mammalian self-lipids or lipid antigens from Mycobacterium tuberculosis. In conjunction, with a tetramer-based enrichment method, we have successfully identified both autoreactive and microbial lipid antigen specific T cells from healthy human blood. We reveal the phenotypic characteristics of these CD1-restricted T cells and used CD1 mutagenesis to provide new insight into TCR recognition of CD1-lipid antigen complexes. Collectively, these studies will serve as a basis for future studies of lipid reactive T cells in health and disease.

The PhysioNet/Computing in Cardiology Challenge 2015: Reducing False Arrhythmia Alarms in the ICU

High false alarm rates in the ICU decrease quality of care by slowing staff response times while increasing patient delirium through noise pollution. The 2015 Physio-Net/Computing in Cardiology Challenge provides a set of 1,250 multi-parameter ICU data segments associated with critical arrhythmia alarms, and challenges the general research community to address the issue of false alarm suppression using all available signals. Each data segment was 5 minutes long (for real time analysis), ending at the time of the alarm. For retrospective analysis, we provided a further 30 seconds of data after the alarm was triggered. A collection of 750 data segments was made available for training and a set of 500 was held back for testing. Each alarm was reviewed by expert annotators, at least two of whom agreed that the alarm was either true or false. Challenge participants were invited to submit a complete, working algorithm to distinguish true from false alarms, and received a score based on their program's performance on the hidden test set. This score was based on the percentage of alarms correct, but with a penalty that weights the suppression of true alarms five times more heavily than acceptance of false alarms. We provided three example entries based on well-known, open source signal processing algorithms, to serve as a basis for comparison and as a starting point for participants to develop their own code. A total of 38 teams submitted a total of 215 entries in this year's Challenge.

Robust detection of heart beats in multimodal data

This editorial reviews the background issues, the design, the key achievements, and the follow-up research generated as a result of the PhysioNet/Computing in Cardiology (CinC) Challenge 2014, published in the concurrent focus issue of Physiological Measurement. Our major focus was to accelerate the development and facilitate the comparison of robust methods for locating heart beats in long-term multi-channel recordings. A public (training) database consisting of 151 032 annotated beats was compiled from records that contained ECGs as well as pulsatile signals that directly reflect cardiac activity, and other signals that may have few or no observable markers of heart beats. A separate hidden test data set (consisting of 152 478 beats) is permanently stored at PhysioNet, and a public framework has been developed to provide researchers with the ability to continue to automatically score and compare the performance of their algorithms. A scoring criteria based on the averaging of gross sensitivity, gross positive predictivity, average sensitivity, and average positive predictivity is proposed. The top three scores (as of March 2015) on the hidden test data set were 93.64%, 91.50%, and 90.70%.

Association between the CD14 gene C-159T polymorphism and serum soluble CD14 with pulmonary tuberculosis

BACKGROUND

Functional C-159T polymorphism in the promoter region of the CD14 lipopolysaccharide receptor has been reported to be associated with the development of tuberculosis (TB).

OBJECTIVE

To assess the association of CD14 C-159T polymorphism and serum soluble CD14 (sCD14) levels with pulmonary tuberculosis (TB) in an Iranian population living in a TB-endemic area.

DESIGN

A case-control study was performed prospectively on 120 newly diagnosed pulmonary TB patients and 131 healthy subjects. C-159T polymorphism was performed using amplification refractory mutation system polymerase chain reaction (ARMS-PCR). Concentrations of sCD14 were measured in serum samples using enzyme-linked immunosorbent assay.

RESULTS

The genotype frequencies of C-159T polymorphism differed significantly between TB patients and controls (P = 0.006). The risk of TB was 2.3-fold greater in individuals with the T-allele (CT + TT) in comparison to those without (OR 2.3, 95%CI 1.2-4.3, P = 0.006). Mean total sCD14 was significantly increased in the serum of patients with newly diagnosed pulmonary TB (mean ± SD = 3177 ± 751 ng/ml) compared to healthy controls (mean ± SD = 2955 ± 424 ng/ml, P < 0.004).

CONCLUSION

These data indicate that the C-159T polymorphism of the CD14 gene is associated with TB; serum sCD14 levels were higher in TB patients in a sample of the Iranian population.

In situ monitoring of adipogenesis with human-adipose-derived stem cells using surface-enhanced Raman spectroscopy

Methods capable of nondestructively collecting high-quality, real-time chemical information from living human stem cells are of increasing importance given the escalating relevance of stem cells in therapeutic and regenerative medicines. Raman spectroscopy is one such technique that can nondestructively collect real-time chemical information. Living cells uptake gold nanoparticles and transport these particles through an endosomal pathway. Once inside the endosome, nanoparticles aggregate into clusters that give rise to large spectroscopic enhancements that can be used to elucidate local chemical environments through the use of surface-enhanced Raman spectroscopy. This report uses 40-nm colloidal gold nanoparticles to create volumes of surface-enhanced Raman scattering (SERS) within living human-adipose-derived adult stem cells enabling molecular information to be monitored. We exploit this method to spectroscopically observe chemical changes that occur during the adipogenic differentiation of human-adipose-derived stem cells over a period of 22 days. It is shown that intracellular SERS is able to detect the production of lipids as little as one day after the onset of adipogenesis and that a complex interplay between lipids, proteins, and chemical messengers can be observed shortly thereafter. After 22 days of differentiation, the cells show visible and spectroscopic indications of completed adipogenesis yet still share spectral features common to the progenitor stem cells.

Statistically significant Raman detection of midsequence single nucleotide polymorphisms

This report highlights methodologies that enable statistically significant data to be collected for single nucleotide polymorphisms using surface enhanced Raman spectroscopy. Single-stranded oligonucleotides functionalized with 40 nm gold nanoparticles are hybridized with oligonucleotides adsorbed to a photolithographically defined gold surface thus creating a surface enhanced Raman environment around the DNA duplex. With this design characteristic Raman spectra have been collected and explored for differences between DNA duplexes formed from complementary oligonucleotides, completely mismatched oligonucleotides, and those formed from oligonucleotides that have a midsequence single nucleotide mismatch. The results show that statistically significant differences in Raman intensity for characteristic peaks can be collected for the three cases.

Simultaneous decoupled detection of dopamine and oxygen using pyrolyzed carbon microarrays and fast-scan cyclic voltammetry

Microfabricated structures utilizing pyrolyzed photoresist have been shown to be useful for monitoring electrochemical processes. These previous studies, however, were limited to constant-potential measurements and slow-scan voltammetry. The work described in this paper utilizes microfabrication processes to produce devices that enable multiple fast-scan cyclic voltammetry (FSCV) waveforms to be applied to different electrodes on a single substrate. This enabled the simultaneous, decoupled detection of dopamine and oxygen. In this paper we describe the fabrication process of these arrays and show that pyrolyzed photoresist electrodes possess surface chemistry and electrochemical properties comparable to PAN-type, T-650, carbon fiber microelectrodes using background-subtracted FSCV. The functionality of the array is discussed in terms of the degree of cross talk in response to flow injections of physiologically relevant concentrations of dopamine and oxygen. Finally, other applications of pyrolyzed photoresist microelectrode arrays are shown, including spatially resolved detection of analytes and combining FSCV with amperometry for the detection of dopamine.

A Parallel Computing Platform for Real-Time Haptic Interaction with Deformable Bodies

Real-time simulation of haptic interaction with deformable objects is computationally demanding. In particular in finite-element (FE) based analysis of such interactions, a large system of equations must be solved at an update rate of 100-1,000 Hz for simulation fidelity and stability. A new hardware-based parallel implementation of a Preconditioned Conjugate Gradient (PCG) algorithm is proposed for solving the linear systems of equations arising from FE-based deformation models. Concurrent utilization of a large number of fixed-point computing units on a Field-Programmable Gate Array (FPGA) device yields a very fast solution to these equations. Quantization and overflow errors in the fixed-point implementation of the iterative solver are minimized through dynamic scaling and preconditioning. Numerical accuracy of the solution, the architecture design, and issues pertaining to the degree of parallelism and scalability of the architecture are discussed in detail. The implementation of the solver on an Altera EP3SE110 FPGA device has enabled real-time simulation of three-dimensional linear elastic deformation models with 1,500 nodes at an update rate of up to 2,500 Hz.

Enhancing Electrochemical Detection by Scaling Solid State Nanogaps

The ability to quickly and inexpensively fabricate planar solid state nanogaps has enabled research to be effectively performed on devices down to just a few nanometers. Here, nanofabricated electrode pairs with electrode-to-electrode spacings of <4, 6 and 20 nm are utilized for monitoring an electroactive molecules, dopamine, in ionic solution. The results show a several order of magnitude enhancement of the electrochemical signal, collected current, for the solid state nanogaps with 6 nm electrode-electrode spacings as compared to traditional microelectrodes. The data from the <4 nm and 20 nm solid state nanogaps verify that this enhancement is due to cycling of the redox molecules in the confined geometry of the nanogap. In addition the data collected for the <4 nm nanogap emphasizes and reinforces that scaling does have limits and that as device sizes move to the few nanometer scale, the influence of a molecule's size and other physical properties becomes increasingly important and can eventually dominate the generated signals.

Using surface-enhanced Raman spectroscopy to probe for genetic markers on single-stranded DNA

Methods capable of quickly and inexpensively collecting genetic information are of increasing importance. We report a method of using surface-enhanced Raman spectroscopy to probe single-stranded DNA for genetic markers. This unique approach is used to analyze unmodified genes of moderate length for genetic markers by hybridizing native test oligonucleotides into a surface-enhanced Raman complex, vastly increasing detection sensitivity as compared to traditional Raman spectroscopy. The Raman complex is formed by sandwiching the test DNA between 40-nm gold nanoparticles and a photolithographically defined gold surface. With this design, we are able to collect characteristic Raman spectra about the test DNA and to detect genetic markers such as single-nucleotide polymorphisms (SNPs) and polymorphic regions. Results show that strands containing one of three different types of polymorphism can be differentiated using statistically significant trends regarding Raman intensity.

Solid state nanogaps for differential measurements of molecular properties

This paper demonstrates the production and probing of solid state nanogaps. These nanogaps can be inexpensively and controllably produced using a combination of molecular and standard photolithography. These nanogaps are implemented for chemical monitoring by using surface enhanced Raman spectroscopy to collect molecular information at the nanogap and current-voltage traces to probe the charge transport of the nanogap. These data show that the oligonucleotides used as the molecular resist are degraded, that some of the degraded oligonucleotides are removed, and then new oligonucleotides are adsorbed.

Dietetic guidelines: diet in secondary prevention of cardiovascular disease (first update, June 2003)

AIM

To update dietetic guidelines summarizing the systematic review evidence on dietary advice to prevent further events in people with existing cardiovascular disease (CVD) (secondary prevention).

METHODS

The Cochrane Library, MEDLINE and EMBASE were comprehensively searched to November 2002 for systematic reviews on aspects of diet and heart health. Reviews were included if they searched systematically for randomised controlled trials relating to diet and secondary prevention of CVD. Two members of the UK Heart Health and Thoracic Dietitians Group critically appraised each review. The quality and results of each review were discussed and summarized in a meeting of the whole group.

RESULTS

Providing evidence-based dietary information (including increasing omega-3 fat intake) to all people who have had a myocardial infarction will save more lives than concentrating dietary advice on just those in need of weight loss or lipid lowering. The practice of prioritizing dietetic time in secondary prevention to those with raised lipids is out of date since the advent of statin therapy. However, effective dietary advice for those with angina, stroke, peripheral vascular disease or heart failure is less clear.

CONCLUSION

There is good systematic review evidence that dietary advice to those with coronary heart disease can reduce mortality and morbidity as well as modify some risk factors. Dietary advice that does this most effectively should be prioritized.

The quality of care in Barrett's esophagus: endoscopist and pathologist practices

BACKGROUND

The diagnosis of Barrett's esophagus (BE) has important psychological and economic implications. Although accepted standards for endoscopic biopsy methods and pathological interpretation for BE exist, adherence to these standards as a measure of the quality of care in BE has not been evaluated. Our aim was to assess the quality of care in BE by evaluating the process of care and adherence to accepted standards of practice.

METHODS

Explicit process-of-care criteria were developed using a systematic literature review and expert opinion in four domains of care: the quality of biopsy methods, the adequacy in identifying endoscopic landmarks, endoscopist-pathologist communication, and pathological interpretation and reporting. We reviewed all endoscopy and pathology reports of BE patients at two institutions from 1994-1997. An academic medical center (N = 237) with staff endoscopists and an academically affiliated community hospital (N = 100) with private-practice endoscopists were analyzed.

RESULTS

Physicians showed the highest adherence to accepted standards of care in the "adequacy of identifying landmarks" and "endoscopist-pathologist communication" domains, with a > or =70% adherence rate in most criteria. Conversely, physicians demonstrated the poorest adherence with the "quality of biopsy methods" and "pathologist interpretation and reporting" domains, with adherence rates frequently <60%. Significantly, biopsies were taken in the presence of visible esophagitis 35% of the time. Performance on several of the quality indicators varied significantly by the practice setting.

CONCLUSIONS

We have identified several opportunities for quality improvement efforts. In every domain, there is room for improvement, particularly in the quality of biopsy methods. As initiatives to screen the large population of gastroesophageal reflux disease patients for BE may be imminent, the time is now to define the critical process-of-care measures to minimize the risk of overdiagnosis and inadequate endoscopic surveillance.

Alternative case definitions of ventilator-associated pneumonia identify different patients in a surgical intensive care unit

Diagnostic criteria that define ventilator-associated pneumonia (VAP) remain controversial. The purpose of this study was to evaluate common definitions of VAP and determine their relationship to each other and clinical treatment. This study prospectively evaluated several diagnostic criteria that define VAP in a cohort of 255 consecutive SICU patients ventilated for < 48 h. Definitions evaluated include the CDC definitions, the Johanson definitions which do not rely on culture data, the Physician's Probable diagnosis which relies on positive quantitative cultures, and the antibiotic treatment group. Forty-four patients (17%) received antibiotic treatment for VAP. Depending on the definition evaluated, criteria were met for a diagnosis of VAP from as low as 4% of patients by the Johanson definition to as high as 48% of patients by the CDC definition. There was poor agreement among the definitions in their ability to select the same patient as having VAP. Besides duration of mechanical ventilation and tube feeding, which were risk factors that predicted meeting the criteria for all groups, risk factors predicting VAP varied among the definitions. This study demonstrates that in a surgical ICU, the candidate definitions of pneumonia evaluated show little agreement. The particular case definition chosen to diagnose VAP will determine the incidence rate of pneumonia, the time to onset of pneumonia, and the risk factors of the type of patient treated.

Practical application of sharing surveillance data

This article provides several practical and effective mechanisms for reporting meaningful information on nosocomial infections to critical care and other specific units. Roadblocks and a small sample of hospital practices for reporting unit-specific infections are described. Graphic presentations, especially line-stay histograms, are recommended.

Physiological and genetic aspects of abortive infection of a Shigella sonnei strain by coliphage T7

Phage T7 adsorbed to and lysed cells of Shigella sonnei D(2) 371-48, although the average burst size was only 0.1 phage per cell (abortive infection). No mechanism of host-controlled modification was involved. Upon infection, T7 rapidly degraded host deoxyribonucleic acid (DNA) to acid-soluble material. Phage-directed DNA synthesis was initiated normally, but after a few minutes the pool of phage DNA, including the parental DNA, was degraded. Addition of chloramphenicol, at the time of phage infection, prevented both the initiation of phage-directed DNA synthesis and the degradation of parental phage DNA. Addition of chloramphenicol 4.5 min after phage was added permitted the onset of phage-directed DNA synthesis but prevented breakdown of phage DNA. Mutants of T7 (ss(-) mutants) have been isolated which show normal growth in strain D(2) 371-48. Upon mixed infection of this strain with T7 wild type and an ss(-) mutant, infection was abortive; no complementation occurred. The DNA of the ss(-) mutants was degraded in mixed infection like that of the wild type. Revertant mutants which have lost their ability to grow on D(2) 371-48 were isolated from ss(-) mutants; they are, in essence, phenotypically like T7 wild type. Independently isolated revertants of ss(-) mutants did not produce ss(-) recombinants when they were crossed among themselves. When independently isolated ss(-) mutants were crossed with each other, wild-type recombinants were found; ss(-) mutants could then be mapped in a cluster compatible with the length of one cistron. We concluded that T7 codes for an active, chloramphenicol-sensitive function [ss(+) function (for suicide in Shigella)] which leads to the breakdown of phage DNA in the Shigella host.