An Intelligent Search & Retrieval System (IRIS) and Clinical and Research Repository for Decision Support Based on Machine Learning and Joint Kernel-based Supervised Hashing.

Large-scale, multi-site collaboration is becoming indispensable for a wide range of research and clinical activities in oncology. To facilitate the next generation of advances in cancer biology, precision oncology and the population sciences it will be necessary to develop and implement data management and analytic tools that empower investigators to reliably and objectively detect, characterize and chronicle the phenotypic and genomic changes that occur during the transformation from the benign to cancerous state and throughout the course of disease progression. To facilitate these efforts it is incumbent upon the informatics community to establish the workflows and architectures that automate the aggregation and organization of a growing range and number of clinical data types and modalities ranging from new molecular and laboratory tests to sophisticated diagnostic imaging studies. In an attempt to meet those challenges, leading health care centers across the country are making steep investments to establish enterprise-wide, data warehouses. A significant limitation of many data warehouses, however, is that they are designed to support only alphanumeric information. In contrast to those traditional designs, the system that we have developed supports automated collection and mining of multimodal data including genomics, digital pathology and radiology images. In this paper, our team describes the design, development and implementation of a multi-modal, Clinical & Research Data Warehouse (CRDW) that is tightly integrated with a suite of computational and machine-learning tools to provide actionable insight into the underlying characteristics of the tumor environment that would not be revealed using standard methods and tools. The System features a flexible Extract, Transform and Load (ETL) interface that enables it to adapt to aggregate data originating from different clinical and research sources depending on the specific EHR and other data sources utilized at a given deployment site.

CardioSim: a PC-based cardiac signal simulator using segmental modeling of electrocardiogram.

Background: ECG modeling has wide application in signal representation, compression and synthetic ECG generation. Method: CardioSim generates synthetic ECG waveform in real-time using PC-based system. It provides dual facility of interface-based visualization with hardware-based waveform generation. It has two stages viz., development of reference model parameter database using Fourier model and generation of synthetic ECG waveform based on user defined parameters using normal and abnormal records (H, APC, PVC, LBBB, RBBB, P) from mitdb under PhysioNet. Result: It generates ten various ECG waveforms including one healthy and nine diseased rhythms from a single dynamic model with flexible user defined parameters. It gives higher reconstruction performance in terms of SNR and MSE. The mean SNR for different beat morphology is 89.2(H), 88.37(V), 86.32(A), 85.35(L), 97.22(P) and 83.3(R) and mean MSE is 2.45 × 10-6(H), 3.14 × 10-6(V), 8.98 × 10-6(A), 5.82 × 10-6(L), 0.43 × 10-6(P) and 0.25 × 10-6(R). Conclusion: It improves the performance parameters over published research work on ECG modeling and simulation. It can be used as a self-learning tool for entry level medical students.

A retrospective analysis of serological & molecular testing data on dengue fever in Kolkata & adjacent districts during 2016-2019.

Background & objectives: Regional Virus Research and Diagnostic Laboratory established at ICMR-National Institute of Cholera and Enteric Diseases (NICED) regularly receives samples for dengue screening and serotyping from patients of acute febrile illness (AFI) from Kolkata and adjacent districts. In this study, data over a three year period (August 2016-July 2019) was retrospectively analyzed to provide insight into the epidemiological trends of dengue fever in this region. Methods: Serological screening of dengue was performed by detection of NS1 antigen and/or immunoglobulin M (IgM) antibody. Dengue serotyping was done by conventional or real-time reverse transcriptase-PCR. The data were analyzed to describe the distribution of dengue with respect to age of patient, duration of fever on the day of blood collection and month of the year. Zip codes were used for spatial plotting. Results: Out of the 24,474 samples received from Kolkata and its adjacent districts (Hooghly, Howrah, North and South 24 Parganas), 38.3 per cent (95% confidence interval: 37.7-38.9%) samples were screened positive for dengue. The correlation between age and dengue positivity was found to be weak. A combination of dengue NS1 antigen and dengue IgM antibody detection may be a better option for detecting dengue positivity compared to a single test. Most AFI cases were tested from August to November during the study period, with maximum dengue positivity noted during September (45.9%). The predominant serotype of 2016, dengue virus serotype 1 (DENV-1), was almost entirely replaced by DENV-2 in 2017 and 2018. Interpretation & conclusions: Dengue continues to be an important cause of AFI in the region and round-the-year preventive measures are required for its control. Serotype switching is alarming and should be monitored routinely.

On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks.

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.

Assessing sustainable development prospects through remote sensing: A review.

The Earth's ecosystems face severe environmental stress from unsustainable socioeconomic development linked to population growth, urbanization, and industrialization. Governments worldwide are interested in sustainability measures to address these issues. Remote sensing allows for the measurement, integration, and presentation of useful information for effective decision-making at various temporal and spatial scales. Scientists and decision-makers have endorsed extensive use of remote sensing to bridge gaps among disciplines and achieve sustainable development. This paper presents an extensive review of remote sensing technology used to support sustainable development efforts, with a focus on natural resource management and assessment of natural hazards. We further explore how remote sensing can be used in a cross-cutting, interdisciplinary manner to support decision-making aimed at addressing sustainable development challenges. Remote sensing technology has improved significantly in terms of sensor resolution, data acquisition time, and accessibility over the past several years. This technology has also been widely applied to address key issues and challenges in sustainability. Furthermore, an evaluation of the suitability and limitations of various satellite-derived indices proposed in the literature for assessing sustainable development goals showed that these older indices still perform reasonably well. Nevertheless, with advancements in sensor radiometry and resolution, they were less exploited and new indices are less explored.

Geographical distribution of primary & secondary dengue cases in India - 2017: A cross-sectional multicentric study.

Background & objectives: Dengue virus infection is endemic in India with all the four serotypes of dengue virus in circulation. This study was aimed to determine the geographic distribution of the primary and secondary dengue cases in India. Methods: A multicentre cross-sectional study was conducted at Department of Health Research / Indian Council of Medical Research (DHR)/(ICMR) viral research and diagnostic laboratories (VRDLs) and selected ICMR institutes located in India. Only laboratory-confirmed dengue cases with date of onset of illness less than or equal to seven days were included between September and October 2017. Dengue NS1 antigen ELISA and anti-dengue IgM capture ELISA were used to diagnose dengue cases while anti-dengue IgG capture ELISA was used for identifying the secondary dengue cases. Results: Of the 1372 dengue cases, 897 (65%) were classified as primary dengue and 475 (35%) as secondary dengue cases. However, the proportion varied widely geographically, with Theni, Tamil Nadu; Tirupati, Andhra Pradesh and Udupi-Manipal, Karnataka reporting more than 65 per cent secondary dengue cases while Srinagar, Jammu and Kashmir reporting as low as 10 per cent of the same. The median age of primary dengue cases was 25 yr [interquartile range (IQR 17-35] while that of secondary dengue cases was 23 yr (IQR 13.5-34). Secondary dengue was around 50 per cent among the children belonging to the age group 6-10 yr while it ranged between 20-43 per cent among other age groups. Interpretation & conclusions: Our findings showed a wide geographical variation in the distribution of primary and secondary dengue cases in India. It would prove beneficial to include primary and secondary dengue differentiation protocol in the national dengue surveillance programme.

Comparison of efficacy and cost-effectiveness of 0.55% ortho-phthalaldehyde and 2% glutaraldehyde for disinfection of laryngoscopes: A prospective pilot study.

BACKGROUND AND AIMS: The laryngoscope is a potential source of cross-infection as it involves contact with the mucous membrane, saliva and occasionally blood. This study compared efficacy and cost-effectiveness of two Centre for Disease Control approved agents for disinfection of laryngoscope blades. METHODS: One hundred and sixty patients requiring laryngoscopy and intubation for general anaesthesia were randomly allocated into two groups. After tracheal intubation, used laryngoscope blades were cleaned with tap water. The blades were then immersed in either 2% w/v glutaraldehyde for a contact time of 20 min or 0.55% w/v ortho-phthalaldehyde (OPA) for 10 min. The handles were wiped with 0.5% w/v chlorhexidine wipes. Samples were collected using sterile cotton swabs from the tip, flange and light bulb area of the laryngoscope blade and one from the handle. They were cultured aerobically on blood and McConkey agar. RESULTS: In 2% glutaraldehyde group, of 240 samples sent from the blades, 2 (0.8%) showed the growth of methicillin-resistant coagulase-negative staphylococci (MRCONS) and Enterobacter. In OPA group, of 240 samples, 2 (0.8%) showed growth of MRCONS. Thus, 2% glutaraldehyde and 0.55% OPA were comparable in terms of efficacy of disinfection. Growth was seen on 4 out of 160 handles. CONCLUSIONS: We suggest OPA for high-level disinfection of laryngoscope blades as it is equally efficacious as compared to glutaraldehyde, with a shorter contact time and available as a ready to use formulation.

Carba NP as a simpler, rapid, cost-effective, and a more sensitive alternative to other phenotypic tests for detection of carbapenem resistance in routine diagnostic laboratories.

PURPOSE: Resistance to carbapenems due to carbapenemases has been increasingly noticed in Enterobacteriaceae. Clinical and Laboratory Standards Institute (CLSI) has recommended the latest Carba NP (CNP) test as a confirmatory test for carbapenemase production in Enterobacteriaceae. Low sensitivity of disk diffusion (DD) and modified Hodge test (MHT) may result in missing out of resistant strains which can adversely affect clinical management. The present study compares three phenotypic tests - CNP test, DD, and MHT for detection of carbapenemase production. MATERIALS AND METHODS: Four hundred consecutive, nonduplicate Enterobacteriaceae isolates were tested for carbapenem resistance using ertapenem disc (10 µg) by Kirby-Bauer DD method, MHT, and CNP. These tests were performed and interpreted as per the CLSI standards. CNP was considered to be the reference test for comparison. Sensitivity, specificity, and accuracy rates for ertapenem DD and MHT were calculated. RESULTS: One hundred and six out of 400 strains were positive by CNP test. Of the 294 CNP-negative strains, 28 were resistant by DD and 18 were resistant by MHT. Of the 106 CNP-positive strains, 82 were resistant and 16 were intermediate by DD while 76 were positive by MHT ertapenem DD had a sensitivity and specificity of 66.04% and 90.48%, respectively. Sensitivity and specificity of MHT were 54.72% and 93.88%, respectively. There was considerable discordance between all the three tests. CONCLUSION: As a rapid, simple, and cost-effective test with a greater capability greater to detect carbapenemase producers, CNP can be implemented in routine diagnostic laboratories, thereby benefiting patient care and antimicrobial stewardship.

Quality Aware Compression of Electrocardiogram Using Principal Component Analysis.

Electrocardiogram (ECG) compression finds wide application in various patient monitoring purposes. Quality control in ECG compression ensures reconstruction quality and its clinical acceptance for diagnostic decision making. In this paper, a quality aware compression method of single lead ECG is described using principal component analysis (PCA). After pre-processing, beat extraction and PCA decomposition, two independent quality criteria, namely, bit rate control (BRC) or error control (EC) criteria were set to select optimal principal components, eigenvectors and their quantization level to achieve desired bit rate or error measure. The selected principal components and eigenvectors were finally compressed using a modified delta and Huffman encoder. The algorithms were validated with 32 sets of MIT Arrhythmia data and 60 normal and 30 sets of diagnostic ECG data from PTB Diagnostic ECG data ptbdb, all at 1 kHz sampling. For BRC with a CR threshold of 40, an average Compression Ratio (CR), percentage root mean squared difference normalized (PRDN) and maximum absolute error (MAE) of 50.74, 16.22 and 0.243 mV respectively were obtained. For EC with an upper limit of 5 % PRDN and 0.1 mV MAE, the average CR, PRDN and MAE of 9.48, 4.13 and 0.049 mV respectively were obtained. For mitdb data 117, the reconstruction quality could be preserved up to CR of 68.96 by extending the BRC threshold. The proposed method yields better results than recently published works on quality controlled ECG compression.

Caspofungin MIC Distribution amongst Commonly Isolated Candida Species in a Tertiary Care Centre - An Indian Experience.

INTRODUCTION: Emergence of Candida species resistant to Amphotericin B and triazole has led to use of echinocandins, mostly caspofungin in the management of invasive candidiasis. There are some published reports of caspofungin resistance in Candida species yet no studies on caspofungin susceptibility pattern of Candida species exist in Indian setup. AIM: To carry out the antifungal susceptibility of Candida isolates against caspofungin. MATERIALS AND METHODS: In a retrospective study at a tertiary care teaching hospital, 60 preserved Candida isolates from inpatients of invasive candidiasis obtained over a period of 6 months from January 2015 to June 2015 were subjected to antifungal susceptibility to caspofungin and the Minimum Inhibitory Concentrations (MICs) of Candida species to caspofungin were determined by Epsilometer test (E-test). RESULTS: Thirty Candida albicans and 30 Non albicansCandida mainly Candida glabrata, Candida parapsilosis and Candida tropicalis were tested for caspofungin susceptibitity by E-test. Caspofungin resistance was detected in 6.67% Candida albicans isolates. Caspofungin resistance was not observed in Candida parapsilosis, Candida glabrata and Candida tropicalis. This shows that caspofungin resistance is still rare. Further elaborate studies with clinical correlation data are needed to detect prevalence of caspofungin resistance. CONCLUSION: Emergence of resistance in our study warrants need of elaborate studies with clinical correlation data to detect prevalence of resistance to caspofungin. E-test method proved to be an easy and simple technique for testing susceptibility of Candida to caspofungin.