Improving the Accuracy of Continuous Blood Glucose Measurement Using Personalized Calibration and Machine Learning.

Despite tremendous developments in continuous blood glucose measurement (CBGM) sensors, they are still not accurate for all patients with diabetes. As glucose concentration in the blood is <1% of the total blood volume, it is challenging to accurately measure glucose levels in the interstitial fluid using CBGM sensors due to within-patient and between-patient variations. To address this issue, we developed a novel data-driven approach to accurately predict CBGM values using personalized calibration and machine learning. First, we scientifically divided measured blood glucose into smaller groups, namely, hypoglycemia (<80 mg/dL), nondiabetic (81-115 mg/dL), prediabetes (116-150 mg/dL), diabetes (151-181 mg/dL), severe diabetes (181-250 mg/dL), and critical diabetes (>250 mg/dL). Second, we separately trained each group using different machine learning models based on patients' personalized parameters, such as physical activity, posture, heart rate, breath rate, skin temperature, and food intake. Lastly, we used multilayer perceptron (MLP) for the D1NAMO dataset (training to test ratio: 70:30) and grid search for hyperparameter optimization to predict accurate blood glucose concentrations. We successfully applied our proposed approach in nine patients with type 1 diabetes and observed that the mean absolute relative difference (MARD) decreased from 17.8% to 8.3%.

Cell wall and immune modulation by Rv1800 (PPE28) helps M. smegmatis to evade intracellular killing.

Rv1800 is predicted as PPE family protein found in pathogenic mycobacteria only. Under acidic stress, the rv1800 gene was expressed in M. tuberculosis H37Ra. In-silico study showed lipase/esterase activity in C-terminus PE-PPE domain having pentapeptide motif with catalytic Ser-Asp-His residue. Full-length Rv1800 and C-terminus PE-PPE domain proteins showed esterase activity with pNP-C4 at the optimum temperature of 40 °C and pH 8.0. However, the N-terminus PPE domain showed no esterase activity, but involved in thermostability of Rv1800 full-length protein. M. smegmatis expressing rv1800 (MS_Rv1800) showed altered colony morphology and a significant resistance to numerous environmental stresses, antibiotics and higher lipid content. In extracellular and membrane fraction, Rv1800 protein was detected, while C terminus PE-PPE was present in cytoplasm, suggesting the role of N-terminus PPE domain in transportation of protein. MS_Rv1800 infected macrophage showed higher intracellular survival and low production of ROS, NO and expression levels of iNOS and pro-inflammatory cytokines, while induced expression of the anti-inflammatory cytokines. The Rv1800, PPE and PE-PPE showed antibody-mediated immunity in MDR-TB and PTB patients. Overall, these results confirmed the esterase activity in the C-terminus and function of N-terminus in thermostabilization and transportation; predicting the role of Rv1800 in immune/lipid modulation to support intracellular mycobacterium survival.

N-terminal PPE domain plays an integral role in extracellular transportation and stability of the immunomodulatory Rv3539 protein of the Mycobacterium tuberculosis.

Multigene PE/PPE family is exclusively present in mycobacterium species. Only few selected genes of this family have been characterized till date. Rv3539 was annotated as PPE63 with conserved PPE domain at N-terminal and PE-PPE at C-terminal. An α/ß hydrolase structural fold, characteristic of lipase/esterase, was present in the PE-PPE domain. To assign the biochemical function to Rv3539, the corresponding gene was cloned in pET-32a (+) as full-length, PPE, and PE-PPE domains individually, followed by expression in E. Coli C41 (DE3). All three proteins demonstrated esterase activity. However, the enzyme activity in the N-terminal PPE domain was very low. The enzyme activity of Rv3539 and PE-PPE proteins was approximately same with the pNP-C4 as optimum substrate at 40 °C and pH 8.0. The loss of enzyme activity after mutating the predicted catalytic triad (Ser296Ala, Asp369Ala, and His395Ala) found only in the PE-PPE domain, confirmed the candidature of the bioinformatically predicted active site residue. The optimal activity and thermostability of the Rv3539 protein was altered by removing the PPE domain. CD-spectroscopy analysis confirmed the role of PPE domain to the thermostability of Rv3539 by maintaining the structural integrity at higher temperatures. The presence of the N-terminal PPE domain directed the Rv3539 protein to the cell membrane/wall and the extracellular compartment. The Rv3539 protein could generate humoral response in TB patients. Therefore, results demonstrated that Rv3539 demonstrated esterase activity. PE-PPE domain of Rv3539 is functionally automated, however, N-terminus domain played a role in protein stabilization and its transportation. Both domains participated in immunomodulation.

Mutation in Eth A protein of Mycobacterium tuberculosis conferred drug tolerance against enthinoamide in Mycobacterium smegmatis mc2155.

EthA is an NADPH-specific flavin adenine dinucleotide (FAD) containing monooxygenase that activates the -second-line drug ethionamide (ETH). ETH gets converted to an active form after interaction with the EthA (monooxygenase) protein. Upon activation, ETH interacts with NAD+ to form an ETH-NAD adduct, which hampers the activity of InhA (Enoyl-[(acyl-carrier-protein) reductase (NADH)]. This, in turn, inhibits the cell wall synthesis, thus killing the Mycobacterium tuberculosis (Mtb). Mutations in the EthA gene can modulate ETH activation. The mutation at 202 position (Val202-Leu) of EthA protein has been reported frequently in ETH resistance. In this study, the effect of this mutation on the function of the EthA protein was examined through structural and functional analysis. Molecular docking of wild type and mutated EthA protein with ETH were compared to inspect the effect of mutation on molecular mechanism of drug resistant. Docking results corroborated that the lower docking score of the mutant protein, larger binding cavity, and lower affinity towards ETH resulted in a less compact and energetically less stable structure than the wild type protein. The computational outcome was authenticated by in-vitro experiments. The wild type and mutated genes were cloned and expressed in M. smegmatis, a surrogate host. Antibiotic susceptibility testing demonstrated that the mutant showed high growth and survival in the presence of the ETH drug. Overall, the results indicated that a mutation in the intergenic region of EthA protein could result in the altered conversion of ETH to the active form, resulting in differential ETH sensitivity for M. smegmatis carrying the wild type and mutant gene.

Adaptive Boosting Based Personalized Glucose Monitoring System (PGMS) for Non-Invasive Blood Glucose Prediction with Improved Accuracy.

In this paper, we present an architecture of a personalized glucose monitoring system (PGMS). PGMS consists of both invasive and non-invasive sensors on a single device. Initially, blood glucose is measured invasively and non-invasively, to train the machine learning models. Then, paired data and corresponding errors are divided scientifically into six different clusters based on blood glucose ranges as per the patient's diabetic conditions. Each cluster is trained to build the unique error prediction model using an adaptive boosting (AdaBoost) algorithm. Later, these error prediction models undergo personalized calibration based on the patient's characteristics. Once, the errors in predicted non-invasive values are within the acceptable error range, the device gets personalized for a patient to measure the blood glucose non-invasively. We verify PGMS on two different datasets. Performance analysis shows that the mean absolute relative difference (MARD) is reduced exceptionally to 7.3% and 7.1% for predicted values as compared to 25.4% and 18.4% for measured non-invasive glucose values. The Clarke error grid analysis (CEGA) plot for non-invasive predicted values shows 97% data in Zone A and 3% data in Zone B for dataset 1. Moreover, for dataset 2 results echoed with 98% and 2% in Zones A and B, respectively.

Accelerated Reliability Growth Test for Magnetic Resonance Imaging System Using Time-of-Flight Three-Dimensional Pulse Sequence.

A magnetic resonance imaging (MRI) system is a complex, high cost, and long-life product. It is a widely known fact that performing a system reliability test of a MRI system during the development phase is a challenging task. The major challenges include sample size, high test cost, and long test duration. This paper introduces a novel approach to perform a MRI system reliability test in a reasonably acceptable time with one sample size. Our approach is based on an accelerated reliability growth test, which consists of test cycle made of a very high-energy time-of-flight three-dimensional (TOF3D) pulse sequence representing an actual hospital usage scenario. First, we construct a nominal day usage scenario based on actual data collected from an MRI system used inside the hospital. Then, we calculate the life-time stress based on a usage scenario. Finally, we develop an accelerated reliability growth test cycle based on a TOF3D pulse sequence that exerts highest vibration energy on the gradient coil and MRI system. We use a vibration energy model to map the life-time stress and reduce the test duration from 537 to 55 days. We use a Crow AMSAA plot to demonstrate that system design reaches its useful life after crossing the infant mortality phase.