Deep Learning Approach for Classifying Bacteria types using Morphology of Bacterial Colony.

The significant bottlenecks in determining bacterial species are much more time-consuming and the biology specialist's long-term experience requirements. Specifically, it takes more than half a day to cultivate a bacterium, and then a skilled microbiologist and a costly specialized machine are utilized to analyze the genes and classify the bacterium according to its nucleotide sequence. To overcome these issues as well as get higher recognition accuracy, we proposed applying convolutional neural networks (CNNs) architectures to automatically classify bacterial species based on some key characteristics of bacterial colonies. Our experiment confirmed that the classification of three bacterial colonies could be performed with the highest accuracy (97.19%) using a training set of 5000 augmented images derived from the 40 original photos taken in the Hanoi Medical University laboratory in Vietnam.

Effectiveness of Continuous Endotracheal Cuff Pressure Control for the Prevention of Ventilator-Associated Respiratory Infections: An Open-Label Randomized, Controlled Trial.

BACKGROUND: An endotracheal tube cuff pressure between 20 and 30 cmH2O is recommended to prevent ventilator-associated respiratory infection (VARI). We aimed to evaluate whether continuous cuff pressure control (CPC) was associated with reduced VARI incidence compared with intermittent CPC. METHODS: We conducted a multicenter open-label randomized controlled trial in intensive care unit (ICU) patients within 24 hours of intubation in Vietnam. Patients were randomly assigned 1:1 to receive either continuous CPC using an automated electronic device or intermittent CPC using a manually hand-held manometer. The primary endpoint was the occurrence of VARI, evaluated by an independent reviewer blinded to the CPC allocation. RESULTS: We randomized 600 patients; 597 received the intervention or control and were included in the intention to treat analysis. Compared with intermittent CPC, continuous CPC did not reduce the proportion of patients with at least one episode of VARI (74/296 [25%] vs 69/301 [23%]; odds ratio [OR] 1.13; 95% confidence interval [CI] .77-1.67]. There were no significant differences between continuous and intermittent CPC concerning the proportion of microbiologically confirmed VARI (OR 1.40; 95% CI .94-2.10), the proportion of intubated days without antimicrobials (relative proportion [RP] 0.99; 95% CI .87-1.12), rate of ICU discharge (cause-specific hazard ratio [HR] 0.95; 95% CI .78-1.16), cost of ICU stay (difference in transformed mean [DTM] 0.02; 95% CI -.05 to .08], cost of ICU antimicrobials (DTM 0.02; 95% CI -.25 to .28), cost of hospital stay (DTM 0.02; 95% CI -.04 to .08), and ICU mortality risk (OR 0.96; 95% CI .67-1.38). CONCLUSIONS: Maintaining CPC through an automated electronic device did not reduce VARI incidence. CLINICAL TRIAL REGISTRATION: NCT02966392.

A non-contact infection screening system using medical radar and Linux-embedded FPGA: Implementation and preliminary validation.

OBJECTIVES: In this study, an infection screening system was developed to detect patients suffering from infectious diseases. In addition, the system was also designed to deal with the variability in age and gender, which would affect the accuracy of the detection. Furthermore, to enable a low-cost, non-contact and embedded system, multiple vital signs from a medical radar were measured and all algorithms were implemented on a Field Programmable Gate Array, named PYNQ-Z1. METHODS: The system consisted of two main stages: digital signal processing and data classification. In the former stage, Butterworth filters, with flexible cut-off frequencies depending on age and gender, and a time-domain peak detection algorithm were deployed to compute three vital signs, namely heart rate, respiratory rate, and standard deviation of heart beat-to-beat interval. For the classification problem, two machine learning models, Support Vector Machine and Quadratic Discriminant Analysis, were implemented. RESULTS: The Student's t-test showed that our proposed digital signal processing algorithms coped well with the variability of human cases in age and gender. Meanwhile, the f1-score of roughly 98.0% represented the high sensitivity and specificity of our proposed machine learning methods. CONCLUSION: This study outlines the implementation of an infection screening system, which achieved competent performance. The system might be beneficial for fast screening of infected patients at public health centers in underdeveloped areas, where people have little access to healthcare.

Dengue Fever Detecting System Using Peak-detection of Data from Contactless Doppler Radar.

Infectious diseases, such as dengue fever and Middle East respiratory syndrome, have become prevalent worldwide in recent times. To conduct highly accurate and effective infection screening, we are working on the development of a contactless infection screening system using Doppler radar and thermography. In our previous work, three parameters (face temperature, heartbeat rate, and respiration rate) were used to judge whether a subject was infected. However, facial temperature measurements may be vastly different from temperatures measured at the axilla owing to influence from the immediate environment. In this study, heartbeat rate (HR), respiration rate (RR), and standard deviation of heartbeat interval (SDHI) were used to quantify the infection screening system without using facial temperature as a parameter. We found that respiratory sinus arrhythmia (RSA) diminished in patients who had dengue fever. We gathered data from 47 patients with dengue fever using a 10-GHz Doppler radar system at the National Hospital of Tropical Diseases (NHTD) in Hanoi, Vietnam. To evaluate the accuracy, the data of these patients were compared to that of 23 unaffected subjects. We observed that a linear discriminant analysis (LDA) was effective at detecting the dengue fever conditions, and the detection accuracy was approximately 97.6%.

Antimicrobial-resistant Pseudomonas aeruginosa and Acinetobacter baumannii From Patients With Hospital-acquired or Ventilator-associated Pneumonia in Vietnam.

PURPOSE: Multidrug-resistant bacterial pathogens are becoming a significant problem worldwide. Acinetobacter baumannii and Pseudomonas aeruginosa are problematic multidrug-resistant pathogens. This multicenter study in Vietnam determined the level of resistance to antimicrobial agents used to treat A baumannii and P aeruginosa infections in this country. METHODS: Five medical centers in Vietnam provided 529 P aeruginosa and 971 Acinetobacter species (904 A baumannii) isolates from patients with hospital-acquired or ventilator-associated pneumonia from 2012 to 2014. A central laboratory verified identification of the isolates and performed susceptibility testing using Clinical and Laboratory Standards Institute methods. FINDINGS: Resistance to cephalosporins, ß-lactam/ß-lactamase inhibitors, carbapenems, and fluoroquinolones was >90% against A baumannii. Aminoglycosides had only slightly better activity, with amikacin resistance >80%. Only colistin (MIC90, ≤0.25 mg/L) and tigecycline (MIC90, 4 mg/L) had appreciable activity against A baumannii. Similar activity was observed among the ß-lactams tested against P aeruginosa. Cefepime demonstrated the highest activity (60.1% susceptible), which was similar to doripenem (58.6% susceptible), the most active carbapenem tested. Amikacin was the most active aminoglycoside tested against P aeruginosa, with susceptibility of 81.7% compared with tobramycin (58.0%) and gentamicin (56.5%). Fluoroquinolones had limited activity against P aeruginosa with susceptibility to ciprofloxacin (55.0%). All P aeruginosa isolates had colistin MIC values ≤2 mg/L. IMPLICATIONS: The data from this 3-year longitudinal study in Vietnam demonstrate that 2 of the most common nonfermentative gram-negative pathogens associated with hospital-acquired and ventilator-associated pneumonia are significantly resistant to most of the available treatment options and require combination therapies unless new antimicrobial agents become available.

Genetic characterization of Enterovirus 71 strains circulating in Vietnam in 2012.

BACKGROUND: Enterovirus 71 subgenogroup C4 caused the largest outbreak of Hand, Foot and Mouth Disease (HFMD) in Vietnam during 2011-2012, resulting in over 200,000 hospitalisations and 207 fatalities. METHODS: A total of 1917 samples with adequate volume for RT-PCR analysis were collected from patients hospitalised with HFMD throughout Vietnam and 637 were positive for EV71. VP1 gene (n=87) and complete genome (n=9) sequencing was performed. Maximum-likelihood phylogenetic analysis was performed to characterise the B5, C4 and C5 strains detected. RESULTS: Sequence analyses revealed that the dominant subgenogroup associated with the 2012 outbreak was C4, with B5 and C5 strains representing a small proportion of these cases. CONCLUSIONS: Numerous countries in the region including Malaysia, Taiwan and China have a large influence on strain diversity in Vietnam and understanding the transmission of EV71 throughout Southeast Asia is vital to inform preventative public health measures and vaccine development efforts.

Trichinellosis in Vietnam.

Trichinellosis is a zoonotic parasitic disease with a worldwide distribution. The aim of this work was to describe the epidemiological and clinical data of five outbreaks of trichinellosis, which affected ethnic minorities living in remote mountainous areas of northwestern Vietnam from 1970 to 2012. Trichinellosis was diagnosed in 126 patients, of which 11 (8.7%) were hospitalized and 8 (6.3%) died. All infected people had consumed raw pork from backyard and roaming pigs or wild boar at wedding, funeral, or New Year parties. The short incubation period (average of 9.5 days), the severity of the symptoms, which were characterized by diarrhea, abdominal pain, fever, myalgia, edema, weight loss, itch, and lisping, and the high mortality, suggest that patients had ingested a high number of larvae. The larval burden in pigs examined in one of the outbreaks ranged from 70 to 879 larvae/g. These larvae and those collected from a muscle biopsy taken from a patient from the 2012 outbreak were identified as Trichinella spiralis. Data presented in this work show that the northern regions of Vietnam are endemic areas for Trichinella infections in domestic pigs and humans.

Cooperative roles of vertebrate Fbh1 and Blm DNA helicases in avoidance of crossovers during recombination initiated by replication fork collapse.

Fbh1 (F-box DNA helicase 1) orthologues are conserved from Schizosaccharomyces pombe to chickens and humans. Here, we report the disruption of the FBH1 gene in DT40 cells. Although the yeast fbh1 mutant shows an increase in sensitivity to DNA damaging agents, FBH1(-)(/)(-) DT40 clones show no prominent sensitivity, suggesting that the loss of FBH1 might be compensated by other genes. However, FBH1(-)(/)(-) cells exhibit increases in both sister chromatid exchange and the formation of radial structures between homologous chromosomes without showing a defect in homologous recombination. This phenotype is reminiscent of BLM(-)(/)(-) cells and suggests that Fbh1 may be involved in preventing extensive strand exchange during homologous recombination. In addition, disruption of RAD54, a major homologous recombination factor in FBH1(-)(/)(-) cells, results in a marked increase in chromosome-type breaks (breaks on both sister chromatids at the same place) following replication fork arrest. Further, FBH1BLM cells showed additive increases in both sister chromatid exchange and the formation of radial chromosomes. These data suggest that Fbh1 acts in parallel with Bloom helicase to control recombination-mediated double-strand-break repair at replication blocks and to reduce the frequency of crossover.