Machine-Learning-Based Approach to Differential Diagnosis in Tuberculous and Viral Meningitis.

BACKGROUND: Tuberculous meningitis (TBM) is the most severe form of tuberculosis, but differentiating between the diagnosis of TBM and viral meningitis (VM) is difficult. Thus, we have developed machine-learning modules for differentiating TBM from VM. MATERIAL AND METHODS: For the training data, confirmed or probable TBM and confirmed VM cases were retrospectively collected from five teaching hospitals in Korea between January 2000 - July 2018. Various machine-learning algorithms were used for training. The machine-learning algorithms were tested by the leave-one-out cross-validation. Four residents and two infectious disease specialists were tested using the summarized medical information. RESULTS: The training study comprised data from 60 patients with confirmed or probable TBM and 143 patients with confirmed VM. Older age, longer symptom duration before the visit, lower serum sodium, lower cerebrospinal fluid (CSF) glucose, higher CSF protein, and CSF adenosine deaminase were found in the TBM patients. Among the various machine-learning algorithms, the area under the curve (AUC) of the receiver operating characteristics of artificial neural network (ANN) with ImperativeImputer for matrix completion (0.85; 95% confidence interval 0.79 - 0.89) was found to be the highest. The AUC of the ANN model was statistically higher than those of all the residents (range 0.67 - 0.72, P <0.001) and an infectious disease specialist (AUC 0.76; P = 0.03). CONCLUSION: The machine-learning techniques may play a role in differentiating between TBM and VM. Specifically, the ANN model seems to have better diagnostic performance than the non-expert clinician.

Is the Initial Size of Tuberculous Lymphadenopathy associated with Lymph Node Enlargement during Treatment?

There are little data on the changes in lymph node (LN) size during the treatment of tuberculous lymphadenopathy (TB LAP). This study aimed to provide data on LN changes during treatment. Between March 2014 and December 2015, 20 patients who were diagnosed with cervical TB LAP were enrolled. LN enlargement within two months (50%, 4/8 vs. 8.3%, 1/12; P = 0.04) was more frequently observed in patients with initial LN size ≥ 7.5 cm². Enlarged LNs were excised in three patients owing to pain and fistula formation. Initial LN size may be associated with LN enlargement during treatment.

Institutional Preparedness to Prevent Future Middle East Respiratory Syndrome Coronavirus-Like Outbreaks in Republic of Korea.

A year has passed since the Middle East respiratory syndrome (MERS) outbreak in the Republic of Korea. This 2015 outbreak led to a better understanding of healthcare infection control. The first Korean patient infected by Middle East Respiratory Syndrome Coronavirus (MERS-CoV) was diagnosed on May 20, 2015, after he returned from Qatar and Bahrain. Thereafter, 186 Korean people were infected with the MERS-CoV in a short time through human-to-human transmission. All these cases were linked to healthcare settings, and 25 (13.5 %) infected patients were healthcare workers. Phylogenetic analysis suggested that the MERS-CoV isolate found in the Korean patient was closely related to the Qatar strain, and did not harbor transmission efficiency-improving mutations. Nevertheless, with the same infecting virus strain, Korea experienced the largest MERS-CoV outbreak outside the Arabian Peninsula, primarily due to the different characteristics of population density and the healthcare system. We aimed to review the epidemiological features and existing knowledge on the Korean MERS outbreak, and suggest methods to prevent future epidemics.

Risk Factors for Mortality in Patients with Acinetobacter baumannii Bacteremia.

BACKGROUND: Acinetobacter baumannii, an opportunistic nosocomial pathogen that can cause significant morbidity and mortality, has emerged as a worldwide problem. The aim of this study was to evaluate the risk factors for mortality in patients with A. baumannii bacteremia. MATERIALS AND METHODS: We retrospectively evaluated 118 patients who had A. baumannii bacteremia between July 2003 and December 2011. The aim of this study was to identify the 30-day mortality in patients with A. baumannii bacteremia and relevant risk factors. RESULTS: The bacteremia-related 30-day mortality rate was 34.1%. Univariate analysis revealed that the risk factors for mortality included malignancy, longer hospital stay before bacteremia, intensive care unit (ICU) stay at the time of bacteremia, mechanical ventilation, use of a central venous catheter, unknown origin of bacteremia, bacteremia due to pneumonia, antimicrobial resistance to carbapenems, and elevated Acute Physiology and Chronic Health Evaluation II and Pitt bacteremia scores. Multivariate logistic regression analysis revealed that resistance to carbapenems (odds ratio [OR]: 4.01, 95% confidence interval [CI]: 1.51 to 0.68, P = 0.005), need for mechanical ventilation (OR: 3.97, 95% CI: 1.41 to 11.13, P = 0.005), and presence of malignancy (OR: 4.40, 95% CI: 1.60 to 12.08, P = 0.004) were significantly related to mortality risk. CONCLUSIONS: Risk factors such as resistance to carbapenems, mechanical ventilation, and presence of malignancy were found to be associated with high mortality rates in the patients with A. baumannii bacteremia.