Prediction of Late-Onset Sepsis in Preterm Infants Using Monitoring Signals and Machine Learning.

OBJECTIVES: Prediction of late-onset sepsis (onset beyond day 3 of life) in preterm infants, based on multiple patient monitoring signals 24 hours before onset. DESIGN: Continuous high-resolution electrocardiogram and respiration (chest impedance) data from the monitoring signals were extracted and used to create time-interval features representing heart rate variability, respiration, and body motion. For each infant with a blood culture-proven late-onset sepsis, a Cultures, Resuscitation, and Antibiotics Started Here moment was defined. The Cultures, Resuscitation, and Antibiotics Started Here moment served as an anchor point for the prediction analysis. In the group with controls (C), an "equivalent crash moment" was calculated as anchor point, based on comparable gestational and postnatal age. Three common machine learning approaches (logistic regressor, naive Bayes, and nearest mean classifier) were used to binary classify samples of late-onset sepsis from C. For training and evaluation of the three classifiers, a leave-k-subjects-out cross-validation was used. SETTING: Level III neonatal ICU. PATIENTS: The patient population consisted of 32 premature infants with sepsis and 32 age-matched control patients. INTERVENTIONS: No interventions were performed. MEASUREMENTS AND MAIN RESULTS: For the interval features representing heart rate variability, respiration, and body motion, differences between late-onset sepsis and C were visible up to 5 hours preceding the Cultures, Resuscitation, and Antibiotics Started Here moment. Using a combination of all features, classification of late-onset sepsis and C showed a mean accuracy of 0.79 ± 0.12 and mean precision rate of 0.82 ± 0.18 3 hours before the onset of sepsis. CONCLUSIONS: Information from routine patient monitoring can be used to predict sepsis. Specifically, this study shows that a combination of electrocardiogram-based, respiration-based, and motion-based features enables the prediction of late-onset sepsis hours before the clinical crash moment.

Septic arthritis and osteomyelitis in a 10-year-old boy, caused by Fusobacterium nucleatum, diagnosed with PCR/16S ribosomal bacterial DNA amplification.

A 10-year-old boy presented with an atypical non-febrile septic arthritis/osteomyelitis. He was unresponsive to routine antibiotic treatment with flucloxacillin/gentamicin as the pain and fluid collection increased. Synovial fluid cultures are negative and gram stain remained negative. Only after PCR/16S ribosomal bacterial DNA amplification a Fusobacterium nucleatum could be detected, and antibiotic therapy switched to clindamycin with rapid response. Septic osteomyelitis and arthritis are relatively rare but important infections in children needing prompt treatment, and should be considered when a child complaints about joint or bone pain without prior recent trauma. Skin bacteria are the most prevalent causative organisms, whereas Fusobacteria or other anaerobic, Gram-negative microorganisms are very seldom encountered. If cultures remain negative and the patients responds insufficiently to empiric treatment, PCR/16S ribosomal bacterial DNA amplification can be useful to detect the causative microorganisms.

Method for phenotypic detection of extended-spectrum beta-lactamases in enterobacter species in the routine clinical setting.

In 271 Enterobacter blood culture isolates from 12 hospitals, extended-spectrum beta-lactamase (ESBL) prevalence varied between 0% and 30% per hospital. High prevalence was associated with dissemination, indicating the potential relevance of infection control measures. Screening with cefepime or Vitek 2, followed by a cefepime/cefepime-clavulanate Etest, was an accurate strategy for ESBL detection in Enterobacter isolates (positive predictive value, 100%; negative predictive value, 99%).

Screening for urinary tract infection with the Sysmex UF-1000i urine flow cytometer.

The diagnosis of urinary tract infection (UTI) by urine culture is time-consuming and can produce up to 60 to 80% negative results. Fast screening methods that can reduce the necessity for urine cultures will have a large impact on overall turnaround time and laboratory economics. We have evaluated the detection of bacteria and leukocytes by a new urine analyzer, the UF-1000i, to identify negative urine samples that can be excluded from urine culture. In total, 1,577 urine samples were analyzed and compared to urine culture. Urine culture showed growth of ≥10(3) CFU/ml in 939 samples (60%). Receiver operating characteristics (ROC) curves and ROC decision plots were been prepared at three different gold standard definitions of a negative urine culture: no growth, growth of bacteria at <10(4) CFU/ml, and growth of bacteria at <10(5) CFU/ml. Also, the reduction in urine cultures and the percentage of false negatives were calculated. At the most stringent gold standard definition of no growth, a chosen sensitivity of 95% resulted in a cutoff value of 26 bacteria/µl, a specificity of 43% and a reduction in urine cultures of only 20%, of which 14% were false negatives. However, at a gold standard definition of <10(5) CFU/ml and a sensitivity of 95%, the UF-1000i cutoff value was 230 bacteria/µl, the specificity was 80%, and the reduction in urine cultures was 52%, of which 0.3% were false negatives. The applicability of the UF-1000i to screen for negative urine samples strongly depends on population characteristics and the definition of a negative urine culture. In our setting, however, the low workload savings and the high percentage of false-negative results do not warrant the UF-1000i to be used as a screening analyzer.

Group-A-streptococcal meningitis in a 7-year-old child--a rare pathogen in a non-immune compromised patient.

A case is presented of meningitis in a 7-year-old female child caused by Group A streptococcus (GAS), a rare bacterial cause of meningitis, with a high rate of morbidity (46%) and mortality (10%). GAS is susceptible for empiric antibiotic therapy aimed at the most prevalent pathogens of meningitis. As GAS meningitis is typically associated with ear-nose-throat (ENT) infections, specific search for a reservoir is advised. Bacterial typification often demonstrates M-protein gene sequence type (EMM type) 1.0 associated with upper respiratory tract infections and also severe, invasive GAS infections. Follow-up investigation including neurologic developmental status and audiologic testing is necessary. Although GAS is a very uncommon cause of acute bacterial meningitis in children, high morbidity and mortality have been reported. Being associated with ENT infections, a search for a GAS reservoir is proposed. GASs are susceptible for common empiric antibiotic therapies in meningitis. Follow-up investigation is necessary.

Group-A-streptococcal meningitis in a 7-year-old child--a rare pathogen in a non-immune compromised patient.

A case is presented of meningitis in a 7-year-old female child caused by Group A streptococcus (GAS), a rare bacterial cause of meningitis, with a high rate of morbidity (46%) and mortality (10%). GAS is susceptible for empiric antibiotic therapy aimed at the most prevalent pathogens of meningitis. As GAS meningitis is typically associated with ear-nose-throat (ENT) infections, specific search for a reservoir is advised. Bacterial typification often demonstrates M-protein gene sequence type (EMM type) 1.0 associated with upper respiratory tract infections and also severe, invasive GAS infections. Follow-up investigation including neurologic developmental status and audiologic testing is necessary. Although GAS is a very uncommon cause of acute bacterial meningitis in children, high morbidity and mortality have been reported. Being associated with ENT infections, a search for a GAS reservoir is proposed. GASs are susceptible for common empiric antibiotic therapies in meningitis. Follow-up investigation is necessary.

Recurring staphylococcal scalded skin syndrome in a very low birth weight infant: a case report.

INTRODUCTION: Staphylococcal scalded skin syndrome is an extensive desquamative erythematous condition caused by exfoliative toxins of Staphylococcus aureus. This disease usually affects neonates and generally responds rapidly to antibiotic therapy. CASE PRESENTATION: We describe the case of a premature baby boy, weighing 1030 g, born after 26 6/7 weeks gestation, who developed two episodes of Staphylococcal scalded skin syndrome on days 19 and 48 of life. Cultures obtained during the first period did not reveal Staphylococcus aureus, but diagnosis was based on typical clinical grounds. Although the initial diagnosis was irritation by the fixation material of a nasal continuous positive airway pressure tube, the infant showed rapidly progressing skin blistering and exfoliation, characteristic of Staphylococcal scalded skin syndrome. After administration of antibiotic treatment, complete recovery was seen. In the second period, diagnosis of Staphylococcal scalded skin syndrome was made clinically and confirmed by results of microbiologic investigations. Staphylococcus aureus was cultured from the nose, skin lesions and the pharynx. The strain appeared to produce exfoliative toxin A. The clinical response to similar antibiotic treatment was identical to the first period of Staphylococcal scalded skin syndrome. CONCLUSION: This case report discusses an unusual presentation of recurring Staphylococcal scalded skin syndrome in a baby with a very low birth weight.

16S rRNA mutation-mediated tetracycline resistance in Helicobacter pylori.

Most Helicobacter pylori strains are susceptible to tetracycline, an antibiotic commonly used for the eradication of H. pylori. However, an increase in incidence of tetracycline resistance in H. pylori has recently been reported. Here the mechanism of tetracycline resistance of the first Dutch tetracycline-resistant (Tet(r)) H. pylori isolate (strain 181) is investigated. Twelve genes were selected from the genome sequences of H. pylori strains 26695 and J99 as potential candidate genes, based on their homology with tetracycline resistance genes in other bacteria. With the exception of the two 16S rRNA genes, none of the other putative tetracycline resistance genes was able to transfer tetracycline resistance. Genetic transformation of the Tet(s) strain 26695 with smaller overlapping PCR fragments of the 16S rRNA genes of strain 181, revealed that a 361-bp fragment that spanned nucleotides 711 to 1071 was sufficient to transfer resistance. Sequence analysis of the 16S rRNA genes of the Tet(r) strain 181, the Tet(s) strain 26695, and four Tet(r) 26695 transformants showed that a single triple-base-pair substitution, AGA(926-928)-->TTC, was present within this 361-bp fragment. This triple-base-pair substitution, present in both copies of the 16S rRNA gene of all our Tet(r) H. pylori transformants, resulted in an increased MIC of tetracycline that was identical to that for the Tet(r) strain 181.