Paenibacillus spp infection among infants with postinfectious hydrocephalus in Uganda: an observational case-control study

Abstract

Background: Paenibacillus thiaminolyticus is a cause of postinfectious hydrocephalus among Ugandan infants. To determine whether Paenibacillus spp is a pathogen in neonatal sepsis, meningitis, and postinfectious hydrocephalus, we aimed to complete three separate studies of Ugandan infants. The first study was on peripartum prevalence of Paenibacillus in mother-newborn pairs. The second study assessed Paenibacillus in blood and cerebrospinal fluid (CSF) from neonates with sepsis. The third study assessed Paenibacillus in CSF from infants with hydrocephalus.

Methods: In this observational study, we recruited mother-newborn pairs with and without maternal fever (mother-newborn cohort), neonates (aged ≤28 days) with sepsis (sepsis cohort), and infants (aged ≤90 days) with hydrocephalus with and without a history of neonatal sepsis and meningitis (hydrocephalus cohort) from three hospitals in Uganda between Jan 13, 2016 and Oct 2, 2019. We collected maternal blood, vaginal swabs, and placental samples and the cord from the mother-newborn pairs, and blood and CSF from neonates and infants. Bacterial content of infant CSF was characterised by 16S rDNA sequencing. We analysed all samples using quantitative PCR (qPCR) targeting either the Paenibacillus genus or Paenibacillus thiaminolyticus spp. We collected cranial ultrasound and computed tomography images in the subset of participants represented in more than one cohort.

Findings: No Paenibacillus spp were detected in vaginal, maternal blood, placental, or cord blood specimens from the mother-newborn cohort by qPCR. Paenibacillus spp was detected in 6% (37 of 631 neonates) in the sepsis cohort and, of these, 14% (5 of 37 neonates) developed postinfectious hydrocephalus. Paenibacillus was the most enriched bacterial genera in postinfectious hydrocephalus CSF (91 [44%] of 209 patients) from the hydrocephalus cohort, with 16S showing 94% accuracy when validated by qPCR. Imaging showed progression from Paenibacillus spp-related meningitis to postinfectious hydrocephalus over 1-3 months. Patients with postinfectious hydrocephalus with Paenibacillus spp infections were geographically clustered.

Interpretation: Paenibacillus spp causes neonatal sepsis and meningitis in Uganda and is the dominant cause of subsequent postinfectious hydrocephalus. There was no evidence of transplacental transmission, and geographical evidence was consistent with an environmental source of neonatal infection. Further work is needed to identify routes of infection and optimise treatment of neonatal Paenibacillus spp infection to lessen the burden of morbidity and mortality.

Funding: National Institutes of Health and Boston Children's Hospital Office of Faculty Development.

Figure 1:

Participant flow diagrams (A) Mother–newborn cohort. (B) Neonatal sepsis cohort. (C) Hydrocephalus cohort. CSF=cerebrospinal fluid. *Peripartum vaginal swab, maternal blood, and placenta sample. †Three placentas not available. ‡All 209 postinfectious hydrocephalus and 191 non-postinfectious hydrocephalus cases were included in quantitative PCR analysis and final designation of Paenibacillus spp.

Figure 2:

Paenibacillus spp associated with PIH using 16S metagenome sequencing (A) Proportions of 16S reads mapped to the ten most common genera by patient for the PIH (left) and NPIH (right) groups. (B, C) Proportion of 16S reads mapped to the ten most common genera by PIH (B) or NPIH (C) status. (D, E) Receiver operating characteristic curves were used to optimise the sensitivity and specificity of 16S Paenibacillus diagnosis with the gold standard quantitative PCR of 54·5 Paenibacillus spp and 32·5 Paenibacillus thiaminolyticus reads. AUC=area under the curve. PIH=postinfectious hydrocephalus. NPIH=non-postinfectious hydrocephalus.

Figure 3:

Paenibacillus spp positive cases cluster by postinfectious hydrocephalus group and CT scores clustered by bacterial species reads Unsupervised hierarchical clustering of samples by 16S reads mapped at the species level. Columns are coloured by hydrocephalus group and CT scores but group and CT score data were not used in clustering. Paenibacillus spp quantitative PCR status is positive or negative based on genus-level qPCR detection of Paenibacillus. Group status refers to postinfectious hydrocephalus or non-postinfectious hydrocephalus grouping. CT scores reflect the quantitative ranking of abnormalities on brain CT, with 0 being minimally affected and 4 being the most severely affected.

Figure 4:

Spatial distribution of infants with hydrocephalus by cause and Paenibacillus status (A) Distribution of non-postinfectious hydrocephalus (black circles) and postinfectious hydrocephalus (red circles) cases in Ugandan villages, mapped within 11 km squares. Postinfectious hydrocephalus cases cluster in eastern and north-central regions whereas non-postinfectious hydrocephalus cases are more dispersed. (B) Ripley’s K function for the difference in postinfectious hydrocephalus and non-postinfectious hydrocephalus case locations (black line) shows spatial aggregation of postinfectious hydrocephalus above a 35 km scale, defined by the 95% confidence bounds from Monte Carlo simulations (grey). (C) Distribution of Paenibacillus spp qPCR positive non-postinfectious (red circles) and postinfectious cases (red triangles) and Paenibacillus spp qPCR negative non-postinfectious (black circles) and postinfectious (black triangles) cases. (D) Ripley’s K function for the difference in Paenibacillus spp positive and negative case locations (black line) shows spatial aggregation of Paenibacillus spp cases at a 5–150 km scale, defined by the 95% confidence bounds from Monte Carlo simulations (grey). PIH=Postinfectious hydrocephalus. NPIH=Non-postinfectious hydrocephalus.

Figure 5:. Imaging of neonatal Paenibacillus thiaminolyticus sepsis cases that subsequently developed postinfectious hydrocephalus

1 month=28 days. Representative cranial ultrasound from coronal, parasagittal and coronal views, and axial CT images, shown from left to right. A) Cranial ultrasound of a healthy neonate and CT image of a healthy 2-month-old infant are shown (reproduced from https://radiopaedia.org). B) 8-day old neonate (patient 1) with P thiaminolyticus CNS infection. Cranial ultrasound shows abnormal white matter and cortex echogenicity, extensive cortical and white matter injury from frontal to occipital lobes bilaterally, periventricular white matter injury, and a left frontal cortex and subcortical cystic lesion (green arrow). CT image of the same patient at 1 month before surgery for postinfectious hydrocephalus shows enlargement of the cyst with abscess formation (green arrow). C) 12-day-old neonate (patient 2) with P thiaminolyticus CNS infection. Cranial ultrasound shows cortical and subcortical white matter lesions with cystic evolution (white star), ventricular fluid with loculation, thickened hyperechogenic ventricular ependymal lining (S symbol), hyperechogenic gyri and sulci, and hyperechogenic extracerebral space (green circle). CT image of the same patient at 2 months of age before surgery for postinfectious hydrocephalus shows destruction of the bilateral frontal lobes, and residual ventricular debris.