Clinical features of dengue in a large Vietnamese cohort: intrinsically lower platelet counts and greater risk for bleeding in adults than children

Abstract

Background: As dengue spreads to new geographical regions and the force of infection changes in existing endemic areas, a greater breadth of clinical presentations is being recognised. Clinical experience suggests that adults manifest a pattern of complications different from those observed in children, but few reports have described the age-related spectrum of disease in contemporaneous groups of patients recruited at the same geographical location.

Methodology/principal findings: Using detailed prospectively collected information from ongoing studies that encompass the full spectrum of hospitalised dengue cases admitted to a single hospital in southern Vietnam, we compared clinical and laboratory features, management, and outcome for 647 adults and 881 children with confirmed dengue. Signs of vascular leakage and shock were more frequent and more severe in children than adults, while bleeding manifestations and organ involvement were more common in adults. Additionally, adults experienced significantly more severe thrombocytopenia. Secondary infection but not serotype was independently associated with greater thrombocytopenia, although with a smaller effect than age-group. The effect of age-group on platelet count was also apparent in the values obtained several weeks after recovery, indicating that healthy adults have intrinsically lower counts compared to children.

Conclusions/significance: There are clear distinctions between adults and children in the pattern of complications seen in association with dengue infection, and these depend partly on intrinsic age-dependent physiological differences. Knowledge of such differences is important to inform research on disease pathogenesis, as well as to encourage development of management guidelines that are appropriate to the age-groups at risk.

Figure 1. Profile of patients studied on the intensive care units (Panel A) and the infection wards (Panel B).

* These 111 patients were admitted to AICU for close observation but did not go on to develop shock or other complications. Due to workload constraints children admitted to PICU with suspected dengue were only enrolled into the observational study if they developed overt complications. ** Note that these patients were recruited into the study in the infection wards and subsequently transferred to PICU/AICU.

Figure 2. Daily platelet counts in children and adults with dengue.

Box and whisker plots showing daily platelet counts during the course of illness and at follow-up for children and adults admitted directly to the relevant ICU with shock (Panel A), and for children and adults with uncomplicated dengue admitted directly to and managed throughout on the relevant infection wards (Panel B). Mean +/− SD day of illness at follow up for patients with DSS was 40+/−3 for children and 31+/−12 for adults, and for patients with uncomplicated dengue was 39+/−3 for children and 29+/−13 for adults. Boxes represent the median and interquartile values. Open circles indicate outlying/extreme values. The total number of patients included in each group each day is indicated on the X axis. The Mann-Whitney test was used to compare the daily platelet counts between children and adults, *** p<0.001 and ** p<0.01.

Figure 3. Associations between platelet counts and bleeding severity in children and adults with dengue.

Box and whisker plots showing associations between the lowest platelet counts observed in specific time-periods (early febrile – days 1–3, critical – days 4–6 and convalescent periods – day 7–10) during the illness course and at the follow up visit, and the overall bleeding severity for all children (Panel A) and adults (Panel B) admitted directly to the hospital. Boxes represent the median and interquartile values. Open circles indicate outlying/extreme values. The total number of patients included in each group each time-period is indicated on the X axis. The Cuzick test for trend was used to compare the lowest platelet counts across the overall bleeding score in each time-period, *** p<0.001 and ** p<0.01.

Figure 4. Platelet counts by day of illness for adults who did or did not develop mucosal bleeding.

Box and whisker plots showing platelet counts on days 4, 5 and 6 of illness comparing adults who developed mucosal bleeding during the subsequent 24 hour period to adults who never developed mucosal bleeding throughout the illness course. Boxes represent the median and interquartile values. Open circles indicate outlying/extreme values. The total number of patients included in each group each day is indicated on the X axis. Patients in whom mucosal bleeding developed prior to admission to HTD are not included. The Mann-Whitney test was used to compare the platelet counts between the two groups on each day. *** p<0.001 and * p<0.05.