Impact of an electronic alert system for pediatric sepsis screening a tertiary hospital experience

This study aimed to assess the potential impact of implementing an electronic alert system (EAS) for systemic inflammatory syndrome (SIRS) and sepsis in pediatric patients mortality. This retrospective study had a pre and post design. We enrolled patients aged ≤ 14 years who were diagnosed with sepsis/severe sepsis upon admission to the pediatric intensive care unit (PICU) of our tertiary hospital from January 2014 to December 2018. We implemented an EAS for the patients with SIRS/sepsis. The patients who met the inclusion criteria pre-EAS implementation comprised the control group, and the group post-EAS implementation was the experimental group. Mortality was the primary outcome, while length of stay (LOS) and mechanical ventilation in the first hour were the secondary outcomes. Of the 308 enrolled patients, 147 were in the pre-EAS group and 161 in the post-EAS group. In terms of mortality, 44 patients in the pre-EAS group and 28 in the post-EAS group died (p 0.011). The average LOS in the PICU was 7.9 days for the pre-EAS group and 6.8 days for the post-EAS group (p 0.442). Considering the EAS initiation time as the “zero time”, early recognition of SIRS and sepsis via the EAS led to faster treatment interventions in post-EAS group, which included fluid boluses with median (25th, 75th percentile) time of 107 (37, 218) min vs. 30 (11,112) min, p < 0.001) and time to initiate antimicrobial therapy median (25th, 75th percentile) of 170.5 (66,320) min vs. 131 (53,279) min, p 0.042). The difference in mechanical ventilation in the first hour of admission was not significant between the groups (25.17% vs. 24.22%, p 0.895). The implementation of the EAS resulted in a statistically significant reduction in the mortality rate among the patients admitted to the PICU in our study. An EAS can play an important role in saving lives and subsequent reduction in healthcare costs. Further enhancement of systematic screening is therefore highly recommended to improve the prognosis of pediatric SIRS and sepsis. The implementation of the EAS, warrants further validation in multicenter or national studies.

Prediction of hospital no-show appointments through artificial intelligence algorithms

BACKGROUND

No-shows, a major issue for healthcare centers, can be quite costly and disruptive. Capacity is wasted and expensive resources are underutilized. Numerous studies have shown that reducing uncancelled missed appointments can have a tremendous impact, improving efficiency, reducing costs and improving patient outcomes. Strategies involving machine learning and artificial intelligence could provide a solution.

OBJECTIVE

Use artificial intelligence to build a model that predicts no-shows for individual appointments.

DESIGN

Predictive modeling.

SETTING

Major tertiary care center.

PATIENTS AND METHODS

All historic outpatient clinic scheduling data in the electronic medical record for a one-year period between 01 January 2014 and 31 December 2014 were used to independently build predictive models with JRip and Hoeffding tree algorithms.

MAIN OUTCOME MEASURES

No show appointments.

SAMPLE SIZE

1 087 979 outpatient clinic appointments.

RESULTS

The no show rate was 11.3% (123 299). The most important information-gain ranking for predicting no-shows in descending order were history of no shows (0.3596), appointment location (0.0323), and specialty (0.025). The following had very low information-gain ranking: age, day of the week, slot description, time of appointment, gender and nationality. Both JRip and Hoeffding algorithms yielded a reasonable degrees of accuracy 76.44% and 77.13%, respectively, with area under the curve indices at acceptable discrimination power for JRip at 0.776 and at 0.861 with excellent discrimination for Hoeffding trees.

CONCLUSION

Appointments having high risk of no-shows can be predicted in real-time to set appropriate proactive interventions that reduce the negative impact of no-shows.

LIMITATIONS

Single center. Only one year of data.

CONFLICT OF INTEREST

None.