Skip to content

Evaluating a sepsis prediction machine learning algorithm

Evaluating a sepsis prediction machine learning algorithm in Thai population

Status
Unknown
Phases
Phase 2Phase 3
Study type
Interventional
Source
TCTR
Registry ID
TCTR20230120001
Enrollment
600
Registered
2023-01-20
Start date
2023-01-02
Completion date
Unknown
Last updated
2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Sepsis sepsis, machine learning, emergency room

Interventions

During the intervention period, the machine learning model would compute the real-time prediction probability of sepsis for the patients immediately after patient registration and the visiting data su
Experimental No treatment,No Intervention Other
AI - augmented decision support,Control

Sponsors

Chulalongkorn University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Age older than 18 years 2. Non-traumatic patient

Exclusion criteria

Exclusion criteria: 1. Pregnancy

Design outcomes

Primary

MeasureTime frame
time to antibiotic time since septic patient registered in emergency room to recieving antibiotic time ( minutes),Percents of sepsis patient that recieved antibiotic within 1 hour since patient registered in emergency room to discharge from emergency room Percents

Secondary

MeasureTime frame
length of stay in emergency room time since patient registered in emergency room to discharge from emergency room time (minutes),Inhospital mortality ince patient registered in emergency room to discharge from hospital Percents

Countries

Thailand

Contacts

Public ContactNorawit Kijpaisalratana

Faculty of Medicine, Chulalongkorn University

norawit.k@chula.ac.th26494000

Outcome results

None listed

Source: TCTR (via WHO ICTRP) · Data processed: Aug 9, 2026