RELIABILITY OF APACHE-II SCORING IN PREDICTING MORTALITY AT THE TIME OF ICU ADMISSION- A CLINICAL AUDIT

Different scoring systems are used to predict ICU patients' health outcomes and mortality rates. APACHE-II score has been found to have a discriminative value in predicting the mortality rate. There are some limitations to this score, such as the patients with multiple comorbid conditions and the physiological variables are all dynamic, which may alter the predicted mortality rate. Objective: The rationale behind doing this study is to see if there is any difference between the observed mortality and predicted mortality per the APACHE-II scoring system and how the APACHE-II scoring system will help predict the length of hospital stay and mortality in ICU patients. Methods: This was a cross-sectional study. The study was conducted in the Surgical Intensive Care Unit (SICU) of Doctors Hospital and Medical Centre, Lahore, from 1st January 2022 to 31st December 2022.: Data were analyzed using IBM SPSS Software version 29.0. Descriptive statistics, including mean and standard deviation, were computed. The results from the SPSS software output file were included along with the text. A one-sample t-test was applied to assess the significance of the data. A p-value of less than 0.05 was considered statistically significant, with a 95% confidence interval. Results: A total of 305 patients were included in our study. The mean age of patients who were admitted was 53.6 years. The mean length of ICU stay over the study period was calculated to be 4.3 days. Of 305 patients, 66 expired, and 239 were stepped down to in-patient units. All groups of APACHE-II score have less observed mortality than actual mortality; only group 3(APACHE 20-30) has higher observed mortality than predicted mortality. Conclusion: The APACHE-II score effectively stratifies patients at the time of admission to ICU as having a higher or lower risk of mortality depending on the disease severity so that the treatment triage, end-of-life ICU-care, and other important decisions can be made. This scoring doesn’t have a very high sensitivity and specificity, but with an increasing score, there is a higher mortality risk. We need to improve our ICU care for patients with APACHE-II scores between 20-30, as we have more observed mortality in that group. Hopefully, this study will help the practices in the ICU care region.

Authors

Institutions

Publication Details

Journal
Biological and Clinical Sciences Research Journal
Published
2024-12-30
DOI
https://doi.org/10.54112/bcsrj.v2024i1.1321
Primary Topic
Artificial Intelligence in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

RELIABILITY OF APACHE-II SCORING IN PREDICTING MORTALITY AT THE TIME OF ICU ADMISSION- A CLINICAL AUDIT

Atiq Ur Rehman, AH KHAN, Unaiza Saeed, Marek Malík et al.
Biological and Clinical Sciences Research Journal
Artificial Intelligence in Healthcare
article

RELIABILITY OF APACHE-II SCORING IN PREDICTING MORTALITY AT THE TIME OF ICU ADMISSION- A CLINICAL AUDIT

Atiq Ur Rehman, AH KHAN, Unaiza Saeed, Marek Malík, Erum Rehman, SU REHMAN
article en

Abstract

Different scoring systems are used to predict ICU patients' health outcomes and mortality rates. APACHE-II score has been found to have a discriminative value in predicting the mortality rate. There are some limitations to this score, such as the patients with multiple comorbid conditions and the physiological variables are all dynamic, which may alter the predicted mortality rate. Objective: The rationale behind doing this study is to see if there is any difference between the observed mortality and predicted mortality per the APACHE-II scoring system and how the APACHE-II scoring system will help predict the length of hospital stay and mortality in ICU patients. Methods: This was a cross-sectional study. The study was conducted in the Surgical Intensive Care Unit (SICU) of Doctors Hospital and Medical Centre, Lahore, from 1st January 2022 to 31st December 2022.: Data were analyzed using IBM SPSS Software version 29.0. Descriptive statistics, including mean and standard deviation, were computed. The results from the SPSS software output file were included along with the text. A one-sample t-test was applied to assess the significance of the data. A p-value of less than 0.05 was considered statistically significant, with a 95% confidence interval. Results: A total of 305 patients were included in our study. The mean age of patients who were admitted was 53.6 years. The mean length of ICU stay over the study period was calculated to be 4.3 days. Of 305 patients, 66 expired, and 239 were stepped down to in-patient units. All groups of APACHE-II score have less observed mortality than actual mortality; only group 3(APACHE 20-30) has higher observed mortality than predicted mortality. Conclusion: The APACHE-II score effectively stratifies patients at the time of admission to ICU as having a higher or lower risk of mortality depending on the disease severity so that the treatment triage, end-of-life ICU-care, and other important decisions can be made. This scoring doesn’t have a very high sensitivity and specificity, but with an increasing score, there is a higher mortality risk. We need to improve our ICU care for patients with APACHE-II scores between 20-30, as we have more observed mortality in that group. Hopefully, this study will help the practices in the ICU care region.

Biological and Clinical Sciences Research JournalVol. 2024(1)
Services Institute of Medical Sciences (PK), Combined Military Hospital (PK), Doctors Hospital (US)
Openalex Percentile: Top 63%
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.