An appraisal of mortality in Intensive Care Unit of a Level III military hospital of Bangladesh

Alam, Rabiul; Haque, Mainul; Haque, Mozibul

doi:10.4103/ijccm.ijccm_250_17

Cited by 7 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This holds true for both adult and pediatric intensive care units. 22,23 Longer duration of stay has been linked with various problems among the patients admitted in the ICU in the past. Poor outcome i.e.…”

Section: Discussionmentioning

confidence: 99%

Thrombocytopenia Among Trauma Patients Admitted in Icu: Frequency and Relationship With Outcome

Farukh

Ahmad

Baig

et al. 2021

PAFMJ

View full text Add to dashboard Cite

Objective: To assess the frequency of thrombocytopenia among the patients of trauma at an intensive care unit and to look for its relationship and other socio-demographic factors with the outcome. Study Design: Cross-sectional study. Place and Duration of Study: Intensive Care Unit, Combined Military Hospital Peshawar, from Mar to Aug 2017. Methodology: Thrombocytopenia was defined as platelet count of <150,000/μl and was performed on the fifth day of admission in the Intensive Care Unit. Age, gender, presence of thrombocytopenia, history of platelet transfusion, and length of stay in the Intensive Care Unit were correlated with the outcome in our study population. Results: A total of 107 patients admitted to intensive care unit with traumatic injuries during the study period were included in analysis. Mean age of the patients was 37.93 ± 6.697 years. Thrombocytopenia developed in 35 (32.7%) of the patients while 72 (67.3%) had normal platelet count. Less than 18% patients died in the intensive care unit. Long duration of Intensive Care Unit stay and presence of thrombocytopenia were statistically significantly associated (p<0.05) with the presence of poor outcome in our sample population. Conclusion: Frequency of thrombocytopenia was high among patients admitted with trauma in intensive care unit and was also related to poor outcome in these patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Thrombocytopenia Among Trauma Patients Admitted in Icu: Frequency and Relationship With Outcome

Farukh

Ahmad

Baig

et al. 2021

PAFMJ

View full text Add to dashboard Cite

show abstract

“…The mean Intensive Care Unit (ICU) mortality rate reported in the United States ranged from 8 to 19% or about 500,000 deaths per year [23]. Alam conducted a study in Bangladesh and showed that the number of ICU beds accounted for 1.8% of the total hospital beds; however the death rate in the ICU was 3.58% of hospital deaths [24]. According to Siddiqui, there were 1134 deaths in three ICU wards in Singapore from July 2010 to March 2015, accounting for 7% of all hospital deaths.…”

Section: Discussionmentioning

confidence: 99%

Factors affecting hospital mortality rate in Iran: a panel data analysis

Bayati

Emadi

2020

BMC Res Notes

View full text Add to dashboard Cite

Objective Hospital deaths account for a large number of community deaths. Moreover, one of the main indicators of inpatient services quality is the hospital death. This study was performed to investigate the factors affecting hospital death rate in Iran using panel data analysis. Results The net death rates in teaching and not-teaching hospitals were 6.24 and 5.58 per 1000 patients, respectively. Models' estimates showed, in teaching hospitals the number of surgeries (P < 0.05) and special beds (P < 0.01) had a significant positive relationship with death rate. In non-teaching hospitals, outpatient admissions (P < 0.01), number of surgeries (P < 0.05), number of special beds (P < 0.01), and length of stay (P < 0.01) had a positive and the number of inpatient admissions (P < 0.05) and active beds (P < 0.01) had a negative relationship with death rate. Policy-making towards optimization of hospital service size and volume, standardization of length of stay, interventions to control nosocomial infections, and planning to control the complications of surgeries and anesthesia could effectively reduce hospital death rate.

show abstract

“…Pre-existing conditions were coded as 1 (present) or 0 (absent). Age was demarcated at 65 years, with those aged >65 years coded 1 and those aged ≤65 years coded 0 [36][37][38][39]. For the sex variable, men were assigned 1 and women were assigned 0 [40].…”

Section: Featuresmentioning

confidence: 99%

Using Item Response Theory for Explainable Machine Learning in Predicting Mortality in the Intensive Care Unit: Case-Based Approach (Preprint)

Kline¹,

Kline²,

Abad³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Supervised machine learning (ML) has made its way into the healthcare literature with results frequently reported using the metrics of accuracy, sensitivity, specificity, recall or F1. While each provides a different perspective on the performance, they remain overall measures on the whole sample, discounting the uniqueness of each case/patient. Intuitively we know that all cases are not equal, but current evaluative approaches do not take case difficulty into account. OBJECTIVE A more case-based comprehensive approach is warranted to assess supervised ML outcomes and forms the rationale for this study. We demonstrate how Item Response Theory (IRT) can be used to stratify the data based on how ‘difficult’ each case is to classify, independent of the outcome measure of interest (e.g., accuracy). This stratification allows the evaluation of ML classifiers to take the form of a distribution rather than a single scalar value. METHODS Two large, public intensive care unit (ICU) data sets, MIMIC III and eICU, were used to showcase this method in predicting mortality. For each data set, a balanced and an imbalanced sample were drawn. Conventional metrics for ML classification are reported for methodological comparison. Several ML algorithms were used in the demonstration: logistic regression (LR), linear discriminate analysis (LDA), K-nearest neighbors (KNN), decision tree (DT), naïve bayes (NB), and a neural network (NN). Generalized linear mixed model analyses assessed the effects of case difficulty strata, machine learning algorithm and their interaction in predicting accuracy. RESULTS The results illustrated that all classifiers performed better with easier-to-classify cases and that overall the NN performed best. Significant interactions suggest that cases that fall in the most arduous strata should be handled by LR LDA, DT or NN, but not NB or KNN. This demonstration shows that IRT is a viable method for understanding the data that are provided to ML algorithms, independent of outcome measures, and highlights how well classifiers differentiate cases of varying difficulty. CONCLUSIONS This method generates an explanation into which features are indicative of healthy states and why. It enables ends users to tailor the classifier appropriate to the difficulty level of the patient for a personalized medicine approach. CLINICALTRIAL N/A

show abstract

An appraisal of mortality in Intensive Care Unit of a Level III military hospital of Bangladesh

Cited by 7 publications

References 21 publications

Thrombocytopenia Among Trauma Patients Admitted in Icu: Frequency and Relationship With Outcome

Thrombocytopenia Among Trauma Patients Admitted in Icu: Frequency and Relationship With Outcome

Factors affecting hospital mortality rate in Iran: a panel data analysis

Using Item Response Theory for Explainable Machine Learning in Predicting Mortality in the Intensive Care Unit: Case-Based Approach (Preprint)

Contact Info

Product

Resources

About