Module modified acute physiology and chronic health evaluation II: predicting the mortality of neuro-critical disease

Su, Yingying; Wang, Miao; Liu, Yifei; Ye, Hong; Gao, Daiquan; Chen, Weibi; Zhang, Yunzhou; Zhang, Yan

doi:10.1179/1743132814y.0000000395

Cited by 4 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the performance of mortality prediction, the APACHE II scale has been validated and accepted in many settings of general ICU, with the AUC varying from 0.74 to 0.86 ( 17 - 21 ). The risk-adjusted formula to predict mortality estimated from APACHE II score is a remarkable advantage ( 18 , 19 ).…”

Section: Discussionmentioning

confidence: 99%

“…From the critical appraisal process, few articles reviewed the value of APACHE II score and performance of mortality prediction in subspecialty ICUs that have different case-mix and different provider-mix such as neurosurgical ICU ( 3 ). The discordance between the predictive implications, particularly on some specific neurosurgical disease conditions that were not generalized to the others, was mentioned ( 17 ). Therefore, this retrospective study was performed to present the severity of illness by acknowledging the APACHE II score among neurosurgical ICU patients, to predict mortality reflecting APACHE II performance, and to evaluate the relationship of APACHE II score parameters as if they could estimate the length of hospital stay.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Acute Physiology and Chronic Health Evaluation (APACHE) II Score – the Clinical Predictor in Neurosurgical Intensive Care Unit

Akavipat

2019

ACC

View full text Add to dashboard Cite

SUMMARY The APACHE II scoring system is approved for its benchmarking and mortality predictions, but there are only a few articles published to demonstrate it in neurosurgical patients. Therefore, this study was performed to acknowledge this score and its predictive performance to hospital mortality in a tertiary referral neurosurgical intensive care unit (ICU). All patients admitted to the Neurosurgical ICU from February 1 to July 31, 2011 were recruited. The parameters indicated in APACHE II score were collected. The adjusted predicted risk of death was calculated and compared with the death rate observed. Descriptive statistics including the receiver operating characteristic curve (ROC) was performed. The results showed that 276 patients were admitted during the mentioned period. The APACHE II score was 16.56 (95% CI, 15.84-17.29) and 19.08 (95% CI, 15.40-22.76) in survivors and non-survivors, while the adjusted predicted death rates were 13.39% (95% CI, 11.83-14.95) and 17.49% (95% CI, 9.81-25.17), respectively. The observed mortality was only 4.35%. The area under the ROC of APACHE II score to the hospital mortality was 0.62 (95% CI, 0.44-0.79). In conclusion, not only the APACHE II score in neurosurgical patients indicated low severity, but its performance to predict hospital mortality was also inferior. Additional studies of predicting mortality among these critical patients should be undertaken.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Acute Physiology and Chronic Health Evaluation (APACHE) II Score – the Clinical Predictor in Neurosurgical Intensive Care Unit

Akavipat

2019

ACC

View full text Add to dashboard Cite

show abstract

“…Use of ROC modeling has applications across diagnoses. As mentioned above, these techniques have been used to classify patients with spinal muscular atrophy based on electrical impedance myography, muscle ultrasound, and biomarker analyses; to predict mortality in a neurointensive care unit in patients with cerebral infarction, intracranial hemorrhage, and neurological infection; and to quantify fracture risk in chronic kidney disease . Although the methods are the same, we would expect results to differ across disease conditions due to individual disease characteristics.…”

Section: Discussionmentioning

confidence: 99%

“…When attempting to understand or predict loss in function, it is important to understand all factors that influence task performance. Statistical modeling techniques of machine learning utilizing receiver operating characteristic (ROC) curves have been used in different diseases to identify variables that differentiate between groups or predict outcomes . Most recently, this technique has been utilized in spinal muscular atrophy to identify and validate biomarkers associated with disease severity .…”

mentioning

confidence: 99%

Modeling functional decline over time in sporadic inclusion body myositis

et al. 2016

View full text Add to dashboard Cite

show abstract

“…In order to attenuate this pitfal l; Acute Physiology and Chronic Health Evaluation (APACHE) score, Simplified Acute Physiology Score (SAPS) have been initiated. These scales can clinical ly simplify and categorize critical ly ill patient with its high mortality pre-dictive ability as shown in the area under the receiver operat ing characteristic curve (AUC) of 0.76-0.90 [9,10] for general ICU and 0.81-0.89 [11][12][13] together with sensitivity/ specifi city over 74% [14] for neurosurgical ICU. However, the diff erences of scale prediction have not been established, especial ly in neurosurgical patients lately.…”

Section: Introductionmentioning

confidence: 99%

Mortality Prediction in a Neurosurgical Intensive Care Unit

Akavipat¹,

Thinkhamrop²,

Thinkhamrop³

et al. 2017

Cesk Slov Neurol N

View full text Add to dashboard Cite

Aim: The ability to estimate factors infl uenc ing intensive care outcome, especial ly mor tality, is highly important to patient care worldwide. Several clinical variables have been identified for the general intensive care unit (ICU) sett ing with high mortality predictive ability. However, the application of such predictors in the neurosurgical ICU sett ing is not yet established. The study was aimed to as sess the predictive ability of the variables as sociated with mortality in a tertiary neurosurgical ICU. Material and methods: All neurosurgical patients admitted to ICU dur ing a 5-month period in 2011 were recruited to the study (n = 258). A logistic regres sion model was used for data analysis and odds ratios were calculated for each predictor. Results: The observed hospital mortality rate was 3.49%. The four result ing predictors of mortality were: increased body temperature of 0.1 °C OR = 1.21, 95% CI 1.02-1.44; 1 mg/ dl increase in blood glucose level OR = 0.93, 95% CI 0.87-0.99; one point increase on the Glasgow Coma Scale (GCS) eye subscale OR = 0.26, 95% CI 0.07-0.89; and 1 day increase in the length of stay prior to ICU admis sion OR = 1.14 (1.05-1.24). These predictors were put into a regres sion model and the area under the receiver operat ing characteristic curve (AUC) was 0.968, 95% CI 0.923-1.000. Conclusion: The body temperature, blood glucose level, GCS eye response and the length of hospital stay prior to ICU admis sion may be hospital mortality predictors in a neurosurgical ICU. Accordingly, a new predictive model should be developed. Souhrn Cíl: Celosvětově je pro péči o pa cienty velmi důležité, abychom byli schopni identifi kovat faktory, které ovlivňují výsledky intenzivní péče, obzvláště mortalitu. Byla identifi kována řada klinických proměnných, které velmi dobře predikují mortalitu na všeobecných jednotkách intenzivní péče (JIP). Použití takových prediktorů na neurochirurgických JIP nebylo zatím zkoumáno. Cílem naší studie bylo zhodnotit prediktivní schopnost proměn ných spojených s mortalitou v terciární neurochirurgické JIP. Meteriál a metody: Do studie byli zapojeni všichni neurochirurgičtí pa cienti přijatí na JIP během pětiměsíčního období roku 2011 (n = 258). Data byla analyzována pomocí logistické regrese a pro každý prediktor bylo vypočítáno odds ratio. Výsledky: Zjištěna byla hospitalizační mortalita 3,49 %. Identifi kovány byly čtyři prediktory mortality: tělesná teplota zvýšená o 0,1 °C OR = 1,21, 95% CI 1,02-1,44; zvýšení hladiny glukózy v krvi o 1 mg/ dl OR = 0,93, 95% CI 0,87-0,99; zvýšení o jeden bod na zrakové podstupnici Glasgow Coma Scale (GCS) OR = 0,26, 95% CI 0,07-0,89; a prodloužení hospitalizace předcházející přijetí na JIP o 1 den OR = 1,14 (1,05-1,24). Tyto prediktory byly vloženy do regresního modelu, přičemž plocha pod křivkou (AUC) činila 0,968, 95% CI 0,923-1,000. Závěr: Jako prediktory nemocniční mortality na neurochirurgické JIP mohou sloužit tělesná teplota, hladina glukózy v krvi, zraková odpověď na GCS a délka hospitalizace před přijetím na JIP. Je ...

show abstract

Module modified acute physiology and chronic health evaluation II: predicting the mortality of neuro-critical disease

Abstract: The APACHE II severity of disease classification system cannot provide accurate prognosis for all kinds of the diseases. A MM-APACHE II model can accurately predict hospital mortality for cerebral infarction, intracranial hemorrhage, and neurologic infection patients in N-ICU.

Cited by 4 publications

References 18 publications

Acute Physiology and Chronic Health Evaluation (APACHE) II Score – the Clinical Predictor in Neurosurgical Intensive Care Unit

Acute Physiology and Chronic Health Evaluation (APACHE) II Score – the Clinical Predictor in Neurosurgical Intensive Care Unit

Modeling functional decline over time in sporadic inclusion body myositis

Mortality Prediction in a Neurosurgical Intensive Care Unit

Contact Info

Product

Resources

About