1
|
Lin YT, Lin KM, Wu KH, Lien F. Enhancing pneumonia prognosis in the emergency department: a novel machine learning approach using complete blood count and differential leukocyte count combined with CURB-65 score. BMC Med Inform Decis Mak 2024; 24:118. [PMID: 38702739 PMCID: PMC11069213 DOI: 10.1186/s12911-024-02523-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Accepted: 04/29/2024] [Indexed: 05/06/2024] Open
Abstract
BACKGROUND Pneumonia poses a major global health challenge, necessitating accurate severity assessment tools. However, conventional scoring systems such as CURB-65 have inherent limitations. Machine learning (ML) offers a promising approach for prediction. We previously introduced the Blood Culture Prediction Index (BCPI) model, leveraging solely on complete blood count (CBC) and differential leukocyte count (DC), demonstrating its effectiveness in predicting bacteremia. Nevertheless, its potential in assessing pneumonia remains unexplored. Therefore, this study aims to compare the effectiveness of BCPI and CURB-65 in assessing pneumonia severity in an emergency department (ED) setting and develop an integrated ML model to enhance efficiency. METHODS This retrospective study was conducted at a 3400-bed tertiary medical center in Taiwan. Data from 9,352 patients with pneumonia in the ED between 2019 and 2021 were analyzed in this study. We utilized the BCPI model, which was trained on CBC/DC data, and computed CURB-65 scores for each patient to compare their prognosis prediction capabilities. Subsequently, we developed a novel Cox regression model to predict in-hospital mortality, integrating the BCPI model and CURB-65 scores, aiming to assess whether this integration enhances predictive performance. RESULTS The predictive performance of the BCPI model and CURB-65 score for the 30-day mortality rate in ED patients and the in-hospital mortality rate among admitted patients was comparable across all risk categories. However, the Cox regression model demonstrated an improved area under the ROC curve (AUC) of 0.713 than that of CURB-65 (0.668) for in-hospital mortality (p<0.001). In the lowest risk group (CURB-65=0), the Cox regression model outperformed CURB-65, with a significantly lower mortality rate (2.9% vs. 7.7%, p<0.001). CONCLUSIONS The BCPI model, constructed using CBC/DC data and ML techniques, performs comparably to the widely utilized CURB-65 in predicting outcomes for patients with pneumonia in the ED. Furthermore, by integrating the CURB-65 score and BCPI model into a Cox regression model, we demonstrated improved prediction capabilities, particularly for low-risk patients. Given its simple parameters and easy training process, the Cox regression model may be a more effective prediction tool for classifying patients with pneumonia in the emergency room.
Collapse
Affiliation(s)
- Yin-Ting Lin
- Department of Internal Medicine, Chang Gung Memorial Hospital, No. 6, W. Sec., Jiapu Rd., Puzih, Chiayi County, 613, Taiwan
| | - Ko-Ming Lin
- Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Chang Gung Memorial Hospital, No. 6, W. Sec., Jiapu Rd, Puzih, Chiayi County, 613, Taiwan
| | - Kai-Hsiang Wu
- Department of Emergency Medicine, Chang Gung Memorial Hospital, No. 6, W. Sec., Jiapu Rd., Puzih, Chiayi County, 613, Taiwan.
- Department of Nursing, Chang Gung University of Science and Technology, Chiayi Campus, Chiayi, Taiwan.
- Graduate Institute of Clinical Medical Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan.
| | - Frank Lien
- Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Chang Gung Memorial Hospital, No. 6, W. Sec., Jiapu Rd, Puzih, Chiayi County, 613, Taiwan.
| |
Collapse
|
2
|
Zaki HA, Hamdi Alkahlout B, Shaban E, Mohamed EH, Basharat K, Elsayed WAE, Azad A. The Battle of the Pneumonia Predictors: A Comprehensive Meta-Analysis Comparing the Pneumonia Severity Index (PSI) and the CURB-65 Score in Predicting Mortality and the Need for ICU Support. Cureus 2023; 15:e42672. [PMID: 37649936 PMCID: PMC10462911 DOI: 10.7759/cureus.42672] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/29/2023] [Indexed: 09/01/2023] Open
Abstract
The CURB-65 (confusion, uremia, respiratory rate, blood pressure, age ≥ 65 years) score and the pneumonia severity index (PSI) are widely used and recommended in predicting 30-day mortality and the need for intensive care support in community-acquired pneumonia. This study aims to compare the performance of these two severity scores in both mortality prediction and the need for intensive care support. A systematic review and meta-analysis was carried out, following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) 2020 guidelines, and PubMed, Scopus, ScienceDirect, and Google Scholar were searched for articles published from 2012 to 2022. The reference lists of the included studies were also searched to retrieve possible additional studies. Twenty-five studies reporting prognostic information for CURB 65 and PSI were identified. ReviewManager (RevMan) 5.4.1 was used to produce risk ratios, and a random effects model was used to pool them. Both PSI and CURB-65 showed a high strength in identifying high-risk patients. However, CURB-65 was slightly better in early mortality prediction and had more sensitivity (96.7%) and specificity (89.3%) in predicting admission to intensive care support. Thus, CURB-65 seems to be the preferred tool in predicting mortality and the need for admission into intensive care support.
Collapse
Affiliation(s)
- Hany A Zaki
- Emergency Medicine, Hamad Medical Corporation, Doha, QAT
| | | | - Eman Shaban
- Cardiology, Al Jufairi Diagnosis and Treatment, Doha, QAT
| | | | | | | | - Aftab Azad
- Emergency Medicine, Hamad Medical Corporation, Doha, QAT
| |
Collapse
|
3
|
Evaluating Possible Mechanisms Linking Obesity to COVID-19: a Narrative Review. Obes Surg 2022; 32:1689-1700. [PMID: 35113309 PMCID: PMC8811344 DOI: 10.1007/s11695-022-05933-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 01/20/2022] [Accepted: 01/23/2022] [Indexed: 01/05/2023]
Abstract
Currently, pneumonia caused by the coronavirus disease 2019 (COVID-19) is a pandemic. To date, there is no specific antiviral treatment for the disease, and universal access to the vaccine is a serious challenge. Some observational studies have shown that COVID-19 is more common in countries with a high prevalence of obesity and that people with COVID-19 have a higher body mass index. In these studies, obesity increased the risk of disease, as well as its severity and mortality. This study aimed to review the mechanisms that link obesity to COVID-19.
Collapse
|
4
|
Rezaei B, Ramazani E, Amiri R, Sanaei Z. A cross-sectional study on the prevalence of electrolyte abnormalities in multiple trauma patients in Hamedan, Iran. Health Sci Rep 2021; 4:e239. [PMID: 33732893 PMCID: PMC7944545 DOI: 10.1002/hsr2.239] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2020] [Revised: 12/17/2020] [Accepted: 12/30/2020] [Indexed: 11/09/2022] Open
Abstract
INTRODUCTION Evaluation of electrolyte status and homeostasis is one of the most important components of evaluation and treatment of critically ill patients, especially those with multiple trauma. Electrolyte imbalance can be associated with a bad prognosis and the need of specialized consultancy. AIM The aim of this study was to evaluate and determine the electrolyte status of patients with multiple trauma and evaluate the relationship of electrolyte disorders with patient outcome. METHODS In this cross-sectional study, 370 patients who were referred to the emergency department of Besat Hospital in Hamadan, Iran with multiple trauma were studied. Demographic parameters clinical characteristics such as blood pressure, heart rate, respiratory rate, consciousness score and body temperature, paraclinical characteristics including radiographic status, ultrasound, and electrocardiography and serum levels of sodium, potassium, creatinine, hemoglobin, hematocrit, and BUN and urine analysis was performed. Data regarding the discharge from emergency department or referral to other units were also complete in a questionnaire for each patient. Statistical analyses were performed using SPSSv24. RESULTS Three hundred seventy patients with multiple trauma were studied where 73% of patients were men and 27% were women. One hundred ninety-six patients were discharged from the emergency department, and 174 patients were referred to other units of the hospital. The most common electrolyte abnormalities were hypotension (62.7%), hypernatremia (9.5%), hypokalemia (6.8%), and hypercreatinine (4.6%). The results of independent t-test showed that heart rate and potassium level were significantly higher in patients referred to other units than in patients discharged from the emergency department and respiratory rate and hematocrit were significantly lower in patients referred to other units. CONCLUSION Hypotension, hypernatremia, hypokalemia, hypercreatinine, and abnormal urine analysis were more frequent in patients referred to other units than in patients discharged from the emergency department. These variables can be considered in predicting patient status for referral to other units and delayed hospital discharge.
Collapse
Affiliation(s)
- Bareza Rezaei
- Department of Emergency, Faculty of Medicine, Taleghani HospitalKermanshah University of Medical SciencesKermanshahIran
- Clinical Research Development Center of TaleghaniKermanshah University of Medical SciencesKermanshahIran
| | - Einaz Ramazani
- Department of Emergency, Besat HospitalHamedan University of Medical SciencesHamedanIran
| | - Rahimpour Amiri
- Department of Pediatrics, Faculty of Medicine, Besat HospitalHamedan University of Medical SciencesHamedanIran
| | - Zahra Sanaei
- Department of Community Medicine, Education Development OfficeHamedan University of Medical SciencesHamedanIran
| |
Collapse
|
5
|
Avci S, Perincek G. The alveolar-arterial gradient, pneumonia severity scores and inflammatory markers to predict 30-day mortality in pneumonia. Am J Emerg Med 2020; 38:1796-1801. [PMID: 32739850 DOI: 10.1016/j.ajem.2020.05.048] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2020] [Revised: 05/16/2020] [Accepted: 05/17/2020] [Indexed: 01/05/2023] Open
Abstract
OBJECTIVE The objective of this study was to evaluate the association of elevated alveolar-arterial oxygen (A-a O2) gradient with risk of mortality in hospitalized patients with community-acquired pneumonia (CAP). METHODS This prospective study included 206 patients diagnosed with CAP admitted to the ED. Demographics, comorbidities, arterial blood gas, serum electrolytes, liver-renal functions, complete blood count, NLR, PLR, CRP, CAR, procalcitonin, A-a O2 gradient, expected A-a O2 and A-a O2 difference were evaluated. PSI and CURB-65 scores were classified as follow: a) PSI low risk (I-III) and moderate-high risk (IV-V) groups; b) CURB-65; low risk (0-2) and high risk (3-5) groups. RESULTS The survival rates of the PSI class (I-III) were significantly higher than the ones of the PSI class (IV-V) (92.1% vs. 62.9%, respectively). The percentage of survivors of the CURB-65 score (0-2) group (81.9%) was higher than the survivors of CURB-65 score (3-5) group (27.8%). Creatinine, BUN, uric acid, phosphorus, RDW, CRP, CAR, procalcitonin, lactate, A-a 02 gradient, expected A-a 02 and A-a 02 difference were significantly higher and basophil was lower in non-survivors. A-a O2 gradient (AUC 0.78), A-a O2 difference (AUC 0.74) and albumin (AUC 0.80) showed highest 30-day mortality prediction. NLR (AUC 0.58) and PLR (AUC 0.55) showed lowest 30-day mortality estimation. Procalcitonin (AUC 0.65), PSI class (AUC 0.81) and PSI score (AUC 0.86) indicated statistically significant higher 30-day mortality prediction. CONCLUSION A-a O2 gradient, A-a O2 difference and albumin are potent predictors of 30-day mortality in CAP patients in the ED.
Collapse
Affiliation(s)
- Sema Avci
- Department of Emergency Medicine, Amasya University Sabuncuoglu Serefeddin Research and Training Hospital, Amasya, Turkey.
| | - Gokhan Perincek
- Department of Pulmonology, Kars Harakani State Hospital, Kars, Turkey
| |
Collapse
|
6
|
Jahanihashemi H, Babaie M, Bijani S, Bazzazan M, Bijani B. Poverty as an independent risk factor for in-hospital mortality in community-acquired pneumonia: A study in a developing country population. Int J Clin Pract 2018; 72:e13085. [PMID: 29665161 DOI: 10.1111/ijcp.13085] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/13/2017] [Accepted: 03/18/2018] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND Community-acquired pneumonia (CAP) is one of the most severe lower respiratory tract infections with a high in-hospital mortality. The aim of this study was to investigate the socioeconomic and medical risk factors affecting the prognosis of acute pneumonia. The results of this study can mention the value of socioeconomic backgrounds like poverty and illiteracy in clinical practice, even in a well-known biological phenomenon (eg acute pneumonia). METHODS In this cross-sectional study, all admitted patients to a tertiary teaching hospital with a diagnosis of community acquired pneumonia in a 12-month period were enrolled. Socioeconomic and demographic characteristics, underlying conditions, clinical manifestations and para-clinical test results at admission registered prospectively. A logistic regression model was conducted using in-hospital mortality as the dependent variable. RESULTS A total of 621 patients was included in this study. Among them, 47 patients (7.6%) died during the hospitalisation period. In multiple logistic regression analysis, pleural effusion, a higher CURB-65 score, hyponatremia, hyperglycaemia and poverty (being in the lower economic class) were identified as independent risk factors for in-hospital mortality in community-acquired pneumonia. CONCLUSION Numerous factors can influence the prognosis of CAP. In addition to the CURB-65 score and some other medical risk factors, socioeconomic backgrounds can also affect the early outcome in CAP. In this study, being in the lower economic class (as an indicator of poverty) is interpreted as an independent risk factor for a poor prognosis in CAP.
Collapse
Affiliation(s)
- Hassan Jahanihashemi
- Department of Community Medicine, Qazvin University of Medical Sciences, Qazvin, Iran
| | - Mona Babaie
- Clinical Microbiology Research Centre, Qazvin University of Medical Sciences, Qazvin, Iran
| | - Soroush Bijani
- Clinical Microbiology Research Centre, Qazvin University of Medical Sciences, Qazvin, Iran
| | - Maryam Bazzazan
- Clinical Microbiology Research Centre, Qazvin University of Medical Sciences, Qazvin, Iran
| | - Behzad Bijani
- Clinical Microbiology Research Centre, Qazvin University of Medical Sciences, Qazvin, Iran
| |
Collapse
|
7
|
Rylance J, Waitt P. Pneumonia severity scores in resource poor settings. Pneumonia (Nathan) 2014; 5:30-37. [PMID: 31641572 PMCID: PMC5922327 DOI: 10.15172/pneu.2014.5/481] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2014] [Accepted: 09/09/2014] [Indexed: 01/15/2023] Open
Abstract
Clinical prognostc scores are increasingly used to streamline care in well-resourced setngs. The potental benefts of identfying patents at risk of clinical deterioraton and poor outcome, delivering appropriate higher level clinical care, and increasing efciency are clear. In this focused review, we examine the use and applicability of severity scores applied to patents with community acquired pneumonia in resource poor setngs. We challenge clinical researchers working in such systems to consider the generalisability of existng severity scores in their populatons, and where performance of scores is suboptmal, to promote eforts to develop and validate new tools for the beneft of patents and healthcare systems.
Collapse
Affiliation(s)
- Jamie Rylance
- 15Department of Respiratory Medicine, Clinical Sciences Centre, University Hospital Aintree, Lower Lane, Liverpool, L9 7AL UK
| | - Peter Waitt
- 25Department of Acute Medicine, Arrowe Park Hospital, Arrowe Park Road, Wirral, Merseyside, CH49 5PE UK
| |
Collapse
|