1
|
Chen D, Zhou K, Tian R, Wang R, Zhou Z. Predictive value of the dynamics of absolute lymphocyte counts for 90-day mortality in ICU sepsis patients: a retrospective big data study. BMJ Open 2024; 14:e084562. [PMID: 38960455 PMCID: PMC11227848 DOI: 10.1136/bmjopen-2024-084562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Accepted: 06/19/2024] [Indexed: 07/05/2024] Open
Abstract
OBJECTIVES The objective of the study was to assess the clinical predictive value of the dynamics of absolute lymphocyte count (ALC) for 90-day all-cause mortality in sepsis patients in intensive care unit (ICU). DESIGN Retrospective cohort study using big data. SETTING This study was conducted using the Medical Information Mart for Intensive Care IV database V.2.0 database. PRIMARY AND SECONDARY OUTCOME MEASURES The primary outcome was 90-day all-cause mortality. PARTICIPANTS Patients were included if they were diagnosed with sepsis on the first day of ICU admission. Exclusion criteria were ICU stay under 24 hours; the absence of lymphocyte count on the first day; extremely high lymphocyte count (>10×109/L); history of haematolymphatic tumours, bone marrow or solid organ transplants; survival time under 72 hours and previous ICU admissions. The analysis ultimately included 17 329 sepsis patients. RESULTS The ALC in the non-survivors group was lower on days 1, 3, 5 and 7 after admission (p<0.001). The ALC on day 7 had the highest area under the curve (AUC) value for predicting 90-day mortality. The cut-off value of ALC on day 7 was 1.0×109/L. In the restricted cubic spline plot, after multivariate adjustments, patients with higher lymphocyte counts had a better prognosis. After correction, in the subgroups with Sequential Organ Failure Assessment score ≥6 or age ≥60 years, ALC on day 7 had the lowest HR value (0.79 and 0.81, respectively). On the training and testing set, adding the ALC on day 7 improved all prediction models' AUC and average precision values. CONCLUSIONS Dynamic changes of ALC are closely associated with 90-day all-cause mortality in sepsis patients. Furthermore, the ALC on day 7 after admission is a better independent predictor of 90-day mortality in sepsis patients, especially in severely ill or young sepsis patients.
Collapse
Affiliation(s)
- Daonan Chen
- Shanghai General Hospital, Department of Critical Care Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Kun Zhou
- Shanghai General Hospital, Department of Hematology, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Rui Tian
- Shanghai General Hospital, Department of Critical Care Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ruilan Wang
- Shanghai General Hospital, Department of Critical Care Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zhigang Zhou
- Shanghai General Hospital, Department of Critical Care Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| |
Collapse
|
2
|
Gunčar G, Kukar M, Smole T, Moškon S, Vovko T, Podnar S, Černelč P, Brvar M, Notar M, Köster M, Jelenc MT, Osterc Ž, Notar M. Differentiating viral and bacterial infections: A machine learning model based on routine blood test values. Heliyon 2024; 10:e29372. [PMID: 38644832 PMCID: PMC11033127 DOI: 10.1016/j.heliyon.2024.e29372] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 04/02/2024] [Accepted: 04/07/2024] [Indexed: 04/23/2024] Open
Abstract
The growing threat of antibiotic resistance necessitates accurate differentiation between bacterial and viral infections for proper antibiotic administration. In this study, a Virus vs. Bacteria machine learning model was developed to distinguish between these infection types using 16 routine blood test results, C-reactive protein concentration (CRP), biological sex, and age. With a dataset of 44,120 cases from a single medical center, the model achieved an accuracy of 82.2 %, a sensitivity of 79.7 %, a specificity of 84.5 %, a Brier score of 0.129, and an area under the ROC curve (AUC) of 0.905, outperforming a CRP-based decision rule. Notably, the machine learning model enhanced accuracy within the CRP range of 10-40 mg/L, a range where CRP alone is less informative. These results highlight the advantage of integrating multiple blood parameters in diagnostics. The "Virus vs. Bacteria" model paves the way for advanced diagnostic tools, leveraging machine learning to optimize infection management.
Collapse
Affiliation(s)
- Gregor Gunčar
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
- Faculty of Chemistry and Chemical Technology, University of Ljubljana, Slovenia
| | - Matjaž Kukar
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
- Faculty of Computer and Information Science, University of Ljubljana, Slovenia
| | - Tim Smole
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | - Sašo Moškon
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | - Tomaž Vovko
- Department of Infectious Diseases, University Medical Centre Ljubljana, Slovenia
| | - Simon Podnar
- Division of Neurology, University Medical Centre Ljubljana, Slovenia
| | - Peter Černelč
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | - Miran Brvar
- Centre for Clinical Toxicology and Pharmacology, University Medical Centre Ljubljana, Slovenia
| | - Mateja Notar
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | - Manca Köster
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | | | - Žiga Osterc
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| | - Marko Notar
- Smart Blood Analytics Swiss SA, CH-8008, Zürich, Switzerland
| |
Collapse
|
3
|
Zhang J, Zhao Q, Hu Z. Clinical predictive value of the initial neutrophils to lymphocytes and platelets ratio for prognosis of sepsis patients in the intensive care unit: a retrospective study. Front Med (Lausanne) 2024; 11:1351492. [PMID: 38318247 PMCID: PMC10840849 DOI: 10.3389/fmed.2024.1351492] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Accepted: 01/02/2024] [Indexed: 02/07/2024] Open
Abstract
Background Neutrophils to lymphocytes and platelets (N/LP) ratio has been confirmed as an indirect marker of inflammation. In this study, we aimed to further evaluate the prognostic significance of the N/LP ratio in sepsis patients admitted to the ICU. Methods Sepsis patients from the Affiliated Hospital of Jiangsu University were retrospectively enrolled from January 2015 and July 2023. The primary outcomes were 30/60 days mortality. The secondary outcomes included the incidence of AKI, vasoactive drug, CRRT, invasive ventilation, length of ICU stay, length of hospital stay and ICU mortality. Results A total of 1,066 sepsis patients were enrolled with a median age of 75.0 (66.0, 85.0) years, and 62.5% of them being male. The 30 days and 60 days mortality rates were found to be 28.7 and 34.0%, respectively, while the incidence of AKI was 45.2%. Based on their N/LP ratios, we classified the sepsis patients into three groups: low, middle, and high, consisting of 266, 534, and 266 patients, respectively. According the Cox proportional hazard model, the middle and high N/LP groups were associated with a 1.990/3.106-fold increase in 30 days mortality risk and a 2.066/3.046-fold increase in 60 days mortality risk compared with the low N/LP group. Besides, multivariate logistic regression model suggested that the risk of AKI occurrence increased 2.460 fold in the high group compared to the low group. However, through subgroup analyses, we observed substantial variations in the association between N/LP ratios and 30/60 days mortality rates as well as the incidence of AKI among different populations. Notably, the N/LP ratio measured at ICU admission exhibited a higher AUC for predicting 30/60 days mortality (0.684/0.687). Additionally, we observed a good predictive power for the occurrence of AKI (AUC: 0.645) using the N/LP ratio measured at sepsis prognosis. Regarding the other secondary outcomes, the N/LP ratio was associated with disease severity in sepsis patients, including the need for vasoactive drugs, length of ICU stay, and ICU mortality. Conclusion The N/LP ratio at ICU admission was found to have a significant independent association with 30/60 days mortality and the incidence of AKI in sepsis patients.
Collapse
Affiliation(s)
| | | | - Zhenkui Hu
- Department of Critical Care Medicine, The Affiliated Hospital, Jiangsu University, Zhenjiang, China
| |
Collapse
|
4
|
Di Rosa M, Sabbatinelli J, Soraci L, Corsonello A, Bonfigli AR, Cherubini A, Sarzani R, Antonicelli R, Pelliccioni G, Galeazzi R, Marchegiani F, Iuorio S, Colombo D, Burattini M, Lattanzio F, Olivieri F. Neutrophil-to-lymphocyte ratio (NLR) predicts mortality in hospitalized geriatric patients independent of the admission diagnosis: a multicenter prospective cohort study. J Transl Med 2023; 21:835. [PMID: 37990223 PMCID: PMC10664513 DOI: 10.1186/s12967-023-04717-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Accepted: 11/09/2023] [Indexed: 11/23/2023] Open
Abstract
BACKGROUND The Neutrophil-to-lymphocyte ratio (NLR) is a marker of poor prognosis in hospitalized older patients with different diseases, but there is still no consensus on the optimal cut-off value to identify older patients at high-risk of in-hospital mortality. Therefore, in this study we aimed at both validating NLR as a predictor of death in older hospitalized patients and assess whether the presence of specific acute diseases can modify its predictive value. METHODS This prospective cohort study included 5034 hospitalizations of older patients admitted to acute care units in the context of the ReportAge study. NLR measured at admission was considered as the exposure variable, while in-hospital mortality was the outcome of the study. ROC curves with Youden's method and restricted cubic splines were used to identify the optimal NLR cut-off of increased risk. Cox proportional hazard models, stratified analyses, and Kaplan-Meier survival curves were used to analyse the association between NLR and in-hospital mortality. RESULTS Both continuous and categorical NLR value (cut-off ≥ 7.95) predicted mortality in bivariate and multivariate prognostic models with a good predictive accuracy. The magnitude of this association was even higher in patients without sepsis, congestive heart failure, and pneumonia, and those with higher eGFR, albumin, and hemoglobin (p < 0.001). A negative multiplicative interaction was found between NLR and eGFR < 45 (p = 0.001). CONCLUSIONS NLR at admission is a readily available and cost-effective biomarker that could improve identification of geriatric patients at high risk of death during hospital stay independent of admitting diagnosis, kidney function and hemoglobin levels.
Collapse
Affiliation(s)
- Mirko Di Rosa
- Centre for Biostatistics and Applied Geriatric Clinical Epidemiology, IRCCS INRCA, Ancona, Italy
| | - Jacopo Sabbatinelli
- Department of Clinical and Molecular Sciences, Università Politecnica Delle Marche, Ancona, Italy
- Laboratory Medicine Unit, Azienda Ospedaliero Universitaria Delle Marche, Ancona, Italy
| | - Luca Soraci
- Unit of Geriatric Medicine, IRCSS INRCA, C.da Muoio Piccolo, 87100, Cosenza, Italy.
| | - Andrea Corsonello
- Centre for Biostatistics and Applied Geriatric Clinical Epidemiology, IRCCS INRCA, Ancona, Italy
- Unit of Geriatric Medicine, IRCSS INRCA, C.da Muoio Piccolo, 87100, Cosenza, Italy
- Department of Pharmacy, Health and Nutritional Sciences, University of Calabria, Rende, Italy
| | | | - Antonio Cherubini
- Geriatria, Accettazione Geriatrica e Centro di ricerca per l'invecchiamento, IRCCS INRCA, Ancona, Italy
| | - Riccardo Sarzani
- Department of Clinical and Molecular Sciences, Università Politecnica Delle Marche, Ancona, Italy
- Internal Medicine and Geriatrics, IRCCS INRCA, Ancona, Italy
| | | | | | - Roberta Galeazzi
- Clinic of Laboratory and Precision Medicine, IRCCS INRCA, Ancona, Italy
| | | | | | | | | | | | - Fabiola Olivieri
- Department of Clinical and Molecular Sciences, Università Politecnica Delle Marche, Ancona, Italy
- Clinic of Laboratory and Precision Medicine, IRCCS INRCA, Ancona, Italy
| |
Collapse
|
5
|
Mahmoud EO, Elsabagh YA, Abd El Ghaffar N, Fawzy MW, Hussein MA. Atherosclerosis Associated With COVID-19: Acute, Tends to Severely Involve Peripheral Arteries, and May be Reversible. Angiology 2023:33197231198253. [PMID: 37611951 DOI: 10.1177/00033197231198253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/25/2023]
Abstract
Arterial stiffness was reported with corona virus disease 2019 (COVID-19). We studied atherosclerosis in COVID-19 directly through duplex ultrasound measurements and their relation to co-morbidities, clinical and laboratory severity markers, and serum interleukin (IL) 6 and 17. Serum IL 6 and 17, average carotid intima-media thickness (cIMT), diameter and peak systolic velocities (PSV) of tibial, ulnar, radial arteries, and ankle brachial index (ABI) were measured in 44 COVID-19 patients and 44 healthy controls. Serum IL6, IL17, PSV, and cIMT were higher while diameter was lower (P ≤ .01) in cases. Clinical severity index correlated positively with age, co-morbidities, ferritin, IL6, IL17, cIMT, and PSV (P ≤ .04) and negatively with diameter and ABI (P = .04). Patients with severe lymphopenia had higher PSV, IL6, and IL17 and lower diameter (P < .00001). Ferritin positively correlated with PSV and negatively with diameter and ABI (P ≤ .01). Those who received an IL6 inhibitor (tocilizumab) showed lower PSV and higher diameter (P ≤ .01). In multiple regression analysis, IL17 and (age, co-morbidities) were related to (PSV, diameter) and cIMT (P ≤ .001, ≤0.02), respectively. COVID-19 may be associated with subclinical acute and may be reversible atherosclerosis severely involving peripheral arteries.
Collapse
Affiliation(s)
- Eman O Mahmoud
- Rheumatology and Clinical Immunology Unit, Internal Medicine Department, Cairo University, Cairo, Egypt
| | - Yumn A Elsabagh
- Rheumatology and Clinical Immunology Unit, Internal Medicine Department, Cairo University, Cairo, Egypt
| | | | - Mary Wadie Fawzy
- Rheumatology and Clinical Immunology Unit, Internal Medicine Department, Cairo University, Cairo, Egypt
| | - Mohamed A Hussein
- Rheumatology and Clinical Immunology Unit, Internal Medicine Department, Cairo University, Cairo, Egypt
| |
Collapse
|