1
|
Xu Y, Guo P, Wang G, Sun X, Wang C, Li H, Cui Z, Zhang P, Feng Y. Integrated analysis of single-cell sequencing and machine learning identifies a signature based on monocyte/macrophage hub genes to analyze the intracranial aneurysm associated immune microenvironment. Front Immunol 2024; 15:1397475. [PMID: 38979407 PMCID: PMC11228246 DOI: 10.3389/fimmu.2024.1397475] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2024] [Accepted: 06/04/2024] [Indexed: 07/10/2024] Open
Abstract
Monocytes are pivotal immune cells in eliciting specific immune responses and can exert a significant impact on the progression, prognosis, and immunotherapy of intracranial aneurysms (IAs). The objective of this study was to identify monocyte/macrophage (Mo/MΦ)-associated gene signatures to elucidate their correlation with the pathogenesis and immune microenvironment of IAs, thereby offering potential avenues for targeted therapy against IAs. Single-cell RNA-sequencing (scRNA-seq) data of IAs were acquired from the Gene Expression Synthesis (GEO) database. The significant infiltration of monocyte subsets in the parietal tissue of IAs was identified using single-cell RNA sequencing and high-dimensional weighted gene co-expression network analysis (hdWGCNA). The integration of six machine learning algorithms identified four crucial genes linked to these Mo/MΦ. Subsequently, we developed a multilayer perceptron (MLP) neural model for the diagnosis of IAs (independent external test AUC=1.0, sensitivity =100%, specificity =100%). Furthermore, we employed the CIBERSORT method and MCP counter to establish the correlation between monocyte characteristics and immune cell infiltration as well as patient heterogeneity. Our findings offer valuable insights into the molecular characterization of monocyte infiltration in IAs, which plays a pivotal role in shaping the immune microenvironment of IAs. Recognizing this characterization is crucial for comprehending the limitations associated with targeted therapies for IAs. Ultimately, the results were verified by real-time fluorescence quantitative PCR and Immunohistochemistry.
Collapse
Affiliation(s)
- Yifan Xu
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Pin Guo
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Guipeng Wang
- Department of Urology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Xiaojuan Sun
- Department of Oncology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Chao Wang
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Huanting Li
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Zhenwen Cui
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Pining Zhang
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Yugong Feng
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| |
Collapse
|
2
|
Autio AH, Paavola J, Tervonen J, Lång M, Elomaa AP, Huuskonen TJ, Huttunen J, Kärkkäinen V, von Und Zu Fraunberg M, Lindgren AE, Koivisto T, Kurola J, Jääskeläinen JE, Kämäräinen OP. Acute evacuation of 54 intracerebral hematomas (aICH) during the microsurgical clipping of a ruptured middle cerebral artery bifurcation aneurysm-illustration of the individual clinical courses and outcomes with a serial brain CT/MRI panel until 12 months. Acta Neurochir (Wien) 2024; 166:17. [PMID: 38231317 PMCID: PMC10794262 DOI: 10.1007/s00701-024-05902-9] [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: 10/08/2023] [Accepted: 12/11/2023] [Indexed: 01/18/2024]
Abstract
PURPOSE In aneurysmal intracerebral hemorrhage (aICH), our review showed the lack of the patient's individual (i) timeline panels and (ii) serial brain CT/MRI slice panels through the aICH evacuation and neurointensive care until the final brain tissue outcome. METHODS Our retrospective cohort consists of 54 consecutive aICH patients from a defined population who acutely underwent the clipping of a middle cerebral artery bifurcation saccular aneurysm (Mbif sIA) with the aICH evacuation at Kuopio University Hospital (KUH) from 2010 to 2019. We constructed the patient's individual timeline panels since the emergency call and serial brain CT/MRI slice panels through the aICH evacuation and neurointensive care until the final brain tissue outcome. The patients were indicated by numbers (1.-54.) in the pseudonymized panels, tables, results, and discussion. RESULTS The aICH volumes on KUH admission (median 46 cm3) plotted against the time from the emergency call to the evacuation (median 8 hours) associated significantly with the rebleeds (n=25) and the deaths (n=12). The serial CT/MRI slice panels illustrated the aICHs, intraventricular hemorrhages (aIVHs), residuals after the aICH evacuations, perihematomal edema (PHE), delayed cerebral injury (DCI), and in the 42 survivors, the clinical outcome (mRS) and the brain tissue outcome. CONCLUSIONS Regarding aICH evacuations, serial brain CT/MRI panels present more information than words, figures, and graphs. Re-bleeds associated with larger aICH volumes and worse outcomes. Swift logistics until the sIA occlusion with aICH evacuation is required, also in duty hours and weekends. Intraoperative CT is needed to illustrate the degree of aICH evacuation. PHE may evoke uncontrollable intracranial pressure (ICP) in spite of the acute aICH volume reduction.
Collapse
Affiliation(s)
- Anniina H Autio
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland.
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland.
| | - Juho Paavola
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Joona Tervonen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Maarit Lång
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
- Neurointensive Care Unit, Kuopio University Hospital, Kuopio, Finland
| | - Antti-Pekka Elomaa
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Terhi J Huuskonen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Jukka Huttunen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Virve Kärkkäinen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
| | - Mikael von Und Zu Fraunberg
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
- Department of Neurosurgery, Oulu University Hospital, Oulu, Finland
- Research Unit of Clinical Medicine, University of Oulu, Oulu, Finland
| | - Antti E Lindgren
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
- Clinical Radiology, Kuopio University Hospital, Kuopio, Finland
| | - Timo Koivisto
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Jouni Kurola
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
- Center for Prehospital Emergency Care, Kuopio University Hospital, Kuopio, Finland
| | - Juha E Jääskeläinen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| | - Olli-Pekka Kämäräinen
- Neurosurgery, NeuroCenter, Kuopio University Hospital, PL 100, 70029, Kuopio, Finland
- Institute of Clinical Medicine, School of Medicine, Faculty of Health Sciences, University of Eastern Finland, Kuopio, Finland
| |
Collapse
|
3
|
Wang R, Zhang J, Shan B, He M, Xu J. XGBoost Machine Learning Algorithm for Prediction of Outcome in Aneurysmal Subarachnoid Hemorrhage. Neuropsychiatr Dis Treat 2022; 18:659-667. [PMID: 35378822 PMCID: PMC8976557 DOI: 10.2147/ndt.s349956] [Citation(s) in RCA: 25] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/25/2021] [Accepted: 03/09/2022] [Indexed: 11/23/2022] Open
Abstract
BACKGROUND Patients suffered aneurysmal subarachnoid hemorrhage (aSAH) usually develop poor survival and functional outcome. Evaluating aSAH patients at high risk of poor outcome is necessary for clinicians to make suitable therapeutical strategy. This study is conducted to develop prognostic model using XGBoost (extreme gradient boosting) algorithm in aSAH. METHODS A total of 351 aSAH patients admitted to West China hospital were identified. Patients were divided into training set and test set with ratio of 7:3 to testify the predictive value of XGBoost based prognostic model. Additionally, logistic regression model was also constructed and compared with XGBoost based model. Area under the receiver operating characteristic curve (AUC), sensitivity and specificity were calculated to evaluate the value of XGBoost and logistic regression. RESULTS There were 74 (21.1%) non-survivors and 148 (42.1%) patients with unfavorable functional outcome. Non-survivors had older age (p=0.025), lower Glasgow coma scale (GCS) (p<0.001), higher World Federation of Neurosurgical Societies WFNS score (p<0.001), mFisher score (p<0.001). The incidence of intraventricular hemorrhage (IVH) (p=0.025) and delayed cerebral ischemia (DCI) (p<0.001) was higher in non-survivors than survivors. The AUC of XGBoost model for predicting mortality and unfavorable functional outcome were 0.950 and 0.958, which were higher than 0.767 and 0.829 of logistic regression model. CONCLUSION XGBoost based model is more precise than logistic regression model in predicting outcome of aSAH patients. Using XGBoost prognostic model is helpful for clinicians to identify high-risk aSAH patients and therefore strengthen medical care.
Collapse
Affiliation(s)
- Ruoran Wang
- Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, Sichuan Province, People's Republic of China
| | - Jing Zhang
- Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, Sichuan Province, People's Republic of China
| | - Baoyin Shan
- Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, Sichuan Province, People's Republic of China
| | - Min He
- Department of Critical care medicine, West China Hospital, Sichuan University, Chengdu, Sichuan Province, People's Republic of China
| | - Jianguo Xu
- Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, Sichuan Province, People's Republic of China
| |
Collapse
|
4
|
Maldaner N, Zeitlberger AM, Sosnova M, Goldberg J, Fung C, Bervini D, May A, Bijlenga P, Schaller K, Roethlisberger M, Rychen J, Zumofen DW, D'Alonzo D, Marbacher S, Fandino J, Daniel RT, Burkhardt JK, Chiappini A, Robert T, Schatlo B, Schmid J, Maduri R, Staartjes VE, Seule MA, Weyerbrock A, Serra C, Stienen MN, Bozinov O, Regli L. Development of a Complication- and Treatment-Aware Prediction Model for Favorable Functional Outcome in Aneurysmal Subarachnoid Hemorrhage Based on Machine Learning. Neurosurgery 2021; 88:E150-E157. [PMID: 33017031 DOI: 10.1093/neuros/nyaa401] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2020] [Accepted: 07/12/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Current prognostic tools in aneurysmal subarachnoid hemorrhage (aSAH) are constrained by being primarily based on patient and disease characteristics on admission. OBJECTIVE To develop and validate a complication- and treatment-aware outcome prediction tool in aSAH. METHODS This cohort study included data from an ongoing prospective nationwide multicenter registry on all aSAH patients in Switzerland (Swiss SOS [Swiss Study on aSAH]; 2009-2015). We trained supervised machine learning algorithms to predict a binary outcome at discharge (modified Rankin scale [mRS] ≤ 3: favorable; mRS 4-6: unfavorable). Clinical and radiological variables on admission ("Early" Model) as well as additional variables regarding secondary complications and disease management ("Late" Model) were used. Performance of both models was assessed by classification performance metrics on an out-of-sample test dataset. RESULTS Favorable functional outcome at discharge was observed in 1156 (62.0%) of 1866 patients. Both models scored a high accuracy of 75% to 76% on the test set. The "Late" outcome model outperformed the "Early" model with an area under the receiver operator characteristics curve (AUC) of 0.85 vs 0.79, corresponding to a specificity of 0.81 vs 0.70 and a sensitivity of 0.71 vs 0.79, respectively. CONCLUSION Both machine learning models show good discrimination and calibration confirmed on application to an internal test dataset of patients with a wide range of disease severity treated in different institutions within a nationwide registry. Our study indicates that the inclusion of variables reflecting the clinical course of the patient may lead to outcome predictions with superior predictive power compared to a model based on admission data only.
Collapse
Affiliation(s)
- Nicolai Maldaner
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland.,Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Anna M Zeitlberger
- Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Marketa Sosnova
- Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Johannes Goldberg
- Department of Neurosurgery, University Hospital Bern, Bern, Switzerland
| | - Christian Fung
- Department of Neurosurgery, University Hospital Bern, Bern, Switzerland.,Department of Neurosurgery, Medical Center - University of Freiburg, Germany
| | - David Bervini
- Department of Neurosurgery, University Hospital Bern, Bern, Switzerland
| | - Adrien May
- Department of Neurosurgery, University Clinic Geneva, Geneva, Switzerland
| | - Philippe Bijlenga
- Department of Neurosurgery, University Clinic Geneva, Geneva, Switzerland
| | - Karl Schaller
- Department of Neurosurgery, University Clinic Geneva, Geneva, Switzerland
| | | | - Jonathan Rychen
- Department of Neurosurgery, Basel University Hospital, Basel, Switzerland
| | - Daniel W Zumofen
- Department of Neurosurgery, Neurology, and Radiology, Maimonides Medical Center, SUNY Downstate University, Brooklyn, NY, USA
| | - Donato D'Alonzo
- Department of Neurosurgery, Kantonsspital Aarau, Aarau, Switzerland
| | - Serge Marbacher
- Department of Neurosurgery, Kantonsspital Aarau, Aarau, Switzerland
| | - Javier Fandino
- Department of Neurosurgery, Kantonsspital Aarau, Aarau, Switzerland
| | - Roy Thomas Daniel
- Department of Clinical Neurosciences, Service of Neurosurgery, Lausanne University Hospital (CHUV), Lausanne, Switzerland
| | | | - Alessio Chiappini
- Department of Neurosurgery, Ospedale Regionale di Lugano, Switzerland
| | - Thomas Robert
- Department of Neurosurgery, Ospedale Regionale di Lugano, Switzerland
| | - Bawarjan Schatlo
- Department of Neurosurgery, University Hospital Göttingen, Germany
| | | | - Rodolfo Maduri
- Neurosurgery, Clinique de Genolier, Swiss Medical Network, Genolier, Switzerland
| | - Victor E Staartjes
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland
| | - Martin A Seule
- Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Astrid Weyerbrock
- Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Carlo Serra
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland
| | - Martin Nikolaus Stienen
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland
| | - Oliver Bozinov
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland.,Department of Neurosurgery, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Luca Regli
- Department of Neurosurgery, University Hospital Zurich & Clinical Neuroscience Center, University of Zurich, Zurich, Switzerland
| |
Collapse
|