1
|
Shlobin NA, Rosseau G. Opportunities and Considerations for the Incorporation of Artificial Intelligence into Global Neurosurgery: A Generative Pretrained Transformer Chatbot-Based Approach. World Neurosurg 2024; 186:e398-e412. [PMID: 38561032 DOI: 10.1016/j.wneu.2024.03.149] [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: 02/29/2024] [Revised: 03/25/2024] [Accepted: 03/26/2024] [Indexed: 04/04/2024]
Abstract
OBJECTIVE Global neurosurgery is a public health focus in neurosurgery that seeks to ensure safe, timely, and affordable neurosurgical care to all individuals worldwide. Although investigators have begun to explore the promise of artificial intelligence (AI) for neurosurgery, its applicability to global neurosurgery has been largely hypothetical. We characterize opportunities and considerations for the incorporation of AI into global neurosurgery by synthesizing key themes yielded from a series of generative pretrained transformers (GPTs), discuss important limitations of GPTs and cautions when using AI in neurosurgery, and develop a framework for the equitable incorporation of AI into global neurosurgery. METHODS ChatGPT, Bing Chat/Copilot, You, Perplexity.ai, and Google Bard were queried with the prompt "How can AI be incorporated into global neurosurgery?" A layered ChatGPT-based thematic analysis was performed. The authors synthesized the results into opportunities and considerations for the incorporation of AI in global neurosurgery. A Pareto analysis was conducted to determine common themes. RESULTS Eight opportunities and 14 important considerations were synthesized. Six opportunities related to patient care, 1 to education, and another to public health planning. Four of the important considerations were deemed specific to global neurosurgery. The Pareto analysis included all 8 opportunities and 5 considerations. CONCLUSIONS AI may be incorporated into global neurosurgery in a variety of capacities requiring numerous considerations. The framework presented in this manuscript may facilitate the incorporation of AI into global neurosurgery initiatives while balancing contextual factors and the reality of limited resources.
Collapse
Affiliation(s)
- Nathan A Shlobin
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA.
| | - Gail Rosseau
- Department of Neurosurgery, George Washington University School of Medicine and Health Sciences, Washington, District of Columbia, USA; Barrow Global, Barrow Neurological Institute, Phoenix, Arizona, USA
| |
Collapse
|
2
|
Zhou Z, Huang C, Fu P, Huang H, Zhang Q, Wu X, Yu Q, Sun Y. Prediction of in-hospital hypokalemia using machine learning and first hospitalization day records in patients with traumatic brain injury. CNS Neurosci Ther 2022; 29:181-191. [PMID: 36258296 PMCID: PMC9804086 DOI: 10.1111/cns.13993] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2022] [Revised: 09/18/2022] [Accepted: 09/23/2022] [Indexed: 02/06/2023] Open
Abstract
AIMS Hypokalemia is a common complication following traumatic brain injury, which may complicate treatment and lead to unfavorable outcomes. Identifying patients at risk of hypokalemia on the first day of admission helps to implement prophylactic treatment, reduce complications, and improve prognosis. METHODS This multicenter retrospective study was performed between January 2017 and December 2020 using the electronic medical records of patients admitted due to traumatic brain injury. A propensity score matching approach was adopted with a ratio of 1:1 to overcome overfitting and data imbalance during subgroup analyses. Five machine learning algorithms were applied to generate a best-performed prediction model for in-hospital hypokalemia. The internal fivefold cross-validation and external validation were performed to demonstrate the interpretability and generalizability. RESULTS A total of 4445 TBI patients were recruited for analysis and model generation. Hypokalemia occurred in 46.55% of recruited patients and the incidences of mild, moderate, and severe hypokalemia were 32.06%, 12.69%, and 1.80%, respectively. Hypokalemia was associated with increased mortality, while severe hypokalemia cast greater impacts. The logistic regression algorithm had the best performance in predicting decreased serum potassium and moderate-to-severe hypokalemia, with an AUC of 0.73 ± 0.011 and 0.74 ± 0.019, respectively. The prediction model was further verified using two external datasets, including our previous published data and the open-assessed Medical Information Mart for Intensive Care database. Linearized calibration curves showed no statistical difference (p > 0.05) with perfect predictions. CONCLUSIONS The occurrence of hypokalemia following traumatic brain injury can be predicted by first hospitalization day records and machine learning algorithms. The logistic regression algorithm showed an optimal predicting performance verified by both internal and external validation.
Collapse
Affiliation(s)
- Zhengyu Zhou
- Department of Anesthesia, Huashan HospitalFudan UniversityShanghaiChina
| | - Chiungwei Huang
- Health Consultation and Physical Examination Center, Zhongshan HospitalFudan UniversityShanghaiChina,Department of Neurosurgery, Huashan Hospital, Shanghai Medical CollegeFudan UniversityShanghaiChina
| | - Pengfei Fu
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical CollegeFudan UniversityShanghaiChina
| | - Hong Huang
- Information Center, Huashan HospitalFudan UniversityShanghaiChina
| | - Qi Zhang
- Information Center, Huashan HospitalFudan UniversityShanghaiChina
| | - Xuehai Wu
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical CollegeFudan UniversityShanghaiChina,National Center for Neurological DisordersShanghaiChina,Shanghai Key Laboratory of Brain Function Restoration and Neural RegenerationShanghaiChina,Neurosurgical Institute of Fudan UniversityShanghaiChina,Shanghai Clinical Medical Center of NeurosurgeryShanghaiChina
| | - Qiong Yu
- Department of Anesthesia, Huashan HospitalFudan UniversityShanghaiChina
| | - Yirui Sun
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical CollegeFudan UniversityShanghaiChina,National Center for Neurological DisordersShanghaiChina,Shanghai Key Laboratory of Brain Function Restoration and Neural RegenerationShanghaiChina,Neurosurgical Institute of Fudan UniversityShanghaiChina,Shanghai Clinical Medical Center of NeurosurgeryShanghaiChina
| |
Collapse
|
3
|
Ghannam MM, Davies JM. Application of Big Data in Vascular Neurosurgery. Neurosurg Clin N Am 2022; 33:469-482. [DOI: 10.1016/j.nec.2022.06.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
4
|
Holste KG, Chopra Z, Saleh S, Saadeh YS, Park P, Maher CO. Editorial. The use of big data for improving understanding of the natural history of neurosurgical disease. Neurosurg Focus 2022; 52:E2. [DOI: 10.3171/2022.1.focus21712] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Affiliation(s)
| | - Zoey Chopra
- Department of Neurosurgery and
- School of Medicine, University of Michigan, Ann Arbor, Michigan
| | | | | | | | | |
Collapse
|
5
|
Vilanilam G, Abraham L. Big data in clinical sciences-value, impact, and fallacies. ARCHIVES OF MEDICINE AND HEALTH SCIENCES 2022. [DOI: 10.4103/amhs.amhs_296_21] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
|
6
|
Shlobin NA, Kedda J, Wishart D, Garcia RM, Rosseau G. Surgical Management of Chronic Subdural Hematoma in Older Adults: A Systematic Review. J Gerontol A Biol Sci Med Sci 2021; 76:1454-1462. [PMID: 33220683 DOI: 10.1093/gerona/glaa293] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2020] [Indexed: 02/05/2023] Open
Abstract
BACKGROUND Chronic subdural hematoma (cSDH) is a form of intracranial hemorrhage common in older adults. Optimal treatment remains controversial. We conducted a systematic review to identify surgical thresholds, characterize outcomes, and delineate critical considerations in the surgical management of older adults in order to summarize the evidence supporting the best contemporary management of cSDH. METHODS A systematic review exploring surgical management of cSDH among individuals aged 65 years and older was conducting by searching the PubMed, Embase, and Scopus databases for articles in English. Abstracts from articles were read and selected for full-text review according to a priori criteria. Relevant full-text articles were analyzed for bibliographic data, aim, study design, population, interventions, and outcomes. RESULTS Of 1473 resultant articles, 21 were included. Surgery rationale was case-by-case for symptomatic patients with cSDH. Surgery was superior to conservative management and promoted equivalent neurologic outcomes and rates of complications. Recurrence and reoperation rates in older adults were similar to younger individuals. Some studies reported higher mortality rates for older adults, while others reported no difference. Anticoagulation or antiplatelet agent use did not seem to be associated with poorer outcomes in older adults. CONCLUSIONS Surgery for cSDH in older adults leads to favorable neurologic outcomes without increased risk of overall complications, recurrence, or reoperation compared to younger patients. However, older adults may be at increased risk for mortality after surgery. It is important to determine use of anticoagulant or antiplatelet agents in older adults to optimally manage patients with cSDH.
Collapse
Affiliation(s)
- Nathan A Shlobin
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois
| | - Jayanidhi Kedda
- Department of Neurosurgery, George Washington University School of Medicine & Health Sciences, Washington, District of Columbia
| | - Danielle Wishart
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois
| | - Roxanna M Garcia
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois
| | - Gail Rosseau
- Department of Neurosurgery, George Washington University School of Medicine & Health Sciences, Washington, District of Columbia
| |
Collapse
|
7
|
Chen YJ, Nie C, Lu H, Zhang L, Chen HL, Wang SY, Li W, Shen S, Wang H. Monitored Anesthetic Care Combined with Scalp Nerve Block in Awake Craniotomy: An Effective Attempt at Enhanced Recovery After Neurosurgery. World Neurosurg 2021; 154:e509-e519. [PMID: 34303853 DOI: 10.1016/j.wneu.2021.07.069] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Accepted: 07/15/2021] [Indexed: 01/24/2023]
Abstract
BACKGROUND Enhanced recovery after surgery has been attempted in neurosurgery at a greater rate. However, concern exists regarding the feasibility of using enhanced recovery after neurosurgery (ERANS). How to manage available resources to safely perform ERANS and improve clinical outcomes has been the subject of much debate and discussion. METHODS Owing to the paucity of data available on the use of ERANS protocols, we performed the present feasibility study. We studied the outcomes of the protocols used within a tertiary referral neurosurgery center. Data from patients who had undergone awake craniotomy within an ERANS protocol were prospectively recorded in our institution from September 2017 to December 2018. We also evaluated the safety and effectiveness of the novel ERANS protocol. RESULTS A total of 20 patients (mean age, 49.5 ± 17.8 years) were included in the present study. Intraoperative hypertension, hypotension, and bradycardia were present in 4 (20%), 1 (5%), and 1 (5%) patient, respectively. The postoperative morbidities included epilepsy in 1 (5%), pain in 3 (15%), and nausea or vomiting in 2 (10%). No significant changes had occurred in the mean arterial pressure, heart rate, blood glucose, or lactic acid level throughout the procedure. The median length of intensive care unit stay and postoperative hospital stay were 1 and 9.5 days, respectively. No 30-day readmissions or reoperations occurred during the present study. CONCLUSIONS Applying an ERANS protocol was feasible, associated with a low incidence of complications, and acceptable intensive care unit and postoperative hospital lengths of stay. The findings from the present study might provide a new approach for the further research of ERANS.
Collapse
Affiliation(s)
- Yan-Jun Chen
- Department of Anesthesiology, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Cai Nie
- Department of Anesthesiology, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Hao Lu
- Department of Anesthesiology, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Liu Zhang
- Department of Neurosurgery, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Hong-Lin Chen
- Medical Imaging Center, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Shi-Yong Wang
- Department of Neurosurgery, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Wei Li
- Department of Neurosurgery, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Si Shen
- Medical Imaging Center, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China
| | - Hao Wang
- Department of Anesthesiology, The First Affiliated Hospital, Jinan University, Guangzhou, People's Republic of China.
| |
Collapse
|
8
|
Kanmounye US, Sebopelo LA, Keke C, Zolo Y, Senyuy WP, Endalle G, Takoukam R, Sichimba D, Nguembu S, Ghomsi N. Mapping Global Neurosurgery Research Collaboratives: A Social Network Analysis of the 50 Most Cited Global Neurosurgery Articles. NEUROSURGERY OPEN 2021. [DOI: 10.1093/neuopn/okab006] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
ABSTRACTSocial network analysis of bibliometric data evaluates the relationships between the articles, authors, and themes of a research niche. The network can be visualized as maps composed of nodes and links. This study aimed to identify and evaluate the relationships between articles, authors, and keywords in global neurosurgery. The authors searched global neurosurgery articles on the Web of Science database from inception to June 18, 2020. The 50 most cited articles were selected and their metadata (document coupling, co-authorship, and co-occurrence) was exported. The metadata were analyzed and visualized with VOSViewer (Centre for Science and Technology Studies, Leiden University, The Netherlands). The articles were published between 1995 and 2020 and they had a median of 4.0 (interquartile range [IQR] = 5.0) citations. There were 5 clusters in the document coupling and 10 clusters in the co-authorship analysis. A total of 229 authors contributed to the articles and Kee B. Park contributed the most to articles (14 publications). Backward citation analysis was organized into 4 clusters and co-occurrence analysis into 7 clusters. The most common themes were pediatric neurosurgery, neurotrauma, and health system strengthening. The authors identified trends, contributors, and themes of highly cited global neurosurgery research. These findings can help establish collaborations and set the agenda in global neurosurgery research.
Collapse
Affiliation(s)
| | - Lorraine Arabang Sebopelo
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Faculty of Medicine, University of Botswana, Gaborone, Botswana
| | - Chiuyu Keke
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Faculty of Medicine, University of Zambia, Lusaka, Zambia
| | - Yvan Zolo
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Faculty of Health Sciences, University of Buea, Buea, Cameroon
| | - Wah Praise Senyuy
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Faculty of Health Sciences, University of Buea, Buea, Cameroon
| | - Genevieve Endalle
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Faculty of Health Sciences, University of Buea, Buea, Cameroon
| | - Régis Takoukam
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Neurosurgery Department, Felix Houphouet Boigny University, Abidjan, Côte d'Ivoire
| | - Dawin Sichimba
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- School of Medicine, Copperbelt University, Kitwe, Zambia
| | - Stéphane Nguembu
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
| | - Nathalie Ghomsi
- Research Department, Association of Future African Neurosurgeons, Yaounde, Cameroon
- Neurosurgery Department, Felix Houphouet Boigny University, Abidjan, Côte d'Ivoire
| |
Collapse
|
9
|
Lundy P, Miller C, Woodrow S. Current US neurosurgical resident involvement, interest, and barriers in global neurosurgery. Neurosurg Focus 2021; 48:E16. [PMID: 32114552 DOI: 10.3171/2019.12.focus19808] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2019] [Accepted: 12/16/2019] [Indexed: 11/06/2022]
Abstract
OBJECTIVE It is estimated that nearly 47 million preventable deaths occur annually due the current worldwide deficit in surgical care; subsequently, the World Health Organization resolved unanimously to endorse a decree to address this deficit. Neurosurgeons from industrialized nations can help address the needs of underserved regions. Exposure during training is critical for young neurosurgeons to gain experience in international work and to cultivate career-long interest. Here, the authors explore the opinions of current residents and interest in global neurosurgery as well as the current state of international involvement, opportunities, and barriers in North American residency training. METHODS An internet-based questionnaire was developed using the authors' university's REDCap database and distributed to neurosurgical residents from US ACGME (Accreditation Council for Graduate Medical Education)-approved programs. Questions focused on the resident's program's involvement and logistics regarding international rotations and the resident's interest level in pursuing these opportunities. RESULTS A 15% response rate was obtained from a broad range of training locations. Twenty-nine percent of respondents reported that their residency program offered elective training opportunities in developing countries, and 7.6% reported having participated in these programs. This cohort unanimously felt that the international rotation was a beneficial experience and agreed that they would do it again. Of those who had not participated, 81.3% reported interest or strong interest in international rotations. CONCLUSIONS The authors' results indicate that, despite a high level of desire for involvement in international rotations, there is limited opportunity for residents to become involved. Barriers such as funding and rotation approval were recognized. It is the authors' hope that governing organizations and residency programs will work to break down these barriers and help establish rotations for trainees to learn abroad and begin to join the cause of meeting global surgical needs. To meet overarching international neurosurgical needs, neurosurgeons of the future must be trained in global neurosurgery.
Collapse
|
10
|
Taha B, Sadda P, Winston G, Odigie E, Londono C, Greenfield JP, Pannullo SC, Hoffman C. Increases in female academic productivity and female mentorship highlight sustained progress in previously identified neurosurgical gender disparities. Neurosurg Focus 2021; 50:E3. [PMID: 33789232 DOI: 10.3171/2020.12.focus20939] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2020] [Accepted: 12/18/2020] [Indexed: 11/06/2022]
Abstract
OBJECTIVE A meta-analysis was performed to understand disparities in the representation of female authorship within the neurosurgical literature and implications for career advancement of women in neurosurgery. METHODS Author names for articles published in 16 of the top neurosurgical journals from 2002 to 2019 were obtained from MEDLINE. The gender of each author was determined using automated prediction methods. Publication trends were compared over time and across subdisciplines. Female authorship was also compared to the proportionate composition of women in the field over time. RESULTS The metadata obtained from 16 major neurosurgical journals yielded 66,546 research articles. Gender was successfully determined for 96% (127,809/133,578) of first and senior authors, while the remainder (3.9%) were unable to be determined through prediction methods. Across all years, 13.3% (8826) of articles had female first authorship and 9.1% (6073) had female senior authorship. Female first authorship increased significantly over time from 5.8% in 2002 to 17.2% in 2019 (p < 0.001). Female senior authorship also increased significantly over time, from 5.5% in 2002 to 12.0% in 2019 (p < 0.001). The journals with the highest proportions of female first authors and senior authors were the Journal of Neurosurgery: Pediatrics (33.5%) and the Asian Journal of Neurosurgery (23.8%), respectively. Operative Neurosurgery had the lowest fraction of female first (12.4%) and senior (4.7%) authors. There was a significant difference between the year-by-year proportion of female neurosurgical trainees and the year-by-year proportion of female neurosurgical first (p < 0.001) and senior (p < 0.001) authors. Articles were also more likely to have a female first author if the senior author of the article was female (OR 2.69, CI 2.52-2.86; p < 0.001). From 1944 to 2019, the Journal of Neurosurgery showed a steady increase in female first and senior authorship, with a plateau beginning in the 1990s. CONCLUSIONS Large meta-analysis techniques have the potential to effectively leverage large amounts of bibliometric data to quantify the representation of female authorship in the neurosurgical literature. The proportion of female authors in major neurosurgical journals has steadily increased. However, the rate of increase in female senior authorship has lagged behind the rate of increase in first authorship, indicating a disparity in academic advancement in women in neurosurgery.
Collapse
Affiliation(s)
- Birra Taha
- 1Department of Neurosurgery, University of Minnesota Medical Center, Minneapolis, Minnesota
| | - Praneeth Sadda
- 2Department of Medicine, Tulane University Medical Center, New Orleans, Louisiana
| | - Graham Winston
- 3Department of Neurological Surgery, NewYork-Presbyterian Hospital, Weill Cornell Medical College; and
| | - Eseosa Odigie
- 3Department of Neurological Surgery, NewYork-Presbyterian Hospital, Weill Cornell Medical College; and
| | | | - Jeffrey P Greenfield
- 3Department of Neurological Surgery, NewYork-Presbyterian Hospital, Weill Cornell Medical College; and
| | - Susan C Pannullo
- 3Department of Neurological Surgery, NewYork-Presbyterian Hospital, Weill Cornell Medical College; and
| | - Caitlin Hoffman
- 3Department of Neurological Surgery, NewYork-Presbyterian Hospital, Weill Cornell Medical College; and
| |
Collapse
|
11
|
Zhu F, Pan Z, Tang Y, Fu P, Cheng S, Hou W, Zhang Q, Huang H, Sun Y. Machine learning models predict coagulopathy in spontaneous intracerebral hemorrhage patients in ER. CNS Neurosci Ther 2021; 27:92-100. [PMID: 33249760 PMCID: PMC7804781 DOI: 10.1111/cns.13509] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2020] [Revised: 10/25/2020] [Accepted: 10/25/2020] [Indexed: 01/01/2023] Open
Abstract
AIMS Coagulation abnormality is one of the primary concerns for patients with spontaneous intracerebral hemorrhage admitted to ER. Conventional laboratory indicators require hours for coagulopathy diagnosis, which brings difficulties for appropriate intervention within the optimal window. This study evaluates the possibility of building efficient coagulopathy prediction models using data mining and machine learning algorithms. METHODS A retrospective cohort enrolled 1668 cases with acute spontaneous intracerebral hemorrhage from three medical centers, excluding those under antithrombotic therapies. Coagulopathy-related clinical parameters were initially screened by univariate analysis. Two machine learning algorithms, the random forest and the support vector machine, were deployed via an approach of four-fold cross-validation to screen out the most important parameters contributing to the occurrence of coagulopathy. Model discrimination was assessed using metrics, including accuracy, precision, recall, and F1 score. RESULTS Albumin/globulin ratio, neutrophil count, lymphocyte percentage, aspartate transaminase, alanine transaminase, hemoglobin, platelet count, white blood cell count, neutrophil percentage, systolic and diastolic pressure were identified as major predictors to the occurrence of acute coagulopathy. Compared to support vector machine, the model based on the random forest algorithm showed better accuracy (93.1%, 95% confidence interval [CI]: 0.913-0.950), precision (92.4%, 95% CI: 0.897-0.951), F1 score (91.5%, 95% CI: 0.889-0.964), and recall score (93.6%, 95% CI: 0.909-0.964), and yielded higher area under the receiver operating characteristic curve (AU-ROC) (0.962, 95% CI: 0.942-0.982). CONCLUSION The constructed models exhibit good prediction accuracy and efficiency. It might be used in clinical practice to facilitate target intervention for acute coagulopathy in patients with spontaneous intracerebral hemorrhage.
Collapse
Affiliation(s)
- Fengping Zhu
- Department of NeurosurgeryHuahsan HospitalFudan UniversityShanghaiChina
- Neurosurgical Institute of Fudan UniversityShanghaiChina
- Shanghai Clinical Medical Center of NeurosurgeryShanghaiChina
- Shanghai Key Laboratory of Brain Function and Restoration and Neural RegenerationShanghaiChina
| | - Zhiguang Pan
- Department of NeurosurgeryHuahsan HospitalFudan UniversityShanghaiChina
- Neurosurgical Institute of Fudan UniversityShanghaiChina
- Shanghai Clinical Medical Center of NeurosurgeryShanghaiChina
- Shanghai Key Laboratory of Brain Function and Restoration and Neural RegenerationShanghaiChina
| | - Ying Tang
- Department of NursingHuahsan HospitalFudan UniversityShanghaiChina
| | - Pengfei Fu
- Department of NeurosurgeryHuahsan HospitalFudan UniversityShanghaiChina
| | - Sijie Cheng
- Information CenterHuahsan HospitalFudan UniversityShanghaiChina
| | - Wenzhong Hou
- Information CenterHuahsan HospitalFudan UniversityShanghaiChina
| | - Qi Zhang
- Information CenterHuahsan HospitalFudan UniversityShanghaiChina
| | - Hong Huang
- Information CenterHuahsan HospitalFudan UniversityShanghaiChina
| | - Yirui Sun
- Department of NeurosurgeryHuahsan HospitalFudan UniversityShanghaiChina
- Neurosurgical Institute of Fudan UniversityShanghaiChina
- Shanghai Clinical Medical Center of NeurosurgeryShanghaiChina
- Shanghai Key Laboratory of Brain Function and Restoration and Neural RegenerationShanghaiChina
| |
Collapse
|
12
|
Behmer Hansen RT, Behmer Hansen RA, Behmer VA, Gold J, Silva N, Dubey A, Nanda A. Update on the global neurosurgery movement: A systematic review of international vernacular, research trends, and authorship. J Clin Neurosci 2020; 79:183-190. [PMID: 33070893 DOI: 10.1016/j.jocn.2020.07.061] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2020] [Accepted: 07/24/2020] [Indexed: 12/20/2022]
Abstract
In 2015, key global and neurosurgical organizations increased collaboration to improve neurosurgical care access, delivery, and outcomes, particularly in low- to middle-income countries (LMICs); sparking what has been termed the global neurosurgery movement. The authors sought to assess trends in usage of the term 'global neurosurgery' in academic literature with particular focus on author affiliations, world regions most frequently discussed, and topics of research performed. A PubMed search for articles indexed as 'global neurosurgery' was completed yielding 277 articles which met inclusion criteria. It was found that over time, use of the term 'global neurosurgery' has increased, with increasing growth notable starting in the year 2008 and continuing into October 2019. Statistical comparisons showed authors with affiliated global neurosurgery centers were more likely to publish studies related to the continent of Africa (47.4% vs 15.9%, p < 0.001), and less likely to focus on countries in Asia (2.6% vs 20.9%, p = 0.023). Use of the term 'global neurosurgery' in the article abstract/title/keywords was associated with focus on LMICs (18.6% vs. 5.1%, p = 0.006). Use of the term 'global neurosurgery' was associated with workforce and capacity as research topics (41.9% vs 22.6%, p = 0.036). While fairly new, the global neurosurgery movement has seen a rapid increase in publications utilizing the term 'global neurosurgery.' Articles frequently have focused on collaborative, targeted workforce capacity building in LMICs. We encourage the development of more global neurosurgery academic centers, especially in non-USA countries, to continue this momentum.
Collapse
Affiliation(s)
| | - Ryan A Behmer Hansen
- Department of Neurosurgery, Rutgers New Jersey Medical School, Newark, NJ, United States.
| | | | - Justin Gold
- University of Rhode Island, Kingston, RI, United States.
| | - Nicole Silva
- Department of Neurosurgery, Rutgers New Jersey Medical School, Newark, NJ, United States.
| | - Arjun Dubey
- Wollongong Hospital - NSW Health, Wollongong, Australia.
| | - Anil Nanda
- Department of Neurosurgery, Rutgers New Jersey Medical School, Newark, NJ, United States.
| |
Collapse
|
13
|
|
14
|
Allareddy V, Rengasamy Venugopalan S, Nalliah RP, Caplin JL, Lee MK, Allareddy V. Orthodontics in the era of big data analytics. Orthod Craniofac Res 2019; 22 Suppl 1:8-13. [DOI: 10.1111/ocr.12279] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2018] [Accepted: 12/05/2018] [Indexed: 12/17/2022]
Affiliation(s)
| | - Shankar Rengasamy Venugopalan
- Department of Orthodontics and Dentofacial OrthopedicsUniversity of Missouri at Kansas City School of Dentistry Kansas City Missouri
| | | | - Jennifer L. Caplin
- Department of OrthodonticsUniversity of Illinois at Chicago College of Dentistry Chicago Illinois
| | - Min Kyeong Lee
- Department of OrthodonticsUniversity of Illinois at Chicago College of Dentistry Chicago Illinois
| | | |
Collapse
|