scholarly journals Comparison of modified mallampati test between sitting and supine positions for prediction of difficult intubation

1970 ◽  
Vol 10 (1) ◽  
pp. 12-15 ◽  
Author(s):  
S Khatiwada ◽  
B Bhattarai ◽  
K Pokharel ◽  
R Acharya ◽  
A Ghirnire ◽  
...  
Keyword(s):  
Difficult Intubation ◽  
Supine Position ◽  
Difficult Laryngoscopy ◽  
Sitting Position ◽  
Predictive Values ◽  
Statistical Measures ◽  
Position Specificity ◽  
Grading Scale ◽  
Sensitivity Specificity ◽  
Grade Iii

Background: Modified Mallampati test is a standard method of assessing the airway for predicting potentially difficult laryngoscopy and intubation. This test requires the patient to be in sitting position for airway evaluation. Although applicable to the majority of patients, airway evaluation in sitting position may not always be convenient or advisable. Objectives: To compare modified Mallampati grades between sitting and supine position and to find out their corelation to Cormack and Lehane laryngoscopy grade. Materials: This prospective study was conducted in 215, ASA I and II patients undergoing various routine surgical procedures under general anaesthesia, in BPKIHS, Dharan over a period of 3 months. The airway assessment was done using modified Mallampati grade in sitting and supine positions. Mallampati grade of III or IV was defined as the predictor of difficult airway. The laryngoscopy grade was assessed using the Cormack and Lehane grading scale. Grade III or IV of Cormack and Lehane grades was defined as the difficult laryngoscopy and assumed as the predictor of difficult intubation. Statistical measures including sensitivity, specificity, positive and negative predictive values and accuracy were used for comparing the two positions for predicting difficult or ease of intubation. Results: Out of 215 patients, majority 146(68%) were females. Mallampati grade III or IV was observed in more patients in supine position compared to sitting position (48.3% vs. 35.8%, p = 0.008). Difficult laryngoscopy was observed in 13(6%) patients. Sensitivity of modified Mallampati test was 77% in both the positions. Predictive value of Mallampati grading for difficult intubation were 13% and 10% and for easy intubation were 96% and 97% respectively in sitting and supine position. Specificity and accuracy of modified Mallampati test were both 67% in sitting position, where as they were 54% and 55% respectively in supine position. Conclusion: Modified Mallampati grade significantly worsens in supine position compared to sitting. However, airway evaluation in both the positions almost equally predicts for difficult intubation. DOI: http://dx.doi.org/10.3126/hren.v10i1.6000 HREN 2012; 10(1): 12-15

Comparison of four methods for predicting difficult intubation

2016 ◽  
Vol 5 (01) ◽  
pp. 4720
Author(s):  
Javaher Foroosh Zadeh F ◽  
Safaii Sara
Keyword(s):  
Difficult Intubation ◽  
Elective Surgery ◽  
Upper Lip ◽  
Laryngoscopic View ◽  
Predictive Values ◽  
Significant Difference ◽  
Combined Test ◽  
Predicted Values ◽  
Sensitivity Specificity ◽  
A Prospective Study

Confirmation of endotracheal tube appointment is of critical importance, since unrecognized esophageal intubation can be rapidly lethal (death, brain damage). The aim of our study was to compare four different methods for prediction of difficult intubation: Mallampati, Thyro-mental distance, ULBT (Upper Lip Bite Test), and Inter incisicor gap. In a prospective study, 448 patients with a mean age of 53.5 who were scheduled for elective surgery were selected randomly and enrolled. Before induction of anesthesia, the airways were assessed by Mallampati test, Thyro mental distance, Upper lip bit test(ULBT) and Inter incisor gap. Laryngoscopic view according to the Cormack and Lehane grading system was determined after induction of anesthesia and Grades 3 and 4 defined as “difficult intubation.” Degree of observed difficulty of intubation was compared to predicted values. Sensitivity, specificity, positive and negative predictive values and accuracy of these tests and their combinations with the ULBT were calculated. Statistical analysis was performed using SPSS version 16. Data were analysis by using Fishers exact and McNemar's test, and a Pvalue. <0.05 was considered statistically significant.  The prevalence of difficult intubation Cormack-Lehane in this study was 8.4%, Mallampati test had the highest sensitivity (47.3%) and Thyro-mental distance was most specific (96%). The ULBT (upper lip bite tests) had most positive and negative predictive value (37.9% & 93. 5%).Data also showed that power of these tests in predicting easy intubation is more than their ability in assessing the likelihood of difficult intubation. There was no significant difference regarding difficult intubation based on gender (P < 0.05), whereas there were significant differences between the older tests and laryngeal view (P < 0.05, Mc-Nemar test). Despite the validity of MMP, TMD, ULBT and IIG in predicting easy intubation is much greater than the value in prediction of difficult intubation; however, the simplicity of performing these tests and results of the four tests in evaluating patients before surgery by combination of tests in predicting difficult intubation will likely safe. It seems that best results are from applying combined test than a single one.

scholarly journals Prediction of Difficult Airway Among Patients Requiring Endotracheal Intubation in a Tertiary Care Hospital in Eastern Nepal

2017 ◽  
Vol 56 (207) ◽  
pp. 314-318 ◽  
Author(s):  
Sindhu Khatiwada ◽  
Balkrishna Bhattarai ◽  
Krishna Pokharel ◽  
Roshan Acharya
Keyword(s):  
Difficult Airway ◽  
Endotracheal Intubation ◽  
Difficult Intubation ◽  
Tertiary Care ◽  
Difficult Laryngoscopy ◽  
Screening Tests ◽  
Care Hospital ◽  
Laryngoscopic View ◽  
Predictive Values ◽  
Lehane Grade

Introduction: Unanticipated difficult intubation is an undesirable situation. Various bedside screening tests are routinely performed for predicting difficult airway. Although considered a surrogate indicator, difficult laryngoscopy is not the exact measure of intubation difficulty. We aimed to determine the best screening test for predicting difficult laryngoscopy and the association between difficult laryngoscopic view and difficult intubation. Methods: This prospective, observational study involved 314, ASA I/II adult patients requiring endotracheal intubation for various routine surgical procedures. Sternomental distance < 12 cm, thyromental distance < 6.5cm, inter-incisor distance < 3.5 cm, mandibular protrusion grade 3 and modified Mallampati class III/IV were the predictors of difficult laryngoscopy. Laryngoscopic view was defined as ‘difficult’ when the Cormack and Lehane grade was III/ IV. The sensitivity, specificity, positive and negative predictive values and accuracy of these predictors were compared to find out the best predictor. Requirement of >3 attempts for insertion of the tracheal tube was defined as ‘difficult intubation’. The association between difficult laryngoscopic view and difficult intubation was determined. Results: The sensitivity of the modified Mallampati class for predicting difficult laryngoscopy was highest (83%). Twelve (3.8%) patients had grade III laryngoscopic view and none had a grade of IV. Intubation was difficult in seven (2.2%) patients. Majority of patients (4 of 7) with difficult intubation had difficult laryngoscopic view (p<0.001). Conclusions: Modified Mallampati test was better for predicting difficult laryngoscopy compared to other bedside screeing tests. Difficult laryngoscopy could significantly predict difficult intubation in our patients.   Keywords: Airway evaluation; difficult intubation; difficult laryngoscopy; modified Mallampati class; Nepalese patients; sensitivity.

Difficult Intubation in Acromegalic Patients

2000 ◽  
Vol 93 (1) ◽  
pp. 110-114 ◽  
Author(s):  
Hubert Schmitt ◽  
Michael Buchfelder ◽  
Martin Radespiel-Tröger ◽  
Rudolf Fahlbusch
Keyword(s):  
Difficult Intubation ◽  
Preoperative Assessment ◽  
Difficult Laryngoscopy ◽  
Fisher Exact Test ◽  
Muscle Paralysis ◽  
Exact Test ◽  
Number Of Patients ◽  
Lehane Grade ◽  
Grade Ii ◽  
Grade Iii

Background Previous studies have suggested that the incidence of difficult intubation in acromegalic patients is higher than in normal patients. However, these studies were retrospective and did not include preoperative assessment of the airways. The aims of this study were to determine the incidence of difficult intubation and to assess the usefulness of preoperative tests in predicting difficult laryngoscopy. Methods One hundred twenty-eight consenting acromegalic patients requiring general anesthesia and tracheal intubation were studied. Preoperatively, Mallampati classification, thyromental distance, and head and neck movement were determined in each patient. After induction of anesthesia and muscle paralysis, laryngoscopic grade was assessed during direct laryngoscopy; Cormack and Lehane grade III or IV were classified as difficult. The association of individual airway assessment with laryngeal view was evaluated using the Fisher exact test. Predictors of difficult laryngoscopy were evaluated by calculating their sensitivity and specificity. Results Laryngoscopy was difficult (grade III) in 33 of 128 patients (26%). Application of external laryngeal pressure improved laryngeal visualization to grade II in 20 of these 33 patients. In the remaining 13 patients (10%), intubation was difficult (more than two attempts, blade change, use of gum-elastic bougie). Mallampati classes 3 and 4 were significantly related to laryngoscopy grade III (Fisher exact test, P = 0.001). Conclusions The incidence of difficult laryngoscopy and intubation in acromegalic patients is higher than in normal patients. Preoperative Mallampati scores of 3 and 4 were of value in predicting difficult laryngoscopy. Nevertheless, even this test will miss a significant number of patients with a difficult airway.

Discriminating Malignancy in Thyroid Nodules: The Nomogram Versus the Kwak and ACR TI-RADS

2020 ◽  
Vol 163 (6) ◽  
pp. 1156-1165
Author(s):  
Juan Xiao ◽  
Qiang Xiao ◽  
Wei Cong ◽  
Ting Li ◽  
Shouluan Ding ◽  
...  
Keyword(s):  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Diagnostic Study ◽  
Diagnostic Efficiency ◽  
Training Set ◽  
Multivariable Logistic Regression Model ◽  
Predictive Values ◽  
Validation Set ◽  
Sensitivity Specificity

Objective To develop an easy-to-use nomogram for discrimination of malignant thyroid nodules and to compare diagnostic efficiency with the Kwak and American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Study Design Retrospective diagnostic study. Setting The Second Hospital of Shandong University. Subjects and Methods From March 2017 to April 2019, 792 patients with 1940 thyroid nodules were included into the training set; from May 2019 to December 2019, 174 patients with 389 nodules were included into the validation set. Multivariable logistic regression model was used to develop a nomogram for discriminating malignant nodules. To compare the diagnostic performance of the nomogram with the Kwak and ACR TI-RADS, the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values were calculated. Results The nomogram consisted of 7 factors: composition, orientation, echogenicity, border, margin, extrathyroidal extension, and calcification. In the training set, for all nodules, the area under the curve (AUC) for the nomogram was 0.844, which was higher than the Kwak TI-RADS (0.826, P = .008) and the ACR TI-RADS (0.810, P < .001). For the 822 nodules >1 cm, the AUC of the nomogram was 0.891, which was higher than the Kwak TI-RADS (0.852, P < .001) and the ACR TI-RADS (0.853, P < .001). In the validation set, the AUC of the nomogram was also higher than the Kwak and ACR TI-RADS ( P < .05), each in the whole series and separately for nodules >1 or ≤1 cm. Conclusions When compared with the Kwak and ACR TI-RADS, the nomogram had a better performance in discriminating malignant thyroid nodules.

scholarly journals The Impact of Narrow-band Imaging on the Pre- and Intra- operative Assessments of Neoplastic and Preneoplastic Laryngeal Lesions. A Systematic Review

2020 ◽  
Author(s):  
Carmelo Saraniti ◽  
Enzo Chianetta ◽  
Giuseppe Greco ◽  
Norhafiza Mat Lazim ◽  
Barbara Verro
Keyword(s):  
White Light ◽  
Diagnostic Tool ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Resection Margins ◽  
Predictive Values ◽  
White Light Endoscopy ◽  
Laryngeal Lesions ◽  
Sensitivity Specificity ◽  
The Impact

Introduction Narrow-band imaging is an endoscopic diagnostic tool that, focusing on superficial vascular changes, is useful to detect suspicious laryngeal lesions, enabling their complete excision with safe and tailored resection margins. Objectives To analyze the applications and benefits of narrow-band imaging in detecting premalignant and malignant laryngeal lesions through a comparison with white-light endoscopy. Data Synthesis A literature search was performed in the PubMed, Scopus and Web of Science databases using strict keywords. Then, two authors independently analyzed the articles, read the titles and abstracts, and read completely only the relevant studies according to certain eligibility criteria. In total, 14 articles have been included in the present review; the sensitivity, specificity, positive and negative predictive values, and accuracy of pre- and/or intraoperative narrow-band imaging were analyzed. The analysis showed that narrow-band imaging is better than white-light endoscopy in terms of sensitivity, specificity, positive and negative predictive values, and accuracy regarding the ability to identify cancer and/or precancerous laryngeal lesions. Moreover, the intraoperative performance of narrow-band imaging resulted more effective than the in-office performance. Conclusion Narrow-band imaging is an effective diagnostic tool to detect premalignant and malignant laryngeal lesions and to define proper resection margins. Moreover, narrow-band imaging is useful in cases of leukoplakia that may cover a possible malignant lesion and that cannot be easily assessed with white-light endoscopy. Finally, a shared, simple and practical classification of laryngeal lesions, such as that of the European Laryngological Society, is required to identify a shared lesion management strategy. Key Points

scholarly journals Predicting youth diabetes risk using NHANES data and machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nita Vangeepuram ◽  
Bian Liu ◽  
Po-hsiang Chiu ◽  
Linhua Wang ◽  
Gaurav Pandey
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Clinical Guideline ◽  
Diabetes Risk ◽  
Screening Tools ◽  
Clinical Screening ◽  
Predictive Values ◽  
Screening Guideline ◽  
Demographic Subgroups ◽  
Sensitivity Specificity

AbstractPrediabetes and diabetes mellitus (preDM/DM) have become alarmingly prevalent among youth in recent years. However, simple questionnaire-based screening tools to reliably assess diabetes risk are only available for adults, not youth. As a first step in developing such a tool, we used a large-scale dataset from the National Health and Nutritional Examination Survey (NHANES) to examine the performance of a published pediatric clinical screening guideline in identifying youth with preDM/DM based on American Diabetes Association diagnostic biomarkers. We assessed the agreement between the clinical guideline and biomarker criteria using established evaluation measures (sensitivity, specificity, positive/negative predictive value, F-measure for the positive/negative preDM/DM classes, and Kappa). We also compared the performance of the guideline to those of machine learning (ML) based preDM/DM classifiers derived from the NHANES dataset. Approximately 29% of the 2858 youth in our study population had preDM/DM based on biomarker criteria. The clinical guideline had a sensitivity of 43.1% and specificity of 67.6%, positive/negative predictive values of 35.2%/74.5%, positive/negative F-measures of 38.8%/70.9%, and Kappa of 0.1 (95%CI: 0.06–0.14). The performance of the guideline varied across demographic subgroups. Some ML-based classifiers performed comparably to or better than the screening guideline, especially in identifying preDM/DM youth (p = 5.23 × 10−5).We demonstrated that a recommended pediatric clinical screening guideline did not perform well in identifying preDM/DM status among youth. Additional work is needed to develop a simple yet accurate screener for youth diabetes risk, potentially by using advanced ML methods and a wider range of clinical and behavioral health data.

scholarly journals COVID-19 Seroprevalence among Healthcare Workers of a Large COVID-19 Hospital in Rome Reveals Strengths and Limits of Two Different Serological Tests

2021 ◽  
Vol 18 (5) ◽  
pp. 2650
Author(s):  
Giuseppe Vetrugno ◽  
Daniele Ignazio La Milia ◽  
Floriana D’Ambrosio ◽  
Marcello Di Pumpo ◽  
Roberta Pastorino ◽  
...  
Keyword(s):  
Blood Test ◽  
Healthcare Workers ◽  
Point Of Care ◽  
Venous Blood ◽  
Administrative Staff ◽  
Serological Tests ◽  
Predictive Values ◽  
Work From Home ◽  
Significant Difference ◽  
Sensitivity Specificity

Healthcare workers are at the forefront against COVID-19, worldwide. Since Fondazione Policlinico Universitario A. Gemelli (FPG) IRCCS was enlisted as a COVID-19 hospital, the healthcare workers deployed to COVID-19 wards were separated from those with limited/no exposure, whereas the administrative staff were designated to work from home. Between 4 June and 3 July 2020, an investigation was conducted to evaluate the seroprevalence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) immunoglobulin (IgG) antibodies among the employees of the FPG using point-of-care (POC) and venous blood tests. Sensitivity, specificity, and predictive values were determined with reverse-transcription polymerase chain reaction on nasal/oropharyngeal swabs as the diagnostic gold standard. The participants enrolled amounted to 4777. Seroprevalence was 3.66% using the POC test and 1.19% using the venous blood test, with a significant difference (p < 0.05). The POC test sensitivity and specificity were, respectively, 63.64% (95% confidence interval (CI): 62.20% to 65.04%) and 96.64% (95% CI: 96.05% to 97.13%), while those of the venous blood test were, respectively, 78.79% (95% CI: 77.58% to 79.94%) and 99.36% (95% CI: 99.07% to 99.55%). Among the low-risk populations, the POC test’s predictive values were 58.33% (positive) and 98.23% (negative), whereas those of the venous blood test were 92.86% (positive) and 98.53% (negative). According to our study, these serological tests cannot be a valid alternative to diagnose COVID-19 infection in progress.

scholarly journals Accuracy of the fluorescence-aided identification technique (FIT) for detecting tooth-colored restorations utilizing different fluorescence-inducing devices: an ex vivo comparative study

2021 ◽  
Author(s):  
W. Leontiev ◽  
E. Magni ◽  
C. Dettwiler ◽  
C. Meller ◽  
R. Weiger ◽  
...  
Keyword(s):  
Multivariate Analysis ◽  
Ex Vivo ◽  
Predictive Values ◽  
Composite Restorations ◽  
Significant Difference ◽  
Identification Technique ◽  
Illumination Method ◽  
Sensitivity Specificity ◽  
Entire Procedure ◽  
Higher Sensitivity

Abstract Objectives The aim of the present study was to compare the accuracy of the conventional illumination method (CONV) and the fluorescence-aided identification technique (FIT) for distinguishing between composite restorations and intact teeth using different fluorescence-inducing devices commonly used for FIT. Materials and methods Six groups of six dentists equipped with one of six different FIT systems each independently attempted to identify composite restorations and intact teeth on a full-mouth model with 22 composite restorations using CONV and, 1 h later, FIT. The entire procedure was repeated 1 week later. Sensitivity, specificity, and positive (PPV) and negative (NPV) predictive values, including 95% confidence intervals (CI), were calculated for CONV and FIT overall and for each device. The influence of examiner age, method, and device on each parameter was assessed by multivariate analysis of variance. Results The sensitivity (84%, CI 81–86%), specificity (94%, CI 93–96%), PPV (92%, CI 90–94%), and NPV (90%, CI 88–91%) of FIT was significantly higher than that of CONV (47%, CI 44–50%; 82%, CI 79–84%; 66%, CI 62–69%, and 69%, CI 68–71%, respectively; p<0.001). The differences between CONV and FIT were significant for all parameters and FIT systems except VistaCam, which achieved no significant difference in specificity. Examiners younger than 40 years attained significantly higher sensitivity and negative predictive values than older examiners. Conclusions FIT is more reliable for detecting composite restorations than the conventional illumination method. Clinical relevance FIT can be considered an additional or alternative tool for improving the detection of composite restorations.

scholarly journals Comparison of saliva with healthcare workers- and patient-collected swabs in the diagnosis of COVID-19 in a large cohort

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Mitnala Sasikala ◽  
Yelamanchili Sadhana ◽  
Ketavarapu Vijayasarathy ◽  
Anand Gupta ◽  
Sarala Kumari Daram ◽  
...  
Keyword(s):  
Healthcare Workers ◽  
Early Stage ◽  
Cost Effective ◽  
Hospitalized Patients ◽  
Detection Sensitivity ◽  
Nasopharyngeal Swab ◽  
Predictive Values ◽  
Qrt Pcr ◽  
Asymptomatic Patients ◽  
Sensitivity Specificity

Abstract Background A considerable amount of evidence demonstrates the potential of saliva in the diagnosis of COVID-19. Our aim was to determine the sensitivity of saliva versus swabs collected by healthcare workers (HCWs) and patients themselves to assess whether saliva detection can be offered as a cost-effective, risk-free method of SARS-CoV-2 detection. Methods This study was conducted in a hospital involving outpatients and hospitalized patients. A total of 3018 outpatients were tested. Of these, 200 qRT-PCR-confirmed SARS-CoV-2-positive patients were recruited for further study. In addition, 101 SARS-CoV-2-positive hospitalized patients with symptoms were also enrolled in the study. From outpatients, HCWs collected nasopharyngeal swabs (NPS), saliva were obtained. From inpatients, HCWs collected swabs, patient-collected swabs, and saliva were obtained. qRT-PCR was performed to detect SARS-CoV-2 by TAQPATH assay to determine the sensitivity of saliva detection. Sensitivity, specificity and positive/negative predictive values (PPV, NPV) of detecting SARS-CoV-2 were calculated using MedCalc. Results Of 3018 outpatients (asymptomatic: 2683, symptomatic: 335) tested by qRT-PCR, 200 were positive (males: 140, females: 60; aged 37.9 ± 12.8 years; (81 asymptomatic, 119 symptomatic). Of these, saliva was positive in 128 (64%); 39 of 81 asymptomatic (47%),89 of 119 symptomatic patients (74.8%). Sensitivity of detection was 60.9% (55.4–66.3%, CI 95%), with a negative predictive value of 36%(32.9–39.2%, CI 95%).Among 101 hospitalized patients (males:65, females: 36; aged 53.48 ± 15.6 years), with HCW collected NPS as comparator, sensitivity of saliva was 56.1% (47.5–64.5, CI 95%), specificity 63.5%(50.4–75.3, CI95%) with PPV of 77.2% and NPV of 39.6% and that of self-swab was 52.3%(44–60.5%, CI95%), specificity 56.6% (42.3–70.2%, CI95%) with PPV 77.2% and NPV29.7%. Comparison of positivity with the onset of symptoms revealed highest detection in saliva on day 3 after onset of symptoms. Additionally, only saliva was positive in 13 (12.8%) hospitalized patients. Conclusion Saliva which is easier to collect than nasopharyngeal swab is a viable alternate to detect SARS-COV-2 in symptomatic patients in the early stage of onset of symptoms. Although saliva is currently not recommended for screening asymptomatic patients, optimization of collection and uniform timing of sampling might improve the sensitivity enabling its use as a screening tool at community level.

scholarly journals Development of Machine Learning Models to Predict Probabilities and Types of Stroke at Prehospital Stage: the Japan Urgent Stroke Triage Score Using Machine Learning (JUST-ML)

2021 ◽  
Author(s):  
Kazutaka Uchida ◽  
Junichi Kouno ◽  
Shinichi Yoshimura ◽  
Norito Kinjo ◽  
Fumihiro Sakakibara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forests ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Vessel Occlusion ◽  
Predictive Values ◽  
Training Cohort ◽  
Sensitivity Specificity

AbstractIn conjunction with recent advancements in machine learning (ML), such technologies have been applied in various fields owing to their high predictive performance. We tried to develop prehospital stroke scale with ML. We conducted multi-center retrospective and prospective cohort study. The training cohort had eight centers in Japan from June 2015 to March 2018, and the test cohort had 13 centers from April 2019 to March 2020. We use the three different ML algorithms (logistic regression, random forests, XGBoost) to develop models. Main outcomes were large vessel occlusion (LVO), intracranial hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral infarction (CI) other than LVO. The predictive abilities were validated in the test cohort with accuracy, positive predictive value, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F score. The training cohort included 3178 patients with 337 LVO, 487 ICH, 131 SAH, and 676 CI cases, and the test cohort included 3127 patients with 183 LVO, 372 ICH, 90 SAH, and 577 CI cases. The overall accuracies were 0.65, and the positive predictive values, sensitivities, specificities, AUCs, and F scores were stable in the test cohort. The classification abilities were also fair for all ML models. The AUCs for LVO of logistic regression, random forests, and XGBoost were 0.89, 0.89, and 0.88, respectively, in the test cohort, and these values were higher than the previously reported prediction models for LVO. The ML models developed to predict the probability and types of stroke at the prehospital stage had superior predictive abilities.

Sign in / Sign up

Export Citation Format

Share Document