Neural network prediction of difficult tracheal intubation risk by using the patient’s face image

Background. The prognosis of the difficult tracheal intubation remains an essential problem. The effectiveness of using predictors does not allow to foreseen such situation accurately. The purpose of the study was to develop a predictive system and evaluate its effectiveness in difficult tracheal intubation based on facial image analysis combined with the most significant predictors of difficult intubation. Materials and methods. A database based on the registration of difficult intubation predictors was developed. It was based on the patients face images with marked reference points. It allowed to estimate the information signs associated with the difficult tracheal intubation. The degree of intubation severity was determined directly during the intubation process according to the proposed original scale of severity. Results. The classifier was synthesized by using the self-organization neural network method. The trained neural network was the basis of the classifier model implemented as a computer application. The sensitivity of the difficult tracheal intubation prognosis was 90.90%, specificity was 97.02%, the prognostic value of the positive result was 58.82%, the negative one was 99.56%. Conclusions. The proposed decision support system allows patients to be stratified into groups according to the degree of difficult tracheal intubation risk. In addition, the self-learning process of the system continues as the new data become available. This allows to improve its efficiency continuously.

Download Full-text

Comparison of Incidence of Difficult Intubation between Obese and Nonobese Patients, and Comparison of Three Predictors of Difficult Intubation in Obese Patients

Research & Innovation in Anesthesia ◽

10.5005/jp-journals-10049-0011 ◽

2016 ◽

Vol 1 (2) ◽

pp. 41-44

Author(s):

Johann Mathew

Keyword(s):

Tracheal Intubation ◽

Difficult Intubation ◽

Mouth Opening ◽

Difficult Tracheal Intubation ◽

Neck Circumference ◽

Obese Patients ◽

Chi Square ◽

Neck Extension ◽

Difficulty Scale ◽

Nonobese Patients

ABSTRACT Background Anticipating a difficult airway is of prime importance to an anesthesiologist. Data available are inconclusive to say that tracheal intubation is more difficult in the obese. The deficiency occurring with individual factors can be avoided by adopting multiple airway assessment factors. In this study, we aim to compare the incidence of difficult intubation between obese and nonobese patients and compare three predictors of difficult intubation. Study design Prospective observational study. Materials and methods About 250 patients were assigned to two groups, obese and nonobese based on their body mass index. Preoperatively, neck circumference (NC), mouth opening, thyromental distance (TMD), neck extension, NC/TM ratio, Mallampati classification (MPC), and Wilson score (WS) were calculated. Difficulty of intubation was assessed using the intubation difficulty scale (IDS). All tracheal intubations were performed by anesthetists with more than 2 years of experience. Statistical analysis used Data analysis was done with the help of Statistical Package for the Social Sciences (SPSS) version 15, MedCalc version 11, and Epi data software. Qualitative data are presented with the help of frequency and percentage table, and association among various study parameters is done with chi-square test. Results The incidence of difficult intubation determined by the IDS (≥5) was more frequent in the obese group (88.6% in obese vs 11.4% in nonobese). Of the three variables, WS was found to be statistically significant (p < 0.005). Neck circumference to thyromental ratio is a new predictor for difficult tracheal intubation (DTI). But an NC/TM ratio of ≥5 gives high false positive for our population. How to cite this article Mathew J, Gvalani SK. Comparison of Incidence of Difficult Intubation between Obese and Nonobese Patients, and Comparison of Three Predictors of Difficult Intubation in Obese Patients. Res Inno in Anesth 2016;1(2):41-44.

Download Full-text

Prediction of the fatigue strength of metals at low temperatures based on artificial intelligence

10.36652/0042-4633-2021-11-11-14 ◽

2021 ◽

pp. 11-14

Author(s):

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Fatigue Strength ◽

Low Temperatures ◽

Intelligent System ◽

Fatigue Cracks ◽

Test Conditions ◽

Neural Network Prediction ◽

Network Prediction ◽

Trained Neural Network

An intelligent system for predicting the fatigue strength of metals in a wide temperature range is developed using a specially trained neural network. The system makes it possible to predict the number of load cycles of a part to failure, as well as the start of formation and growth rate of fatigue cracks for different test conditions, including at low temperatures. Keywords: neural network, prediction of loading cycles, low temperatures, fatigue strength. [email protected]

Download Full-text

Awake Fiberoptic or Awake Video Laryngoscopic Tracheal Intubation in Patients with Anticipated Difficult Airway Management

Anesthesiology ◽

10.1097/aln.0b013e318254d085 ◽

2012 ◽

Vol 116 (6) ◽

pp. 1210-1216 ◽

Cited By ~ 123

Author(s):

Charlotte V. Rosenstock ◽

Bente Thøgersen ◽

Arash Afshari ◽

Anne-Lise Christensen ◽

Claus Eriksen ◽

...

Keyword(s):

Tracheal Intubation ◽

Difficult Airway ◽

Scale Score ◽

Visual Analog Scale ◽

Difficult Intubation ◽

Visual Analog Scale Score ◽

Difficult Tracheal Intubation ◽

Fiberoptic Intubation ◽

Analog Scale ◽

Intubation Success

Background Awake flexible fiberoptic intubation (FFI) is the gold standard for management of anticipated difficult tracheal intubation. The purpose of this study was to compare awake FFI to awake McGrath® video laryngoscope, (MVL), (Aircraft Medical, Edinburgh, Scotland, United Kingdom) intubation in patients with an anticipated difficult intubation. The authors examined the hypothesis that MVL intubation would be faster than FFI. Methods Ninety-three adult patients with anticipated difficult intubation were randomly allocated to awake FFI or awake MVL, patients were given glycopyrrolate, nasal oxygen, topical lidocaine orally, and a transtracheal injection of 100 mg lidocaine. Remifentanil infusion was administered intravenously to a Ramsay sedation score of 2-4. Time to tracheal intubation was recorded by independent assessors. The authors also recorded intubation success on the first attempt, investigators' evaluation of ease of the technique, and patients reported intubation-discomfort evaluated on a visual analog scale. Results Eighty-four patients were eligible for analysis. Time to tracheal intubation was median [interquartile range, IQR] 80 s [IQR 58-117] with FFI and 62 s [IQR 55-109] with MVL (P = 0.17). Intubation success on the first attempt was 79% versus 71% for FFI and MVL, respectively. The median visual analog scale score for ease of intubation was 2 (IQR 1-4) versus 1 (IQR 1-6) for FFI and MVL, respectively. The median visual analog scale score for patients' assessment of discomfort for both techniques was 2, FFI (IQR 0-3), MVL (IQR 0-4). Conclusions The authors found no difference in time to tracheal intubation between awake FFI and awake MVL intubation performed by experienced anesthesiologists in patients with anticipated difficult airway.

Download Full-text

Axle Temperature Monitoring and Neural Network Prediction Analysis for High-Speed Train under Operation

Symmetry ◽

10.3390/sym12101662 ◽

2020 ◽

Vol 12 (10) ◽

pp. 1662

Author(s):

Wei Hao ◽

Feng Liu

Keyword(s):

Neural Network ◽

Network Model ◽

Neural Network Model ◽

High Speed ◽

Prediction Method ◽

High Speed Train ◽

The Neural Network ◽

Neural Network Prediction ◽

Network Prediction ◽

Trained Neural Network

Predicting the axle temperature states of the high-speed train under operation in advance and evaluating working states of axle bearings is important for improving the safety of train operation and reducing accident risks. The method of monitoring the axle temperature of a train under operation, combined with the neural network prediction method, was applied. A total of 36 sensors were arranged at key positions such as the axle bearings of the train gearbox and the driving end of the traction motor. The positions of the sensors were symmetrical. Axle temperature measurements over 11 days with more than 38,000 km were obtained. The law of the change of the axle temperature in each section was obtained in different environments. The resultant data from the previous 10 days were used to train the neural network model, and a total of 800 samples were randomly selected from eight typical locations for the prediction of axle temperature over the following 3 min. In addition, the results predicted by the neural network method and the GM (1,1) method were compared. The results show that the predicted temperature of the trained neural network model is in good agreement with the experimental temperature, with higher precision than that of the GM (1,1) method, indicating that the proposed method is sufficiently accurate and can be a reliable tool for predicting axle temperature.

Download Full-text

Predictors of Difficult Tracheal Intubation on Adult Elective Patients in a Teaching Hospital

The Open Anesthesiology Journal ◽

10.2174/1874321801610010034 ◽

2016 ◽

Vol 10 (1) ◽

pp. 34-39

Author(s):

Dawit Tafesse ◽

Getu Ataro

Keyword(s):

Tracheal Intubation ◽

Difficult Intubation ◽

Prospective Observational Study ◽

Preoperative Evaluation ◽

Preoperative Assessment ◽

Difficult Tracheal Intubation ◽

Adult Patients ◽

Chi Square ◽

Chi Square Test ◽

Sensitivity Specificity

Background: During routine preoperative assessment of patients one of the commonest practices is predicting difficulty of tracheal intubation from various factors detected. Whether the factors reliably predict the difficulty is subject of argument. This study was conducted to assess the predictors of difficult tracheal intubation in adult patients. Methods: In this prospective observational study, we studied 120 consecutive elective adult patients admitted for general, gynecologic and orthopedic surgeries. Socio-demographic parameters and test variables such as BMI, TMD, SMD, IIG and Mallampati class were collected during preoperative evaluation. CL grade and difficulty of intubation were observed while the anesthetist in duty performs the laryngoscopy. While the former obtained from the preoperative anesthesia note, the latter were filled to questionnaire based on what the anesthetist reports during or after laryngoscopy. The prevalence of difficult intubation and the sensitivity, specificity, PPV and NPV of the tests were analyzed. SPSS-20 and different formulas were used during analysis. Chi square test was used and P<0.05 was considered as statistically significant. Result: The overall prevalence of difficult tracheal intubation was 2.5%. The sensitivity, specificity, PPV & NPV of the tests were 0%, 98.3%, 0% & 97.46% for BMI; 0%, 97.5%, 0% & 100% for SMD; 100%, 96.64%, 20% & 100% for TMD; 0%, 99.17%, 0%, & 100% for IIG; and 100%, 99.14%, 75% & 100% for Mallampati test. Conclusion: The incidence is not quite small that anesthetists should use necessary tests to predict the difficult intubation. Probably combining the tests being the best option, Mallampati test alone can predict the difficult intubation in adult patients.

Download Full-text

Management of Difficult Tracheal Intubation

Anesthesiology ◽

10.1097/aln.0000000000002815 ◽

2019 ◽

Vol 131 (4) ◽

pp. 818-829 ◽

Cited By ~ 30

Author(s):

Aaron M. Joffe ◽

Michael F. Aziz ◽

Karen L. Posner ◽

Laura V. Duggan ◽

Shawn L. Mincer ◽

...

Keyword(s):

Tracheal Intubation ◽

Airway Management ◽

Difficult Intubation ◽

Multiple Testing ◽

Difficult Tracheal Intubation ◽

Sufficient Information ◽

Physical Status ◽

Emergency Procedures ◽

Malpractice Claims ◽

Preoperative Predictors

Abstract Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New Background Difficult or failed intubation is a major contributor to morbidity for patients and liability for anesthesiologists. Updated difficult airway management guidelines and incorporation of new airway devices into practice may have affected patient outcomes. The authors therefore compared recent malpractice claims related to difficult tracheal intubation to older claims using the Anesthesia Closed Claims Project database. Methods Claims with difficult tracheal intubation as the primary damaging event occurring in the years 2000 to 2012 (n = 102) were compared to difficult tracheal intubation claims from 1993 to 1999 (n = 93). Difficult intubation claims from 2000 to 2012 were evaluated for preoperative predictors and appropriateness of airway management. Results Patients in 2000 to 2012 difficult intubation claims were sicker (78% American Society of Anesthesiologists [ASA] Physical Status III to V; n = 78 of 102) and had more emergency procedures (37%; n = 37 of 102) compared to patients in 1993 to 1999 claims (47% ASA Physical Status III to V; n = 36 of 93; P < 0.001 and 22% emergency; n = 19 of 93; P = 0.025). More difficult tracheal intubation events occurred in nonperioperative locations in 2000 to 2012 than 1993 to 1999 (23%; n = 23 of 102 vs. 10%; n = 10 of 93; P = 0.035). Outcomes differed between time periods (P < 0.001), with a higher proportion of death in 2000 to 2012 claims (73%; n = 74 of 102 vs. 42%; n = 39 of 93 in 1993 to 1999 claims; P < 0.001 adjusted for multiple testing). In 2000 to 2012 claims, preoperative predictors of difficult tracheal intubation were present in 76% (78 of 102). In the 97 claims with sufficient information for assessment, inappropriate airway management occurred in 73% (71 of 97; κ = 0.44 to 0.66). A “can’t intubate, can’t oxygenate” emergency occurred in 80 claims with delayed surgical airway in more than one third (39%; n = 31 of 80). Conclusions Outcomes remained poor in recent malpractice claims related to difficult tracheal intubation. Inadequate airway planning and judgment errors were contributors to patient harm. Our results emphasize the need to improve both practitioner skills and systems response when difficult or failed tracheal intubation is encountered.

Download Full-text