Prediction of severity of aviation landing accidents using support vector machine models

The purpose of this study was to apply support vector machine (SVM) models to predict the severity of aircraft damage and the severity of personal injury during an aircraft approach and landing accident and to evaluate and rank the importance of 14 accident factors across 39 sub-categorical factors. Three new factors were introduced using the theory of inattentional blindness: The presence of visual area surface penetrations for a runway, the Federal Aviation Administration's (FAA) visual area surface penetration policy timeframe, and the type of runway approach lighting. The study comprised 1,297 aircraft approach and landing accidents at airports within the United States with at least one instrument approach procedure. Support vector machine models were developed in using the linear, polynomial, radial basis function (RBF), and sigmoid kernels for the severity of aircraft damage and additional SVM models were developed for the severity of personal injury. The SVM models using the RBF kernel produced the best machine learning models with a 96% accuracy for predicting the severity of aircraft damage (0.94 precision, 0.95 recall, and 0.95 F1-score) and a 98% accuracy for predicting the severity of personal injury (0.99 precision, 0.98 recall, and 0.99 F1-score). The top predictors across both models were the pilot's total flight hours, time of the accident, pilot's age, crosswind component, landing runway number, single-engine land certificate, and any obstacle penetration. This study demonstrates the benefit of SVM modeling using the RBF kernel for accident prediction and for datasets with categorical factors.

"The eye sees only what the mind is prepared to comprehend": Unrecognized incidental findings on intraoperative computed tomography during spine instrumentation surgery

BACKGROUND

Intraoperative computed tomography (CT) is becoming more widely utilized in spine fusion surgeries. The use of CT-based image guidance has been shown to increase the accuracy in instrumentation placement and to reduce the rate of reoperation. However, incidental findings that are obvious in retrospect are still missed in spinal fusion surgeries due to the concept of inattentional blindness and surgeons' preoccupation with the main objective of intraoperative CT (i.e. instrumentation accuracy).

CASE DESCRIPTION

The first case describes a 60-year-old male who underwent posterior spinal laminectomy and interbody fusions from L2-L5. Intraoperative CT confirmed appropriate placement of hardware. However, when he was transferred out to the care unit and extubated, he developed a severe headache for which the source was confirmed to be a pneumocephalus from durotomy and cerebrospinal fluid leakage on repeat CT. A retrospective review of his intraoperative CT demonstrated the intrathecal air at L5-S1 interlaminar space that was missed on evaluation during surgery. The second case describes a 68-year-old female who was treated with a successful T4 to pelvis instrumentation and fusion with vertebral column resection at T10 confirmed with imaging. Postoperatively, she developed rapidly progressive oxygen desaturation and was found to have a pneumothorax which had been present on the intraoperative imaging.

CONCLUSION

This case report of two patients with missed intraoperative findings demonstrates the importance of looking beyond instrumentation placement and evaluating the entire intraoperative CT imaging to find abnormalities that could complicate the patients' postoperative recovery and overall hospital stay.

Distraction or cognitive overload? Using modulations of the autonomic nervous system to discriminate the possible negative effects of advanced assistance system

The interaction with Advanced Driver Assistance Systems has several positive implications for road safety, but also some potential downsides such as mental workload and automation complacency. Malleable attentional resources allocation theory describes two possible processes that can generate workload in interaction with advanced assisting devices. The purpose of the present study is to determine if specific analysis of the different modalities of autonomic control of nervous system can be used to discriminate different potential workload processes generated during assisted-driving tasks and automation complacency situations. Thirty-five drivers were tested in a virtual scenario while using head-up advanced warning assistance system. Repeated MANOVA were used to examine changes in autonomic activity across a combination of different user interactions generated by the advanced assistance system: (1) expected take-over request without anticipatory warning; (2) expected take-over request with two-second anticipatory warning; (3) unexpected take-over request with misleading warning; (4) unexpected take-over request without warning. Results shows that analysis of autonomic modulations can discriminate two different resources allocation processes, related to different behavioral performances. The user's interaction that required divided attention under expected situations produced performance enhancement and reciprocally-coupled parasympathetic inhibition with sympathetic activity. At the same time, supervising interactions that generated automation complacency were described specifically by uncoupled sympathetic activation. Safety implications for automated assistance systems developments are considered.

How does a collision warning system shape driver's brake response time? The influence of expectancy and automation complacency on real-life emergency braking

Brake Reaction Time (BRT) is an important parameter for road safety. Previous research has shown that drivers' expectations can impact RT when facing hazardous situations, but driving with advanced driver assistance systems, can change the way BRT are considered. The interaction with a collision warning system can help faster more efficient responses, but at the same time can require a monitoring task and evaluation process that may lead to automation complacency. The aims of the present study are to test in a real-life setting whether automation compliancy can be generated by a collision warning system and what component of expectancy can impact the different tasks involved in an assisted BRT process. More specifically four component of expectancy were investigated: presence/absence of anticipatory information, previous direct experience, reliability of the device, and predictability of the hazard determined by repeated use of the warning system. Results supply indication on perception time and mental elaboration of the collision warning system alerts. In particular reliable warning quickened the decision making process, misleading warnings generated automation complacency slowing visual search for hazard detection, lack of directed experienced slowed the overall response while unexpected failure of the device lead to inattentional blindness and potential pseudo-accidents with surprise obstacle intrusion.