Rigorous assessment of medical knowledge and technical skill inspires learning, reinforces confidence, and reassures the public. Identifying curricular effectiveness using objective measures of learning is therefore crucial for competency-oriented program development in a learner-centric educational environment. The aim of this study was to determine whether various measures of learning, including class-average normalized gain, can be used to assess the effectiveness of a one-day introductory bronchoscopy course curriculum. We conducted a quasi-experimental one-group pre-test/post-test study at the University of California, Irvine. The group comprised 24 first-year pulmonary and critical care trainees from eight training institutions in southern California. Class-average normalized gain, single-student normalized gain, absolute gain, and relative gain were used as objective measures of cognitive knowledge and bronchoscopy technical skill learning. A class-average normalized gain of 30% was used to determine curricular effectiveness. Perceived educational value using Likert-scale surveys and post-course questionnaires was determined during and 3 months after course participation. Mean test scores of cognitive knowledge improved significantly from 48 to 66% (p = 0.043). Absolute gain for the class was 18%, relative gain was 37%, class average normalized gain 〈g〉 was 34%, and the average of the single-student normalized gains g(ave) was 29%. Mean test scores of technical skill improved significantly from 43 to 77% (p = 0.017). Absolute gain was 34%, relative gain was 78%, class average normalized gain 〈g〉 was 60%, and the average of the single-student normalized gains g(ave) was 59%. Statistically significant improvements in absolute gain were noted in all five elements of technical skill (p < 0.05). Likert-scale surveys, questionnaires, and surveys demonstrated strong perceived educational value. The effectiveness of a one-day introductory bronchoscopy curriculum was demonstrated using a pre-test/post-test model with calculation of normalized gain and related metrics.

Artificial intelligence (AI) is transforming healthcare delivery. The digital revolution in medicine and healthcare information is prompting a staggering growth of data intertwined with elements from many digital sources such as genomics, medical imaging and electronic health records. Such massive growth has sparked the development of an increasing number of AI-based applications that can be deployed in clinical practice. Pulmonary specialists who are familiar with the principles of AI and its applications will be empowered and prepared to seize future practice and research opportunities. The goal of this review is to provide pulmonary specialists and other readers with information pertinent to the use of AI in pulmonary medicine. First, we describe the concept of AI and some of the requisites of machine learning and deep learning. Next, we review some of the literature relevant to the use of computer vision in medical imaging, predictive modelling with machine learning, and the use of AI for battling the novel severe acute respiratory syndrome-coronavirus-2 pandemic. We close our review with a discussion of limitations and challenges pertaining to the further incorporation of AI into clinical pulmonary practice.

Objective/hypothesis

Laser-induced damage of tracheal wall microstructures might contribute to recurrence after bronchoscopic treatment of tracheal strictures. The purpose of this study was to demonstrate how multimodal imaging using white light bronchoscopy (WLB), endobronchial ultrasound (EBUS), and optical coherence tomography (OCT) might identify in vivo airway wall changes before and resulting from Nd:YAG laser ablation and dilation of tracheal stenosis.

Study design

Case study.

Methods

Commercially available WLB, high frequency EBUS using a 20-MHz radial probe and time-domain, frontal imaging OCT systems were used to characterize the extent, morphology, and airway wall microstructures at the area of hypertrophic fibrotic tissue formation before, during and after treatment of postintubation tracheal stenosis.

Results

WLB revealed the location of a complex, extensive, severe stricture. EBUS showed a homogeneous layer overlying a hyperechogenic layer corresponding to disrupted cartilage. OCT showed a homogeneous light backscattering layer and absence of layered microstructures, confirming absence in close proximity of normal airway wall. After laser ablation, OCT of charred tissue showed high backscattering and shadowing artifacts. OCT of noncharred tissue showed a thinner, homogeneous, light backscattering layer. EBUS showed thinner but persistent hypertrophic tissue suggesting incomplete treatment. WLB revealed improved airway patency postprocedure and recurrence 3 weeks later.

Conclusions

EBUS identified cartilage disruption and residual hypertrophic tissue, the evidence of which might contribute to recurrence. OCT revealed homogeneous light backscaterring representing persistent noncharred hypertrophic tissues but it did not visualize cartilage disruption. Future studies are warranted to confirm whether these technologies can help guide bronchoscopic treatments.

A fast-scan-rate swept laser for optical coherence tomography (OCT) is suitable to record and analyze a 3-D image volume. However, the whole OCT system speed is limited by data streaming, processing, and storage. In this case, postprocessing is a common technique. Endoscopic clinical applications prefer onsite diagnosis, which requires a real-time technique. Parallel digital signal processors were applied to stream and process data directly from a data digitizer. A real-time system with 20-kHz axial line speed, which was limited only by our swept laser scan rate, was implemented. To couple with the system speed, an endoscope based on an improved 3-D microelectromechanical motor (diameter 1.5 mm, length 9.4 mm) was developed. In vivo 3-D imaging of the human airway was demonstrated.

Objectives/hypothesis

Recurrent respiratory papillomatosis (RRP) of the central airways requires removal to potentially reduce recurrence and risk for malignant transformation. Analogous to the principles of treatment for early lung cancer, a precise determination of the extent of cartilage invasion could help guide therapeutic decisions and monitor response to treatment. The purpose of this study was to determine whether a bronchoscopy platform comprised of white light bronchoscopy (WLB), endobronchial ultrasound (EBUS), and optical coherence tomography (OCT) could identify layered microstructure of RRP and underlying cartilage.

Study design

Case study.

Methods

A bronchoscopy platform consisting of commercially available WLB, EBUS using a 7.5 MHz convex probe (BF-UC 160F; Olympus Optical Co. Ltd, Tokyo, Japan), and a time-domain OCT with front imaging and inside actuation (Niris Imaging System; Imalux Corp., Cleveland, OH) was used in a patient with tracheal stenosis from RRP. Findings are compared with results of histology and the characteristics of imaging modalities are discussed.

Results

WLB revealed tracheal pedunculated lesions. EBUS showed a 1-cm hypoechogenic density corresponding to the papilloma, visualized above a hyperechogenic density corresponding to tracheal cartilage. There was no sonographic evidence of cartilage disruption or adjacent lymphadenopathy. OCT revealed a layer of heterogeneous light backscattering suggesting the mucosal papilloma, and a layer of high-degree scattering, corresponding to the central fibrovascular core noted on histology.

Conclusions

Layered microstructures of RRP and underlying airway cartilage can be identified using a combination of acoustic and optical bronchoscopic imaging modalities with different resolution and depth of penetration characteristics.

Previous detections of individual astrophysical sources of neutrinos are limited to the Sun and the supernova 1987A, whereas the origins of the diffuse flux of high-energy cosmic neutrinos remain unidentified. On 22 September 2017, we detected a high-energy neutrino, IceCube-170922A, with an energy of ~290 tera-electron volts. Its arrival direction was consistent with the location of a known γ-ray blazar, TXS 0506+056, observed to be in a flaring state. An extensive multiwavelength campaign followed, ranging from radio frequencies to γ-rays. These observations characterize the variability and energetics of the blazar and include the detection of TXS 0506+056 in very-high-energy γ-rays. This observation of a neutrino in spatial coincidence with a γ-ray-emitting blazar during an active phase suggests that blazars may be a source of high-energy neutrinos.