Development of an Artificial Intelligence-Based Image Recognition System for Time-Sequence Analysis of Tracheal Intubation.

BACKGROUND: Total intubation time (TIT) is an objective indicator of tracheal intubation (TI) difficulties. However, large variations in TIT because of diverse initial and end targets make it difficult to compare studies. A video laryngoscope (VLS) can capture images during the TI process. By using artificial intelligence (AI) to detect airway structures, the start and end points can be freely selected, thus eliminating the inconsistencies. Further deconstructing the process and establishing time-sequence analysis may aid in gaining further understanding of the TI process. METHODS: We developed a time-sequencing system for analyzing TI performed using a #3 Macintosh VLS. This system was established and validated on 30 easy TIs performed by specialists and validated using TI videos performed by a postgraduate-year (PGY) physician. Thirty easy intubation videos were selected from a cohort approved by our institutional review board (B-ER-107-088), and 6 targets were labeled: the lip, epiglottis, laryngopharynx, glottic opening, tube tip, and a black line on the endotracheal tube. We used 887 captured images to develop an AI model trained using You Only Look Once, Version 3 (YOLOv3). Seven cut points were selected for phase division. Seven experts selected the cut points. The expert cut points were used to validate the AI-identified cut points and time-sequence data. After the removal of the tube tip and laryngopharynx images, the durations between 5 identical cut points and sequentially identified the durations of 4 intubation phases, as well as TIT. RESULTS: The average and total losses approached 0 within 150 cycles of model training for target identification. The identification rate for all cut points was 92.4% (194 of 210), which increased to 99.4% (179 of 180) after the removal of the tube tip target. The 4 phase durations and TIT calculated by the AI model and those from the expert exhibited strong Pearson correlation (phase I, r = 0.914; phase II, r = 0.868; phase III, r = 0.964; and phase IV, r = 0.949; TIT, r = 0.99; all P < .001). Similar findings were obtained for the PGY's observations (r > 0.95; P < .01). CONCLUSIONS: YOLOv3 is a powerful tool for analyzing images recorded by VLS. By using AI to detect the airway structures, the start and end points can be freely selected, resolving the heterogeneity resulting from the inconsistencies in the TIT cut points across studies. Time-sequence analysis involving the deconstruction of VLS-recorded TI images into several phases should be conducted in further TI research.

Molecular characterization of Clostridium perfringens isolates from a tertiary children's hospital in Guangzhou, China, establishing an association between bacterial colonization and food allergies in infants.

BACKGROUND: Cow's milk protein allergy (CMPA) is one of the most common types of food allergy in infants. Faecal pathogen cultures showed that the positive rate of Clostridium perfringens was more than 30%, which was significantly higher than that for other bacteria. Therefore, it is speculated that Clostridium perfringens colonization may be one of the pathogenetic factors for CMPA in infants. We conducted a real-world evidence study. Infants aged 0-6 months with diarrhoea and mucoid and/or bloody stools were recruited from a large tertiary hospital in China. Faecal pathogen cultures for the detection of Clostridium perfringens were confirmed by flight mass spectrometry, and potential toxin genes were identified using PCR. After 12 months of follow-up, the diagnoses of CMPA and food allergy were recorded. The correlation was assessed by Pearson correlation analysis. RESULTS: In this study, 358 infants aged 0-6 months with gastrointestinal symptoms and faecal pathogen cultures were recruited. A total of 270 (44.07% girls; mean age, 2.78 ± 2.84 months) infants were followed up for 12 months. Overall, the rate of positivity for Clostridium perfringens in faecal pathogen cultures was 35.75% (128/358) in infants aged ≤ 6 months. The earliest Clostridium perfringens colonization was detected within 2 days after birth. The majority of Clostridium perfringens isolates were classified as type C in 85 stool samples. In the Clostridium perfringens-positive group, 48.21% (54/112) of infants were clinically diagnosed with food allergies after 12 months, including 37.5% (42/112) with CMPA, which was significantly higher than that of the negative group, with 7.59% (12/158) exhibiting food allergies and 5.06% (8/158) presenting CMPA (P < 0.0001). Faecal Clostridium perfringens positivity was significantly correlated with CMPA, food allergy, faecal occult blood, faecal white blood cells, antibiotic use, increased peripheral blood platelet counts, and decreased haemoglobin levels (P < 0.0001). CONCLUSIONS: This study demonstrates that intestinal colonization by Clostridium perfringens is common in infants. The majority of Clostridium perfringens isolates are classified as type C. Colonization of the intestine by Clostridium perfringens is associated with the development of CMPA and food allergy in infants.

Cell-Coupled Long Short-Term Memory With L -Skip Fusion Mechanism for Mood Disorder Detection Through Elicited Audiovisual Features.

In early stages, patients with bipolar disorder are often diagnosed as having unipolar depression in mood disorder diagnosis. Because the long-term monitoring is limited by the delayed detection of mood disorder, an accurate and one-time diagnosis is desirable to avoid delay in appropriate treatment due to misdiagnosis. In this paper, an elicitation-based approach is proposed for realizing a one-time diagnosis by using responses elicited from patients by having them watch six emotion-eliciting videos. After watching each video clip, the conversations, including patient facial expressions and speech responses, between the participant and the clinician conducting the interview were recorded. Next, the hierarchical spectral clustering algorithm was employed to adapt the facial expression and speech response features by using the extended Cohn-Kanade and eNTERFACE databases. A denoizing autoencoder was further applied to extract the bottleneck features of the adapted data. Then, the facial and speech bottleneck features were input into support vector machines to obtain speech emotion profiles (EPs) and the modulation spectrum (MS) of the facial action unit sequence for each elicited response. Finally, a cell-coupled long short-term memory (LSTM) network with an L -skip fusion mechanism was proposed to model the temporal information of all elicited responses and to loosely fuse the EPs and the MS for conducting mood disorder detection. The experimental results revealed that the cell-coupled LSTM with the L -skip fusion mechanism has promising advantages and efficacy for mood disorder detection.