Clinical applicability of an artificial intelligence prediction algorithm for early prediction of non-persistent atrial fibrillation.

Background and aims: It is difficult to document atrial fibrillation (AF) on ECG in patients with non-persistent atrial fibrillation (non-PeAF). There is limited understanding of whether an AI prediction algorithm could predict the occurrence of non-PeAF from the information of normal sinus rhythm (SR) of a 12-lead ECG. This study aimed to derive a precise predictive AI model for screening non-PeAF using SR ECG within 4 weeks. Methods: This retrospective cohort study included patients aged 18 to 99 with SR ECG on 12-lead standard ECG (10 seconds) in Ewha Womans University Medical Center for 3 years. Data were preprocessed into three window periods (which are defined with the duration from SR to non-PeAF detection) - 1 week, 2 weeks, and 4 weeks from the AF detection prospectively. For experiments, we adopted a Residual Neural Network model based on 1D-CNN proposed in a previous study. We used 7,595 SR ECGs (extracted from 215,875 ECGs) with window periods of 1 week, 2 weeks, and 4 weeks for analysis. Results: The prediction algorithm showed an AUC of 0.862 and an F1-score of 0.84 in the 1:4 matched group of a 1-week window period. For the 1:4 matched group of a 2-week window period, it showed an AUC of 0.864 and an F1-score of 0.85. Finally, for the 1:4 matched group of a 4-week window period, it showed an AUC of 0.842 and an F1-score of 0.83. Conclusion: The AI prediction algorithm showed the possibility of risk stratification for early detection of non-PeAF. Moreover, this study showed that a short window period is also sufficient to detect non-PeAF.

Effect of Etching Procedures on the Adhesion of Biofilm-Coated Dentin.

Oral biofilms coat all surfaces in the oral cavity including the exposed dentin surface. This study aimed to investigate biofilm removal by acid etching procedures and the effects of the residual biofilm on dentin surfaces on composite-dentin adhesion. Dentin discs were assigned to five groups: no biofilm formation (C); biofilm formation and no surface treatment (BF); biofilm formation and acid etching (BF-E); biofilm formation and acid etching followed by chlorhexidine soaking (BF-EC); and biofilm formation and rubbing with pumice, followed by acid etching (BF-RE). Biofilms were formed on saliva-precoated dentin discs by soaking the discs in Streptococcus mutans (S. mutans) suspension. Biofilm removal from the dentin surface was evaluated quantitatively and qualitatively by confocal laser scanning microscopy and scanning electron microscopy, respectively. To compare the bond strength of the biofilm-coated dentin discs with the surface treatments, specimens were assigned to four groups: no biofilm formation and acid etching (C-E); BF-E; BF-EC; and BF-RE. Assessments of the micro-shear bond strength and subsequent failure modes were performed. BF-E and BF-EC did not remove the biofilm, whereas BF-RE partially removed the biofilm attached to the dentin (p < 0.05). The bond strength of BF-RE was significantly higher than those of BF-E and BF-EC, but lower than that of C-E (p < 0.05). In conclusion, mechanical biofilm removal is recommended before etching procedures to enhance adhesion to the biofilm-coated dentin.

Performance of the nasal photoplethysmographic index as an analgesic index during surgery under general anaesthesia.

In a previous study, we developed a new analgesic index using nasal photoplethysmography (nasal photoplethysmographic index, NPI) and showed that the NPI was superior to the surgical pleth index (SPI) in distinguishing pain above numerical rating scale 3. Because the NPI was developed using data obtained from conscious patients with pain, we evaluated the performance of NPI in comparison with the SPI and the analgesia nociception index (ANI) in patients under general anaesthesia with target-controlled infusion of propofol and remifentanil. The time of nociception occurrence was defined as when the signs of inadequate anaesthesia occurred. The median values of NPI, SPI, and ANI for 1 minute from the time of the sign of inadequate anaesthesia were determined as the value of each analgesic index that represents inadequate anaesthesia. The time of no nociception was determined as 2 minutes before the onset of skin incision, and the median value for 1 minute from that time was defined as the baseline value. In total, 81 patients were included in the analysis. NPI showed good performance in distinguishing inadequate anaesthesia during propofol-remifentanil based general anaesthesia. NPI had the highest value in terms of area under the receiver operating characteristic curve, albeit without statistical significance (NPI: 0.733, SPI: 0.722, ANI: 0.668). The coefficient of variations of baseline values of NPI, SPI, and ANI were 27.5, 47.2, and 26.1, respectively. Thus, the NPI was effective for detecting inadequate anaesthesia, showing similar performance with both indices and less baseline inter-individual variability than the SPI.