Cognitive-motor exergame training on a labile surface in stroke inpatients: study protocol for a randomized controlled trial.

Background: Cognitive-motor training in form of exergames has been found to be feasible and effective for the improvement of motor and cognitive functioning in older adults and several patient populations. Exergame training under unstable conditions might increase the proprioceptive resources needed and thus might be a superior training approach compared to exergame training on stable ground for stroke patients, who often have proprioceptive deficits. Objective: Aim of this study is to assess the feasibility and effects of exergame-based cognitive-motor training on a labile platform on physical and cognitive functioning in stroke inpatients. Methods: This is two-armed pilot randomized controlled trial taking place in an inpatient neurologic rehabilitation clinic. A total of 30 persons that are undergoing inpatient rehabilitation due to a stroke will be randomly assigned to either the intervention group (IG) or the control group (CG). Participants of the IG will receive exergame-based motor-cognitive training on a labile surface, whereas participants of the CG will train on a stable surface. Primary outcome is feasibility comprising measures of adherence, attrition, safety and usability. Secondary outcomes will be measures of cognitive (psychomotor speed, inhibition, selective attention, cognitive flexibility, brain activity) and motor (functional mobility, gait speed, balance, proprioception) functioning. Results: Data collection started in February 2024 and is expected to be completed by August 2024. Conclusion: This is the first study looking into exergame training on labile surface in stroke patients. It will give valuable insights into the feasibility and potential added value of this type of training and thus inform further implementation efforts in the context of inpatient rehabilitation. Clinical trial registration: ClinicalTrials.gov, NCT06296069.

Comparison of Enhanced and Standard Data Sheets on Treatment Fidelity and Data Collection for Tact Training.

Specifically designed data sheets have been recommended to assist with the fidelity of implementation of treatment procedures. The present study extended previous research (e.g., Bottini et al. Behavior Analysis: Research & Practice 21(2), 140-152, 2021; LeBlanc et al. Behavior Analysis in Practice 13(1), 53-62, 2020) by comparing an enhanced data sheet (i.e., the inclusion of randomized targets, prompts for treatment components of securing attending and reinforcement) to a standard data sheet (i.e., targets not preset, no prompts for treatment components) on the fidelity of tact training of features. Ten behavior therapists participated in each condition (n = 20). Participants first watched a brief instructional video explaining the teaching procedure and their assigned data sheet, followed by conducting a treatment session with a confederate serving as a child with autism spectrum disorder. The enhanced data sheet resulted in higher fidelity on multiple variables including randomizing of targets and data collection.

Machine learning judged neutral facial expressions as key factors for a "good therapist" within the first five minutes: An experiment to simulate online video counselling.

Objective: Machine learning models were employed to discern patients' impressions from the therapists' facial expressions during a virtual online video counselling session. Methods: Eight therapists simulated an online video counselling session for the same patient. The facial emotions of the therapists were extracted from the session videos; we then utilized a random forest model to determine the therapist's impression as perceived by the patients. Results: The therapists' neutral facial expressions were important controlling factors for patients' impressions. A predictive model with three neutral facial features achieved an accuracy of 83% in identifying patients' impressions. Conclusions: Neutral facial expressions may contribute to patient impressions in an online video counselling environment with spatiotemporal disconnection. Innovation: Expression recognition techniques were applied innovatively to an online counselling setting where therapists' expressions are limited. Our findings have the potential to enhance psychiatric clinical practice using Information and Communication Technology.

Native Aortic Valve Endocarditis Caused by Scopulariopsis Species: Case Report, Considerations for Management, and Review of Literature.

We present the first case of native aortic valve endocarditis caused by Scopulariopsis. Intraoperative images and videos from valve replacement surgery illustrate the severity of fungal endocarditis. This case demonstrates the aggressive presentation of left-sided fungal endocarditis, highlights challenges with treating highly resistant fungi, and considers the potential utility of olorofim.

Evaluation of the effectiveness of a video-based educational intervention on perinatal mental health related stigma reduction strategies for healthcare professionals: A single group pre-test-post-test pilot study.

BACKGROUND: Healthcare professionals have a role to play in reducing perinatal mental health related stigma. AIM: To assess the effectiveness of a video-based educational intervention developed to provide guidance to healthcare professionals on perinatal mental health related stigma reduction strategies. DESIGN: A single group pre-test-post-test pilot study with no control group. SETTING(S): A university affiliated maternity hospital in Ireland PARTICIPANTS: A convenience sample of registered midwives, nurses and doctors (n = 60) recruited from October 2020-January 2021. INTERVENTION: A twenty-minute video-based educational intervention. METHODS: Respondents (n = 60) completed a pre-test (time point one) and post-test (time point-two) questionnaire, and a three-month follow-up post-test questionnaire (time point-three) (n = 39). The questionnaire included the Mental Illness Clinicians' Attitudes Scale, Reported and Intended Behaviour Scale, Reynolds Empathy Scale and open-ended questions. Wilcoxon Signed Rank Test was selected to evaluate the pre-test post-test scores. RESULTS: The difference in mean Mental Illness: Clinicians' Attitudes-4 scores were statistically significant between time points one and three (z = 3.27, df=36, P = 0.0007) suggesting more positive attitudes towards people with mental health conditions after the intervention. The mean total score for the Reported and Intended Behaviour Scale increased from 18.7 (SD 1.87) at time point one to 19.2 (SD 1.60) at time point two (z= -3.368, df=59, P = 0.0004) suggesting an increase in positive intended behaviours towards those with mental health issues immediately following the intervention. These findings were also corroborated by responses to open-ended survey questions. CONCLUSIONS: Further research with a larger sample of healthcare professionals evaluated over a longer period would provide further evidence for the sustainability of the intervention. TWEETABLEABSTRACT: A video-based intervention can increase healthcare professionals' knowledge of perinatal #mentalhealth related stigma reduction strategies @Journal. Link to article.

Quality of lymph node dissection and early recurrence in robotic versus thoracoscopic lobectomy for stage N1-2 non-small cell lung cancer: Eleven-year real-world data from a high-volume center.

BACKGROUND: The efficacy of lymph node dissection (LND) and oncological outcomes of robot-assisted (RL) versus video-assisted thoracoscopic lobectomy (VL) for non-small cell lung cancer (NSCLC) with nodal involvement remains controversial. This study aims to compare LND quality and early recurrence (ER) rate between RL and VL for stage N1-2 NSCLC patients based on eleven-year real-world data from a high-volume center. METHODS: Pathologic stage IIB-IIIB (T1-3N1-2) NSCLC patients undergoing RL or VL in Shanghai Chest Hospital from 2010 to 2021 were retrospectively reviewed from a prospectively maintained database. Propensity-score matching (PSM, 1:4 RL versus VL) was performed to mitigate baseline differences. LND quality was evaluated by adequate (≥16) LND and nodal upstaging rates. ER was defined as recurrence occurring within 24 months post-surgery. RESULTS: Out of 1578 cases reviewed, PSM yielded 200 RL and 800 VL cases. Without compromising perioperative outcomes, RL assessed more N1 and N2 LNs and N1 stations, and led to higher incidences of adequate LND (58.5 % vs. 42.0 %, p < 0.001) and nodal upstaging (p = 0.026), compared to VL. Notably, RL improved perioperative outcomes for patients undergoing adequate LND than VL. Finally, RL notably reduced ER rate (22.0 % vs. 29.6 %, p = 0.032), especially LN ER rate (15.0 % vs. 21.5 %, p = 0.041), and prolonged disease-free survival (DFS; hazard ratio = 0.837, p = 0.040) compared with VL. Further subgroup analysis of ER and DFS within the cN1-2-stage cohort verified this survival benefit. CONCLUSIONS: RL surpasses VL in enhancing LND quality, reducing ER rates, and improving perioperative outcomes when adequate LND is performed for stage N1-2 NSCLC patients.

Co-occurrence of problematic facebook and video game use: prevalence and association with mental health disorders among adolescents.

INTRODUCTION: The rapid proliferation of technology and its impact on adolescents' lives have raised concerns about addictive behaviors and its potential consequences, including behavioral and mental health problems. This study investigates the prevalence and risk factors associated with the co-occurrence of Problematic Facebook Use and Problematic Video game Use among Tunisian adolescents. METHODOLOGY: We conducted a cross-sectional study in the urban area of Sousse governorate in Tunisia during the 2018/2019 school year. We selected a representative sample of high school students enrolled in public educational institutions in Sousse. Data collection was performed through a self-administered structured questionnaire, which gathered information on sociodemographic characteristics, lifestyle behaviors, and mental health disorders. Problematic Facebook Use was assessed using the validated Arabic version of the Bergen Scale, while Problematic Video Game Use was measured using the 21-point Lemmens Scale, which was translated into Arabic. Statistical analysis was carried out using the SPSS program (version 20). RESULTS: We enrolled a total of 1342 high school students in our study, of whom, 63.2% were female with a mean age of 17.5 ± 1.44 years. The prevalence of Problematic Facebook Use and Problematic Video Game Use was  28.3% and  13% respectively. Regarding the co-occurrence of the two problematic behaviors, 31.3% of participants faced a singular addictive behavior, either related to problematic Facebook or video game use, while 5% had both addictive behaviors simultaneously. In a multivariate analysis, risk factors for the co-occurrence of Problematic Facebook and Video Game Use, in decreasing order of significance, included severe depression (AOR = 4.527; p = 0.003), anxiety (AOR = 4.216; p = 0.001), male gender (AOR = 4.130; p < 0.001), problematic internet use (AOR = 3.477; p = 0.006), as well as moderate depression (AOR = 3.048; p = 0.007). CONCLUSION: Our study found that Problematic Facebook and Video Game Use were prevalent among Tunisian adolescents. The co-occurrence of these disorders is strongly linked to male gender, problematic internet use, depression, and anxiety disorders. These findings underscore the urgency of implementing tailored and effective awareness and prevention programs to address these emerging challenges.

Digital competences of university students after face-to-face and remote teaching: Video-animations digital create content.

In today's digitally advanced society, there is a need to focus on collaborative educational approaches of a socio-community nature that incorporate technology. From this perspective, the FEJYLEN and FEJYLENVAL programs were conceived and implemented for both remote (online) and face-to-face teaching. These programs are based on an E-Learning-Service methodology, enabling the training of university students in digital skills, and facilitating the transfer of their interactive educational video-animations to early childhood education centers. The study sample consisted of 221 students enrolled in Early Childhood Education and Speech Therapy Degrees. The study had two objectives: first, to compare digital competences before and after participating in the mentioned programs; and second, to evaluate the impact of the type of teaching and university training on the acquisition of digital competences. The findings indicate that students receiving face-to-face teaching demonstrated significant improvement across all digital competences' factors with a medium-high effect size. Conversely, for students receiving remote instruction, improvements were limited to only certain skill factors. Our study reveals that face-to-face teaching is associated with higher scores in digital competencies and more efficient digital content creation. In conclusion, this research highlights the advantages of face-to-face teaching in comparison to remote instruction. This has facilitated a closer connection between the university and the realities faced by educational centers, fostering the exchange of knowledge between learning communities.

Comparison of early postoperative patient-reported outcomes after multiportal robotic-assisted thoracoscopic surgery and uniportal video-assisted thoracoscopic surgery for non-small cell lung cancer.

INTRODUCTION: We aimed to compare early postoperative patient-reported outcomes between multiportal robotic-assisted thoracoscopic surgery (M-RATS) and uniportal video-assisted thoracoscopic surgery (U-VATS) for non-small-cell lung cancer (NSCLC). MATERIALS AND METHODS: Symptom severity and functional status were measured using the Perioperative Symptom Assessment for Lung Surgery at pre-surgery, during postoperative hospitalisation, and within 4 weeks of discharge. A propensity score-matched (PSM) analysis of patients with NSCLC who were treated with M-RATS and U-VATS was performed. The symptom severity and daily functional status presented as proportion of moderate-to-severe scores on a 0-10-point scale, were compared using a generalised estimation equation model. RESULTS: We enrolled 762 patients with NSCLC from a prospective cohort (CN-PRO-Lung 3), including 151 and 611 who underwent M-RATS and U-VATS, respectively, before PSM analysis. After 1:1 PSM, two groups of 148 patients each were created. Pain severity (P = 0.019) and activity limitation (P = 0.001) during hospitalisation were higher in the M-RATS group. However, no significant differences existed post-discharge in pain (P = 0.383), cough (P = 0.677), shortness of breath (P = 0.526), disturbed sleep (P = 0.525), drowsiness (P = 0.304), fatigue (P = 0.153), distress (P = 0.893), walking difficulty (P = 0.242), or activity limitation (P = 0.513). M-RATS caused less intraoperative blood loss (P = 0.013), more stations of dissected lymph nodes (P = 0.001), more numbers of dissected lymph nodes (P = 0.001), and less tube drainage on the first postoperative day (P = 0.003) than U-VATS. CONCLUSION: M-RATS and U-VATS achieved comparable symptom burden and functional impairment after discharge. However, compared to U-VATS, M-RATS was associated with more severe pain and activity limitation in the short postoperative period. TRIAL REGISTRATION NUMBER: ChiCTR2000033016.

Clinical practices in Swedish speech-language pathology for children with (developmental) language disorder.

In Sweden, treatment for children with (developmental) language disorder ((D)LD) is traditionally carried out at a speech-language pathology (SLP) clinic, and based on formal language tests, which may not entirely represent the child's everyday language and communication skills. SLP services that include video recordings have shown positive outcomes in terms of providing information about children's linguistic and communicative abilities in everyday life, but little is known about the use of video in clinical practice. The aim of this study is therefore to investigate how Swedish SLPs link their clinical practices (assessment, treatment, and evaluation of treatment outcome) to the everyday language and communication abilities of children with (D)LD. A further aim is to explore SLPs' utilisation of video recordings as a part of their clinical practices with the target group. A web-based questionnaire was distributed to SLPs in Sweden, who work with children with (D)LD. Results demonstrate that Swedish SLPs perceive that their intervention is in alignment with children's everyday language and communication needs to a fairly high degree. However, an exception is assessment, which is considered to have a weaker alignment with children's everyday communication abilities. The use of video recordings for clinical purposes is very limited. It is suggested here that incorporating video recordings from children's everyday life would be an easy and time-efficient way to strengthen the ecological validity of SLP practices for children with (D)LD.

Lymph node dissection in lung cancer surgery: a comparison between robot-assisted vs. video-assisted thoracoscopic approach.

Background: TNM staging is the most important prognosticator for non-small cell lung cancer (NSCLC) patients. Staging has significant implications for the treatment modality for these patients. Lymph node dissection in robot-assisted thoracoscopic (RATS) surgery remains an area of ongoing evaluation. In this study, we aim to compare lymph node dissection in RATS and VATS approach for lung resection in NSCLC patients. Methods: We retrospectively compiled a database of 717 patients from July 31, 2015-July 7, 2022, who underwent either a wedge resection, segmentectomy or lobectomy. We analysed the database according to lymph node dissection. The database was divided into RATS (n = 375) and VATS (n = 342) procedures. Results: The mean number of lymph nodes harvested overall with RATS was 6.1 ± 1.5 nodes; with VATS approach, it was 5.53 ± 1.8 nodes. The mean number of N1 stations harvested was 2.66 ± 0.8 with RATS, 2.36 ± 0.9 with VATS. RATS approach showed statistically higher lymph node dissection rates compared to VATS (p = 0.002). Out of the 375 RATS procedures, 26 (6.4%) patients undergoing a RATS procedure were upstaged from N0/N1 staging to N2. N0/N1-N2 upstaging was reported in 28 of 342 (8.2%) patients undergoing a VATS procedure. The majority of upstaging was seen in N0-N2 disease: 19 of 375 (5%) for RATS and 23 of 342 (6.7%) for VATS. Conclusions: We conclude that in RATS procedures, there is a higher rate of lymph node dissection compared to VATS procedures. Upstaging was mostly seen in N0-N2 disease, this was observed at a higher rate with VATS procedures.

The effect of informing patients with video before cardiac surgery on intensive care experience: A randomized controlled trial.

Objectives: To study the effect of informing patients with video before cardiac surgery on intensive care experience. Methods: This randomized controlled trial was conducted between December 2021 and December 2022 in the cardiovascular surgery clinic of a public hospital with the participation of 90 patients (45 patients in experimental group - 45 patients in control group) who were scheduled to undergo cardiac surgery. Patient Information Form and Intensive Care Experiences Scale were used for study data. Patients in experimental group were informed with video about the intensive care before cardiac surgery. Results: It was found that the total score on ICES of the experimental group (74.5±3.9) was statistically and significantly higher than that of the control group (63.9±6.4) (p<0.001). The sub-dimension of awareness of surroundings (20.8±1.7), the frightening experiences (18.6±1.0), and the recall of experience (18.5±1.5) and satisfaction with care (16.7±1.4) were found to be statistically significantly higher in the experimental group, than in the control group sub-dimension scores (p<0.001). Conclusion: It was found that informing patients with video about the intensive care setting and process before cardiac surgery had a positive effect on the intensive care experience. Note: The study was produced from a master's thesis and was not presented. All participants gave informed consent for the study, and that their anonymity was preserved.Trial Registration NO.: NCT05255887.

Efficacy of uniportal versus multiportal video-assisted thoracoscopic lobectomy for non-small cell lung cancer: A retrospective analysis.

Objective: To compare the uniportal and multiportal video-assisted thoracoscopic surgery (VATS) in patients with non-small-cell lung cancer (NSCLC). Methods: Medical records of 128 patients with NSCLC who underwent surgical treatment in the First School of Clinical Medicine, Southern Medical University from August 2020 to February 2022 were retrospectively analyzed. There were 60 patients who underwent uniportal VATS (UVATS group) and 68 patients underwent multiportal VATS (MVATS group). The relevant indexes, complications, postoperative pain levels and quality of life, recurrence, metastases and survival between the two groups were compared. Results: UVATS was associated with longer operation time and higher intraoperative blood loss compared to MVATS (P<0.05). The postoperative drainage volume, and the visual analogue scale (VAS) scores at 24 and 72 hours were lower in the UVATS group compared to the MVATS group, while the chest tube retention time and hospitalization time were shorter than those in the MVATS group (P<0.05). The quality of life at six months after surgery in the UVATS group was significantly higher than that in the MVATS group (P<0.05). Conclusions: UVATS and MVATS have similar outcomes in patients with NSCLC. Although UVATS surgery takes longer and is associated with more interoperative bleeding, it can reduce postoperative pain, shorten postoperative recovery time, and help further improve the quality of life of patients after surgery.

Glottis Recognition Software Development Using Artificial Intelligence.

The use of video laryngoscopes has enhanced the visualization of the vocal cords, thereby improving the accessibility of tracheal intubation. Employing artificial intelligence (AI) to recognize images obtained through video laryngoscopy, particularly when marking the epiglottis and vocal cords, may elucidate anatomical structures and enhance anatomical comprehension of anatomy. This study investigates the ability of an AI model to accurately identify the glottis in video laryngoscope images captured from a manikin. Tracheal intubation was conducted on a manikin using a bronchoscope with recording capabilities, and image data of the glottis was gathered for creating an AI model. Data preprocessing and annotation of the vocal cords, epiglottis, and glottis were performed, and human annotation of the vocal cords, epiglottis, and glottis was carried out. Based on the AI's determinations, anatomical structures were color-coded for identification. The recognition accuracy of the epiglottis and vocal cords recognized by the AI model was 0.9516, which was over 95%. The AI successfully marked the glottis, epiglottis, and vocal cords during the tracheal intubation process. These markings significantly aided in the visual identification of the respective structures with an accuracy of more than 95%. The AI demonstrated the ability to recognize the epiglottis, vocal cords, and glottis using an image recognition model of a manikin.

Leveraging technology to improve access to medical education in anatomy and physiology in resource-limited settings: A mixed methods study.

This study assesses the acceptability, appropriateness, feasibility, and efficacy of a novel asynchronous video-based intervention for teaching respiratory physiology and anatomy to medical students in resource-limited settings. A series of short video lectures on pleural anatomy, pulmonary physiology, and pathophysiology was created using Lightboard and screen capture technology. These were uploaded to YouTube and Google Drive and made available to 1st-3rd year medical students at two Latin American universities for 1 week. Employing a parallel-convergent mixed methods design, we conducted surveys, focus groups, interviews, and pre/post testing for qualitative and quantitative data. Thematic Analysis was used to analyze qualitative data and McNemar's test for quantitative analysis. Seventy-six students participated. The videos' short format, interactivity, and Lightboard style were highly valued for their flexibility, time efficiency, and educational impact. Students recognized their clinical relevance and trusted their content, suggesting potential applicability in similar settings. Despite infrastructure and connectivity challenges, the use of flexible streaming and downloadable options facilitated learning. Survey results indicated high levels of feasibility (99%), appropriateness (95%), and acceptability (95%), with significant knowledge gains observed (37% correct pre-test answers vs. 56% post-test, p < 0.0001). Our findings demonstrate high acceptability, appropriateness, feasibility, and efficacy of a targeted asynchronous education centered on short-format videos in resource-limited settings, enabling robust learning despite local barriers. Flexible access is key for overcoming localized barriers. Taking an adaptive, learner-centered approach to content creation and delivery to address constraints was pivotal to success. Our modular videos could serve as versatile models for flexible education in resource-constrained settings.

Types of short video addiction among college freshmen: Effects on career adaptability, insomnia, and depressive symptoms.

This study investigated the effects of different types of short video addiction on social adaptation. The aim of this study was to identify the various types of short video addiction among freshmen and the correlations with career adaptability, insomnia, and depressive symptoms. We recruited 931 freshmen and used latent profile analysis to classify participants based on different characteristics of short video addiction. Based on the results of a short video addiction questionnaire, participants were found to exhibit distinct answer patterns, categorized into five types. Class 1 exhibited minimal signs of addiction. Class 2 displayed fluctuations with stronger tendencies towards withdrawal or escape. Class 3 demonstrated a moderate inability to control cravings for short videos. Class 4 showed fluctuations but with less anxiety and feelings of lost. Finally, Class 5 presented the most pronounced symptoms of short video addiction. Freshmen with varying degrees of short video addiction exhibited significant differences in career adaptability, sleep quality, and depressive symptoms. Class 1 students showed strong career adaptability and sound sleep, whereas Class 5 students had the highest depression rates. Overall, our findings suggest that the characteristics of short video addiction in first-year students also indicate poor social adaptation, which is mainly manifested as weak career adaptability, decreased sleep quality, and depressive symptoms. One way to guide first-year students to adapt to campus life is for educators to provide timely interventions for students with severe short video addiction.

Are we tackle ready? Cross-sectional video analysis of match tackle characteristics in elite women's Rugby Union.

The tackle contest is the most common and most injurious match contact event in rugby and is an indicator of performance. Tackle Ready is World Rugby's tackle technique education program. Limited research has characterized the tackle contest in women's rugby. The purpose of this study is to: (1) identify the match situational characteristics, ball-carrier and tackler technical actions demonstrated in elite women's Rugby Union and (2) to determine the extent to which Tackle Ready recommended tackle techniques were exhibited. Technical characteristics for 1500 tackle events in the 2022-2023 Women's Six Nations Championship were visually assessed according to a predefined coding framework and the Tackle Ready program. Tackles lacked full completion (0.2%) of the 22 coded Tackle Ready techniques with 47% of the recommended techniques demonstrated in each tackle on average (range 15%-98%). A high proportion of tackles involved two defenders (48%), approaching ball-carriers from the side (38%) or oblique angles (39%), in an upright position (30%), and with initial contact made with the arm (51%). Incorrect pre-contact head positioning and head placement upon contact accounted for 50% and 15% of tackles, respectively, and there was a mean of 14 (95% CI 11-18) head and neck contacts to a tackler and 18 (95% CI 14-22) head and neck contacts to a ball-carrier per game. Targeted interventions to encourage adoption of recommended techniques are needed to reduce tackle-related injury risk in women's rugby. This study provides valuable context for future discussion across law enforcement, coach education and gender-specific tackle coaching in the women's game.

Artificial intelligence automated surgical phases recognition in intraoperative videos of laparoscopic pancreatoduodenectomy.

BACKGROUND: Laparoscopic pancreatoduodenectomy (LPD) is one of the most challenging operations and has a long learning curve. Artificial intelligence (AI) automated surgical phase recognition in intraoperative videos has many potential applications in surgical education, helping shorten the learning curve, but no study has made this breakthrough in LPD. Herein, we aimed to build AI models to recognize the surgical phase in LPD and explore the performance characteristics of AI models. METHODS: Among 69 LPD videos from a single surgical team, we used 42 in the building group to establish the models and used the remaining 27 videos in the analysis group to assess the models' performance characteristics. We annotated 13 surgical phases of LPD, including 4 key phases and 9 necessary phases. Two minimal invasive pancreatic surgeons annotated all the videos. We built two AI models for the key phase and necessary phase recognition, based on convolutional neural networks. The overall performance of the AI models was determined mainly by mean average precision (mAP). RESULTS: Overall mAPs of the AI models in the test set of the building group were 89.7% and 84.7% for key phases and necessary phases, respectively. In the 27-video analysis group, overall mAPs were 86.8% and 71.2%, with maximum mAPs of 98.1% and 93.9%. We found commonalities between the error of model recognition and the differences of surgeon annotation, and the AI model exhibited bad performance in cases with anatomic variation or lesion involvement with adjacent organs. CONCLUSIONS: AI automated surgical phase recognition can be achieved in LPD, with outstanding performance in selective cases. This breakthrough may be the first step toward AI- and video-based surgical education in more complex surgeries.

Hospital Staff Perspectives on the Drivers and Challenges in Implementing a Virtual Rehabilitation Ward: Qualitative Study.

Background: Over the past decade, the adoption of virtual wards has surged. Virtual wards aim to prevent unnecessary hospital admissions, expedite home discharge, and enhance patient satisfaction, which are particularly beneficial for the older adult population who faces risks associated with hospitalization. Consequently, substantial investments are being made in virtual rehabilitation wards (VRWs), despite evidence of varying levels of success in their implementation. However, the facilitators and barriers experienced by virtual ward staff for the rapid implementation of these innovative care models remain poorly understood. Objective: This paper presents insights from hospital staff working on an Australian VRW in response to the growing demand for programs aimed at preventing hospital admissions. We explore staff's perspectives on the facilitators and barriers of the VRW, shedding light on service setup and delivery. Methods: Qualitative interviews were conducted with 21 VRW staff using the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework. The analysis of data was performed using framework analysis and the 7 domains of the NASSS framework. Results: The results were mapped onto the 7 domains of the NASSS framework. (1) Condition: Managing certain conditions, especially those involving comorbidities and sociocultural factors, can be challenging. (2) Technology: The VRW demonstrated suitability for technologically engaged patients without cognitive impairment, offering advantages in clinical decision-making through remote monitoring and video calls. However, interoperability issues and equipment malfunctions caused staff frustration, highlighting the importance of promptly addressing technical challenges. (3) Value proposition: The VRW empowered patients to choose their care location, extending access to care for rural communities and enabling home-based treatment for older adults. (4) Adopters and (5) organizations: Despite these benefits, the cultural shift from in-person to remote treatment introduced uncertainties in workflows, professional responsibilities, resource allocation, and intake processes. (6) Wider system and (7) embedding: As the service continues to develop to address gaps in hospital capacity, it is imperative to prioritize ongoing adaptation. This includes refining the process of smoothly transferring patients back to the hospital, addressing technical aspects, ensuring seamless continuity of care, and thoughtfully considering how the burden of care may shift to patients and their families. Conclusions: In this qualitative study exploring health care staff's experience of an innovative VRW, we identified several drivers and challenges to implementation and acceptability. The findings have implications for future services considering implementing VRWs for older adults in terms of service setup and delivery. Future work will focus on assessing patient and carer experiences of the VRW.