Similarity Analysis of Clinical Notes for Revealing Writing Styles in an Electronic Medical Record System.

BACKGROUND: One of the disadvantages of medical documentation in Electronic Medical Record (EMR) systems is that records tend to be redundant by "copying and pasting", a writing style to duplicate and revise previous records. In this study, we analyzed the similarity between records to identify the factors affecting the writing style of clinical notes. METHOD: We analyzed 98,038 records of 4,149 patients from two years in the Department of Obstetricians and Gynecology at Kyoto University Hospital, Japan. We observed the correlation between the distribution of the record similarity and string amounts, as well as the disease codes and ratios of outpatient visit. RESULTS: The patient group with high record similarity and large number of strings was the group with reproductive medicine, followed by the group of malignant tumor follow-up or Women's Healthcare. DISCUSSION: In reproductive medicine, physicians have a demand for an overarching evaluation, and in follow-up malignancies or in Women's Healthcare, they have a demand to check for subtle differences from the last time. These facts along with our data insist that the writing style in EMR systems is related to the patient's status. CONCLUSION: We declared that the writing style in EMR systems is affected by the patient's status. The writing style of duplicating and revising is preferred (1) when there is a clinical demand for an overarching evaluation, and (2) when there is a clinical demand to check for subtle differences from the last time.

Comparing Patient Perception and Physician's Records: Generative AI Performance Evaluation.

Patient perception involves a patient's thoughts and beliefs regarding their health status. It is also associated with medical compliance and outcomes. However, discrepancies often arise between patient perception and physicians' documentation within the medical records, resulting in misunderstanding and suboptimal doctor-patient communication. In this study, we assessed the efficacy of generative artificial intelligence (AI) in comparing the content of patient perception as recorded in patient questionnaires and physicians' records of the Department of Breast Surgery. We evaluated the precision and recall of the generative AI by comparison with human-created ground truth. Our results demonstrated the high performance of the generative AI in comprehending and contrasting symptoms and the entire content recorded differently by patients and physicians, with F1 scores ranging from 0.77 to 0.97. These results highlight the potential contribution of a generative AI to deeper mutual comprehension in healthcare scenarios.

Real-time detection of active bleeding in laparoscopic colectomy using artificial intelligence.

BACKGROUND: Most intraoperative adverse events (iAEs) result from surgeons' errors, and bleeding is the majority of iAEs. Recognizing active bleeding timely is important to ensure safe surgery, and artificial intelligence (AI) has great potential for detecting active bleeding and providing real-time surgical support. This study aimed to develop a real-time AI model to detect active intraoperative bleeding. METHODS: We extracted 27 surgical videos from a nationwide multi-institutional surgical video database in Japan and divided them at the patient level into three sets: training (n = 21), validation (n = 3), and testing (n = 3). We subsequently extracted the bleeding scenes and labeled distinctively active bleeding and blood pooling frame by frame. We used pre-trained YOLOv7_6w and developed a model to learn both active bleeding and blood pooling. The Average Precision at an Intersection over Union threshold of 0.5 (AP.50) for active bleeding and frames per second (FPS) were quantified. In addition, we conducted two 5-point Likert scales (5 = Excellent, 4 = Good, 3 = Fair, 2 = Poor, and 1 = Fail) questionnaires about sensitivity (the sensitivity score) and number of overdetection areas (the overdetection score) to investigate the surgeons' assessment. RESULTS: We annotated 34,117 images of 254 bleeding events. The AP.50 for active bleeding in the developed model was 0.574 and the FPS was 48.5. Twenty surgeons answered two questionnaires, indicating a sensitivity score of 4.92 and an overdetection score of 4.62 for the model. CONCLUSIONS: We developed an AI model to detect active bleeding, achieving real-time processing speed. Our AI model can be used to provide real-time surgical support.

Individual Activity Anomaly Estimation in Operating Rooms Based on Time-Sequential Prediction.

Surveillance videos of operating rooms have potential to benefit post-operative analysis and study. However, there is currently no effective method to extract useful information from the long and massive videos. As a step towards tackling this issue, we propose a novel method to recognize and evaluate individual activities using an anomaly estimation model based on time-sequential prediction. We verified the effectiveness of our method by comparing two time-sequential features: individual bounding boxes and body key points. Experiment results using actual surgery videos show that the bounding boxes are suitable for predicting and detecting regional movements, while the anomaly scores using key points can hardly be used to detect activities. As future work, we will be proceeding with extending our activity prediction for detecting unexpected and urgent events.

PreFlap: From Photoacoustic Tomography Images to Vascular Mapping Sheets for Improved Preoperative Flap Evaluation.

OBJECTIVE: Advancements in technology have improved image acquisition and processing in the field of medical imaging, giving medical doctors the tools to implement effective medical care. In plastic surgery, despite advances in anatomical knowledge and technology, problems in preoperative planning for flap surgery remain. METHODS: In this study, we propose a new protocol to analyze three-dimensional (3D) Photoacoustic tomography images and generate two-dimensional (2D) mapping sheets that can help surgeons identify perforators and the perfusion territory during preoperative planning. The core of this protocol is PreFlap, a new algorithm that converts 3D photoacoustic tomography images into 2D vascular mapping images. CONCLUSION: Experimental results demonstrate that PreFlap can improve preoperative flap evaluation, thus can greatly saving surgeons' time and improving surgical outcomes.

Preoperative visualization of midline-crossing subcutaneous arteries in transverse abdominal flaps using photoacoustic tomography.

BACKGROUND: Photoacoustic tomography is a noninvasive vascular imaging modality that uses near-infrared pulsed laser light and ultrasound to visualize vessels. We previously demonstrated the utility of photoacoustic tomography for anterolateral thigh flap surgery involving body-attachable vascular mapping sheets. However, it was not possible to obtain clear separate images of arteries and veins. In this study, we tried to visualize subcutaneous arteries that cross the midline of the abdomen, since these arteries are known to be important for obtaining large perfusion areas in transverse abdominal flaps. METHODS: Four patients scheduled to undergo breast reconstruction with abdominal flaps were examined. Photoacoustic tomography was performed preoperatively. The tentative arteries and veins were traced according to the S-factor, an approximate hemoglobin oxygen saturation parameter calculated using 2 laser excitation wavelengths (756 and 797 nm). Intraoperatively, arterial-phase indocyanine green (ICG) angiography was performed after abdominal flap elevation. Images of vessels speculated to be arteries by preoperative photoacoustic tomography were merged with those of intraoperative ICG angiography and analyzed in an 8 × 4-cm2 area below the umbilical region. RESULTS: The S-factor was used to visualize the midline-crossing subcutaneous arteries in all 4 patients. A matching analysis compared preoperative tentative arteries according to photoacoustic tomography with ICG angiography results in the 8 × 4-cm2 area below the umbilical region and indicated a 71.3-82.1% match (average: 76.9% match). CONCLUSIONS: This study demonstrates that the S-factor, a noninvasive, label-free imaging modality, can be used to successfully visualize subcutaneous arteries. This information can aid in selecting perforators for abdominal flap surgery.

Detecting Severe Incidents from Electronic Medical Records Using Machine Learning Methods.

The goal of this research was to design a solution to detect non-reported incidents, especially severe incidents. To achieve this goal, we proposed a method to process electronic medical records and automatically extract clinical notes describing severe incidents. To evaluate the proposed method, we implemented a system and used the system. The system successfully detected a non-reported incident to the safety management department.

Preoperative vascular mapping for anterolateral thigh flap surgeries: A clinical trial of photoacoustic tomography imaging.

BACKGROUND: Photoacoustic tomography (PAT) is a noninvasive vascular imaging modality that uses near-infrared pulse laser beams and ultrasound (US) to visualize vessels. We previously demonstrated the utility of PAT for visualizing anterolateral thigh (ALT) perforators in a clinical study of 10 thighs in 5 healthy adults. Evaluation of the correlation between PAT and US findings showed that PAT had comparable diagnostic potential but was superior in visualizing subcutaneous microvessels; however, there was no comparison with intraoperative findings. In this study, we used a newly developed technique to transfer a PAT image to a body-attachable transparent sheet to compare PAT and intraoperative findings. METHODS: Eight patients were recruited in this prospective study. Patient age ranged from 32 to 79 years (average 60). Seven ALT flaps were applied in head and neck reconstruction. One flap was elevated in chest wall reconstruction. Each PAT scan of an 18 cm × 13.5 cm region took approximately 5 min. Acquired data were processed three-dimensionally using a novel imaging software program. Perforator vessel data from PAT imaging were traced and corrected for projection onto medical film sheets. The correlation between the perforator stem portions predicted by PAT and the intraoperative findings at the level of the fascia-penetrating points was evaluated, and distal branching patterns were analyzed. RESULTS: PAT imaging showed 16 perforators in 8 thighs. Intraoperative surgical findings revealed that all the perforator penetrating points at the deep fascia level matched the PAT findings within 10 mm. None of the eight ALT flaps demonstrated postoperative complications. The perforator complexes were classified as type I in three cases (19%), type II in eight cases (50%), and type III in five cases (31%). CONCLUSIONS: PAT imaging matched the intraoperative findings within 10 mm. Preoperative vascular evaluation allows for the creation of a vascular map for facilitating ALT flap surgeries.

Evaluation of a novel multi-articulated endoscope: proof of concept through a virtual simulation.

PURPOSE: In endoscopic surgery such as video-assisted thoracoscopic surgery and laparoscopic surgery, providing the surgeon a good view of the target is important. Rigid endoscope has for years been the go-to tool for this purpose, but it has certain limitations like the inability to work around obstacles. To improve on current tools, a novel multi-articulated endoscope (MAE) is currently under development. To investigate its feasibility and possible value, we performed a user test using virtual prototype of the MAE with the intent to show that it outperforms the conventional endoscope while bringing minimal additional burden to the operator. METHODS: To evaluate the prototype, we built a virtual model of the MAE and a rigid oblique-viewing endoscope. Through a comparative user study we evaluate the ability of each device to visualize certain targets placed inside the virtual chest cavity by the angle between the visual axis of the scope and the normal of the plane of the target, while accounting for the usability of each endoscope by recording the time taken for each task. In addition, we collected a questionnaire from each participant to obtain feedback. RESULTS: The angles obtained using the MAE were smaller on average ([Formula: see text]), indicating that better visualization can be achieved through the proposed method. A nonsignificant difference in mean time taken for each task in favor of the rigid endoscope was also found ([Formula: see text]). CONCLUSIONS: We have demonstrated that better visualization for endoscopic surgery can be achieved through our novel MAE. The scope may bring about a paradigm shift in the field of minimally invasive surgery by providing more freedom in viewpoint selection, enabling surgeons to perform more elaborate procedures in minimally invasive settings.