Search Results (5)

Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO^® stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software^®. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed. Full article

Background and Clinical Significance: Uterine fibroids affect up to 25% of women of reproductive age and can lead to significant symptoms or impact fertility, often requiring surgical management. While hysteroscopic myomectomy is suitable for intracavitary fibroids, intramural and subserosal fibroids typically necessitate open or minimally invasive surgery (MIS). Laparoscopic approaches offer notable advantages, including reduced postoperative pain and faster recovery. However, MIS is frequently avoided in cases of very large fibroids due to technical difficulty and concerns about safe tissue extraction. Power morcellation, previously used for specimen removal, has fallen out of favor due to the risk of disseminating occult malignancies, especially in women over 35. Therefore, establishing the feasibility of MIS without morcellation in such cases is essential. Case Presentation: A woman of reproductive age presented with a symptomatic uterine fibroid measuring approximately 4 kg (1500 cm³). Laparoscopic myomectomy was performed using a modified trocar entry technique and contained tissue fragmentation, avoiding morcellation. The operation was completed successfully without complications. Postoperative recovery was uneventful, and the patient was discharged on postoperative day two. Histopathological examination confirmed a benign leiomyoma. Conclusions: This case highlights the feasibility of laparoscopic removal of an exceptionally large uterine fibroid without morcellation. Through careful patient selection, strategic trocar placement, and controlled tissue fragmentation, MIS can be safely performed in select high-volume cases. These findings support reconsidering the size limitations of laparoscopic myomectomy when conducted by experienced surgeons using appropriate techniques. Full article

Background: To report the evaluation of incentive spirometry (IS)-induced pressure changes in intra-abdominal drainage catheters and consider its use for maintaining catheter patency and enhancing drainage. Methods: Prospective study of patients with indwelling intra-abdominal drainage catheters for abdominal fluid collections who had their intra-abdominal pressures measured while performing incentive spirometry. Patients were instructed in the use of an incentive spirometer. Within a week after initial drainage, pressure changes with IS were evaluated three times at 1500 cc and three times at maximum inspiratory effort. Intra-abdominal pressure (IAP) was measured using a pressure monitor connected to the drainage catheter. Results: Twenty patients (men, 12; women, 8). Fluid collection locations were pelvis, Right-upper quadrant (RUQ), Left-upper quadrant (LUQ), Left-lower quadrant (LLQ), and Right-lower quadrant (RLQ). A total of 16 of 20 patients showed an elevation of IAP with IS. At 1500 cc, the pressure increased by an average of 41.24 mmH₂O. At maximal inspiratory effort, the pressure increased by an average of 48.26 mmH₂O. Pressure increase was greater in upper abdomen catheters. Four patients with lower abdominal and pelvic collections showed minimal pressure changes with IS. Conclusion: IS increases IAP and fluid flow through abdominal drainage catheters. Future studies are warranted to determine whether the use of IS enhances catheter performance and facilitates drainage via its effect on IAP. Full article

With rapid urban population growth and industrial agglomeration, the urban land supply is becoming gradually tight. Improving land use quality (LUQ) is becoming increasingly critical. This study was carried out in the Luohe built-up zones between 2013 and 2021. The aim is to explore the growth characteristics of LUQ and determine the association between the inner urban location and the growth rate from the perspective of spatial heterogeneity. Therefore, based on a socio-economic-environmental framework, we selected an integration/GDP/population/artificial-surface Rate, and a remote-sensing-based ecological index to construct a LUQ assessment framework that is more stable and applicable for developing urban areas. Additionally, then, multiscale geographical weighted regression is adopted, which can better help us explore the scale of the location factors. The results show that: (1) The LUQ overall growth is gradually slowing. High-quality areas clustered in the urban center and subsystem elements spread outward along the national and provincial highways to drive boundary expansion; (2) In the W/E/SE direction, land use tends more towards physical sprawl than usual development and expansion; (3) Location factors were distinguished as global, semi-global, and local. The global factors constitute the homogenized locational space. Semi-global and local factors constitute a heterogeneous locational space. The latter is critical to guide LUQ growth. LUQ assessment can promote intensive land use. Exploring location factors can further guide the LUQ spatial growth and provide data in support of urban planning. Full article

Streams and rivers of the Luquillo Experimental Forest, Puerto Rico, have been the subject of extensive watershed and aquatic research since the 1980s. This research includes understanding stream export of nutrients and coarse particulate organic matter, physicochemical constituents, aquatic fauna populations and community structure. However, many of the streams and watersheds studied do not appear in standard scale maps. We document recent collaborative and multi-institutional work to improve hydrological network information and identify knowledge gaps. The methods used to delimit and densify stream networks include establishment and incorporation of an updated new vertical datum for Puerto Rico, LIDAR derived elevation, and a combination of visual-manual and automated digitalization processes. The outcomes of this collaborative effort have resulted in improved watershed delineation, densification of hydrologic networks to reflect the scale of on-going studies, and the identification of constraining factors such as unmapped roadways, culverts, and other features of the built environment that interrupt water flow and alter runoff pathways. This work contributes to enhanced knowledge for watershed management, including attributes of riparian areas, effects of road and channel intersections and ridge to reef initiatives with broad application to other watersheds. Full article