> Detailanzeige

Yin, Ping; Wang, Hongli

Evaluation of Nursing Effect of Pelvic Floor Rehabilitation Training on Pelvic Organ Prolapse in Postpartum Pregnant Women under Ultrasound Imaging with Artificial Intelligence Algorithm

Literatur-
verwaltung

Zur
Merkliste

Lösche von
Merkliste

Per Whatsapp teilen

Schließen

Merkliste



Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
  • Medientyp: E-Artikel
  • Titel: Evaluation of Nursing Effect of Pelvic Floor Rehabilitation Training on Pelvic Organ Prolapse in Postpartum Pregnant Women under Ultrasound Imaging with Artificial Intelligence Algorithm
  • Beteiligte: Yin, Ping; Wang, Hongli
  • Erschienen: Hindawi Limited, 2022
  • Erschienen in: Computational and Mathematical Methods in Medicine
  • Sprache: Englisch
  • DOI: 10.1155/2022/1786994
  • ISSN: 1748-6718; 1748-670X
  • Schlagwörter: Applied Mathematics ; General Immunology and Microbiology ; General Biochemistry, Genetics and Molecular Biology ; Modeling and Simulation ; General Medicine
  • Entstehung:
  • Anmerkungen:
  • Beschreibung: <jats:p>This study was aimed at exploring the application value of ultrasound technology and rehabilitation training based on artificial intelligence algorithm in postpartum recovery of pelvic organ prolapse. Sixty patients diagnosed as mild and moderate pelvic organ prolapse by pelvic organ prolapse quantification evaluation were selected as the research objects. The patients were randomly divided into experimental group (30 cases) and control group (30 cases). The patients in the control group were given routine guidance and postpartum health education 42 days after delivery and given no pelvic floor rehabilitation training, waiting for natural recovery. 42 days after delivery, the patients in the experimental group received pelvic floor rehabilitation training based on the patients in the control group. All patients underwent ultrasonography, the convolution neural network (CNN) algorithm was used for image denoising and edge feature extraction, and the performance of the algorithm was evaluated by the Dice coefficient, positive predictive value, sensitivity, and Hausdorff distance. The thickness of levator ani muscle, anterior and posterior diameter of perineal hiatus, pelvic floor muscle strength, and imaging data were compared between the two groups. The results revealed that the thickness of levator ani muscle in the experimental group was significantly greater than that in the control group after one month and three months of treatment (<jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M1"> <mn>0.633</mn> <mo>±</mo> <mn>0.26</mn> </math> </jats:inline-formula> cm vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M2"> <mn>0.519</mn> <mo>±</mo> <mn>0.234</mn> </math> </jats:inline-formula> cm, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M3"> <mn>0.7</mn> <mo>±</mo> <mn>0.214</mn> </math> </jats:inline-formula> cm vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M4"> <mn>0.507</mn> <mo>±</mo> <mn>0.168</mn> </math> </jats:inline-formula> cm, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M5"> <mi>P</mi> <mo>&lt;</mo> <mn>0.05</mn> </math> </jats:inline-formula>). After one month and three months of treatment, the anterior and posterior diameter of perineal fissure in the experimental group was obviously smaller than that in the control group (<jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M6"> <mn>4.76</mn> <mo>±</mo> <mn>0.513</mn> </math> </jats:inline-formula> cm vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M7"> <mn>5.002</mn> <mo>±</mo> <mn>0.763</mn> </math> </jats:inline-formula> cm, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M8"> <mn>4.735</mn> <mo>±</mo> <mn>0.614</mn> </math> </jats:inline-formula> cm vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M9"> <mn>4.987</mn> <mo>±</mo> <mn>0.581</mn> </math> </jats:inline-formula> cm, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M10"> <mi>P</mi> <mo>&lt;</mo> <mn>0.05</mn> </math> </jats:inline-formula>). The pelvic floor muscle strength of the experimental group was remarkably higher than that of the control group after one month and three months of treatment (<jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M11"> <mn>3.183</mn> <mo>±</mo> <mn>1.47</mn> </math> </jats:inline-formula> vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M12"> <mn>2.41</mn> <mo>±</mo> <mn>1.57</mn> </math> </jats:inline-formula>, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M13"> <mn>3.365</mn> <mo>±</mo> <mn>1.53</mn> </math> </jats:inline-formula> vs. <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M14"> <mn>2.865</mn> <mo>±</mo> <mn>1.69</mn> </math> </jats:inline-formula>, <jats:inline-formula> <math xmlns="http://www.w3.org/1998/Math/MathML" id="M15"> <mi>P</mi> <mo>&lt;</mo> <mn>0.05</mn> </math> </jats:inline-formula>). The ultrasonic image was clearer, the focus was more prominent, and the image quality was significantly improved after being processed by artificial intelligence algorithm. The Dice coefficient, positive predictive value, sensitivity, and Hausdorff distance of the proposed algorithm were better than those of the traditional algorithm. Thus, artificial intelligence algorithm had a good effect in ultrasonic image processing. Pelvic floor rehabilitation training had a good effect on postpartum nursing of patients with pelvic organ prolapse.</jats:p>
  • Zugangsstatus: Freier Zugang