Browsing by Author "Rao, Satish S. C."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Predicting Response to Neuromodulators or Prokinetics in Patients With Suspected Gastroparesis Using Machine Learning: The "BMI, Infectious Prodrome, Delayed GES, and No Diabetes" Model
    (Wolters Kluwer, 2024-09-01) Takakura, Will; Surjanhata, Brian; Nguyen, Linda Anh Bui; Parkman, Henry P.; Rao, Satish S. C.; McCallum, Richard W.; Schulman, Michael; Wo, John Man-Ho; Sarosiek, Irene; Moshiree, Baha; Kuo, Braden; Hasler, William L.; Lee, Allen A.; Medicine, School of Medicine
    Introduction: Pharmacologic therapies for symptoms of gastroparesis (GP) have limited efficacy, and it is difficult to predict which patients will respond. In this study, we implemented a machine learning model to predict the response to prokinetics and/or neuromodulators in patients with GP-like symptoms. Methods: Subjects with suspected GP underwent simultaneous gastric emptying scintigraphy (GES) and wireless motility capsule and were followed for 6 months. Subjects were included if they were started on neuromodulators and/or prokinetics. Subjects were considered responders if their GP Cardinal Symptom Index at 6 months decreased by ≥1 from baseline. A machine learning model was trained using lasso regression, ridge regression, or random forest. Five-fold cross-validation was used to train the models, and the area under the receiver operator characteristic curve (AUC-ROC) was calculated using the test set. Results: Of the 150 patients enrolled, 123 patients received either a prokinetic and/or a neuromodulator. Of the 123, 45 were considered responders and 78 were nonresponders. A ridge regression model with the variables, such as body mass index, infectious prodrome, delayed gastric emptying scintigraphy, no diabetes, had the highest AUC-ROC of 0.72. The model performed well for subjects on prokinetics without neuromodulators (AUC-ROC of 0.83) but poorly for those on neuromodulators without prokinetics. A separate model with gastric emptying time, duodenal motility index, no diabetes, and functional dyspepsia performed better (AUC-ROC of 0.75). Discussion: This machine learning model has an acceptable accuracy in predicting those who will respond to neuromodulators and/or prokinetics. If validated, our model provides valuable data in predicting treatment outcomes in patients with GP-like symptoms.
  • Thumbnail Image
    Item
    Surgical Interventions and the Use of Device-Aided Therapy for the Treatment of Fecal Incontinence and Defecatory Disorders
    (Elsevier, 2017) Bharucha, Adil E.; Rao, Satish S. C.; Shin, Andrea; Department of Medicine, School of Medicine
    The purpose of this clinical practice update expert review is to describe the key principles in the use of surgical interventions and device-aided therapy for managing fecal incontinence (FI) and defecatory disorders. The best practices outlined in this review are based on relevant publications, including systematic reviews and expert opinion (when applicable). Best Practice Advice 1: A stepwise approach should be followed for management of FI. Conservative therapies (diet, fluids, techniques to improve evacuation, a bowel training program, management of diarrhea and constipation with diet and medications if necessary) will benefit approximately 25% of patients and should be tried first. Best Practice Advice 2: Pelvic floor retraining with biofeedback therapy is recommended for patients with FI who do not respond to the conservative measures indicated above. Best Practice Advice 3: Perianal bulking agents such as intra-anal injection of dextranomer may be considered when conservative measures and biofeedback therapy fail. Best Practice Advice 4: Sacral nerve stimulation should be considered for patients with moderate or severe FI in whom symptoms have not responded after a 3-month or longer trial of conservative measures and biofeedback therapy and who do not have contraindications to these procedures. Best Practice Advice 5: Until further evidence is available, percutaneous tibial nerve stimulation should not be used for managing FI in clinical practice. Best Practice Advice 6: Barrier devices should be offered to patients who have failed conservative or surgical therapy, or in those who have failed conservative therapy who do not want or are not eligible for more invasive interventions. Best Practice Advice 7: Anal sphincter repair (sphincteroplasty) should be considered in postpartum women with FI and in patients with recent sphincter injuries. In patients who present later with symptoms of FI unresponsive to conservative and biofeedback therapy and evidence of sphincter damage, sphincteroplasty may be considered when perianal bulking injection and sacral nerve stimulation are not available or have proven unsuccessful. Best Practice Advice 8: The artificial anal sphincter, dynamic graciloplasty, may be considered for patients with medically refractory severe FI who have failed treatment or are not candidates for barrier devices, sacral nerve stimulation, perianal bulking injection, sphincteroplasty and a colostomy. Best Practice Advice 9: Major anatomic defects (eg, rectovaginal fistula, full-thickness rectal prolapse, fistula in ano, or cloaca-like deformity) should be rectified with surgery. Best Practice Advice 10: A colostomy should be considered in patients with severe FI who have failed conservative treatment and have failed or are not candidates for barrier devices, minimally invasive surgical interventions, and sphincteroplasty. Best Practice Advice 11: A magnetic anal sphincter device may be considered for patients with medically refractory severe FI who have failed or are not candidates for barrier devices, perianal bulking injection, sacral nerve stimulation, sphincteroplasty, or a colostomy. Data regarding efficacy are limited and 40% of patients had moderate or severe complications. Best Practice Advice 12: For defecatory disorders, biofeedback therapy is the treatment of choice. Best Practice Advice 13: Based on limited evidence, sacral nerve stimulation should not be used for managing defecatory disorders in clinical practice. Best Practice Advice 14: Anterograde colonic enemas are not effective in the long term for management of defecatory disorders. Best Practice Advice 15: The stapled transanal rectal resection and related procedures should not be routinely performed for correction of structural abnormalities in patients with defecatory disorders.