Bariatric Times

DEC 2017

A peer-reviewed, evidence-based journal that promotes clinical development and metabolic insights in total bariatric patient care for the healthcare professional

Issue link: http://bariatrictimes.epubxp.com/i/917574

Contents of this Issue

Navigation

Page 15 of 24

15 Original Research Bariatric Times • December 2017 with one half going up and the other half being reconnected further down. T his restricts the amount a patient can eat and reduces fat intake through malabsorption. Gastric bypass to duodenal switch included any gastric bypass surgery t hat failed and was revised by a second surgery. Band to duodenal switch included any band surgery that failed and was revised by a second surgery. " Bandication," or laparoscopic adjustable gastric banding with gastric plication, represents a technique combining the volume reduction of the plication with the restriction of the b and to enhance the weight loss Band or laparoscopic adjustable gastric banding relies on an implanted silicone band around the upper stomach to constrict the amount of f ood a patient eats. Neural networks. Overview of neural networks. A neural network is a mathematical representation of the human brain and falls under the c ategory of artificial intelligence. Neural networks have the capacity to "learn" like the human brain. The neural network is modeled as a series of neurons, which are organized in layers. Each neuron in one layer is connected to neurons by values called weights. The weight values describe the direction and strength of the connection between neurons. An input neuron represents information that is presented to the neural network. It is similar to our brains receiving information from our senses. An output neuron represents a prediction made after synthesis within the neural network. This is similar to how our brain makes a conclusion after receiving information from our senses. Neural network development. Neural networks first train, or learn by fitting the values of the weight after being fed input data. Once the data has been used to train the neural network, the neural network is presented with new data that was not used to train the network with and the predictions of the neural network are compared to the actual data in the new data set. The quality of the neural network is evaluated by its performance on the training data set. Eight neural networks were trained and tested using the statistical package SPSS v21 (IBM Corp, Armonk, New York). The training set and testing set data were randomly selected by the statistical package to approximately reflect 70 percent of the data for training the neural network and 30 percent of the data for testing. Neural networks can predict binary outcomes, such as success versus failure. Success needs to be defined beforehand, for example, "exceeding a threshold percent weight lost." The coarsening of outcome as a classification improves predictive accuracy, and combined with the amplification yielded by a neural network versus standard regression should result in an increase of accuracy previously reported. On the other hand, neural networks can also predict a continuous variable like weight at the first clinical weigh in one-year post surgery. Four neural networks were trained to predict long-term weight, day of long-term clinical weigh-in, weight loss, and percent weight loss. In the neural networks where predictions were classified as success versus non-success, receiver operating characteristic curves were generated, and the AUC was computed. Values of AUC closer to 1 indicate improved performance of the neural network as a diagnostic tool that classifies long-term success. The percent correctly classified in both the training and testing set were also calculated. For neural networks predicting continuous variables of long-term weight, day of long-term clinical weigh in, weight loss, and percent weight loss, the Pearson Correlation Constant was calculated for the actual versus predicted on the test data set. The mean relative percent error was computed for both the training and testing datasets. Relative error is calculated as the ratio of continuous outcomes that were inaccurately predicted over total predictions. Percent error is the relative error multiplied by 100. Lower values of percent error represent more accurate predictions. All neural network outputs included a rank ordering of input variable importance contributing to the predictions. Neural networks that classify long-term weight loss success. The first neural network relied on solely pre-operative inputs of surgery types 1 to 8, age, height, weight, BMI, and sex. A binary output of whether the patient lost more than 35 percent of their body weight after one year or not was predicted using 71.8 percent of the data. The model was independently tested on 28.2 percent of the data, which was not used for model development. The second neural network again relied solely on pre-operative measurements, but additionally TABLE 1. Patient characteristics S URGERY TYPE (N) B ODY MASS INDEX (kg/m 2 ) A GE (YEARS) % WEIGHT LOSS (1 YEAR) 1-YEAR CLINICAL VISIT (DAYS AFTER SURGERY) Loop duodenal switch (28) 47.37±9.68 52.18±13.52 34.80±11.64 416.64±43.35 Regular duodenal switch (26) 52.28±8.63 52.46±10.86 44.53±8.24 422.54±72.31 Sleeve (20) 42.49±6.46 45.95±11.30 33.41±12.87 425.60±118.89 Gastric bypass (17) 46.04±9.55 46.00±15.64 44.39±9.25 447.76±113.77 Gastric bypass to duodenal s witch (6) 52.93±13.60 52.33±11.98 42.60±9.18 399.33±98.43 Band to duodenal switch (4) 54.20±20.55 42.75±14.38 43.50±7.35 381.25±44.93 Bandication (36) 41.69±6.07 50.61±12.93 32.41±14.59 638.86±274.98 Band (37) 44.34±8.62 48.73±12.87 56.52±25.12 663.81±303.67 Total 56.81±32.34 49.63±12.85 41.63±17.81 512.47±234.64 TABLE 2. Neural network input/output nerons and training/testing set descriptions N EURAL NETWORK I NPUT NEURONS O UTPUT NEURON T RAINING N (%) T ESTING N (%) 1. Pre-operative Surgery types 1 to 8, age, height, weight, BMI, sex Classified Successful N = 125 (71.8%) N= 49 (28.2%) 2. Pre-operative Surgery types 1 to 6, age, height, weight, BMI, sex, comorbidities Classified Successful N= 64 (63.4%) N= 37 (36.6%) 3. Pre-operative and s hort-term Surgery types 1 to 8, age, height, weight, BMI, sex, came in for short-term visit, short-term weight lost (kg), p ercent short-term weight lost, short-term weight gain (kg) Classified Successful N= 118 ( 68.6%) N= 54 (31.4%) 4. Pre-operative and short-term Surgery types 1 to 6, age, height, weight, BMI, sex, comorbidities, came in for short-term visit, day of short- term visit, short-term weight lost (kg), percent short- term weight lost, short-term weight (kg) Classified Successful N= 74 (74.7%) N= 25 (25.3%) 5. Pre-operative Surgery types 1 to 8, age, height, weight, BMI, sex Long-term weight (kg), weight lost (kg), day of long-term visit, percent weight lost N= 111 (63.8%) N= 63 (36.2%) 6. Pre-operative Surgery types 1 to 6, age, height, weight, BMI, sex, comorbidities Long-term weight gain (kg), weight lost (kg), day of long-term visit, percent weight lost N= 111 (63.8%) N= 63 (36.2%) 7. Pre-operative and short-term Surgery types 1 to 8, age, height, weight, BMI, sex, came in for short-term visit, day of short-term visit, short-term weight lost (kg), percent short-term weight lost, short-term weight (kg) Long-term weight (kg), weight lost (kg), day of long-term visit, percent weight lost N= 117 (68.0%) N= 55 (32.0%) 8. Pre-operative and short-term Surgery types 1 to 6, age, height, weight, body mass index, gender, comorbidities, came in for short-term visit, day of short-term visit, short-term weight lost (kg), percent short-term weight lost, short-term weight (kg) Long-term weight (kg), weight lost (kg), day of long-term visit, percent weight lost N= 74 (74.7%) N= 25 (25.3%) BMI: body mass index

Articles in this issue

Archives of this issue

view archives of Bariatric Times - DEC 2017