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:

Contents of this Issue


Page 16 of 24

16 Original Research Bariatric Times • December 2017 included comorbidities. Because the last two surgeries did not retain data o n patient comorbidities, only data from surgery types 1 to 6 were applied. Similar to the first model, a binary output of whether the patient lost more than 35 percent of their body w eight after one year or not was predicted using 63.4 percent of the data. The model was independently tested on the remaining portion of the data not applied for model d evelopment. The third neural network used pre- operative inputs of surgery types 1 to 8, age, height, weight, BMI, and sex, combined with data that identifying w hether the patient came in for a clinical visit within one month (<31 days). If the patient did come in before 31 days, then input data of short-term weight loss and percent weight loss w ere also included as inputs. A binary output of whether the patient lost more than 35 percent of their body weight after one year or not was predicted using 68.6 percent of the d ata and independently tested on the remaining data. Finally, a fourth neural network applied inputs of pre-operative measurements, comorbidities, and short-term visit information as in the third model. A binary output of whether the patient lost more than 35 percent of their body weight after one year or not was predicted using 63.4 percent of the data and independently tested on the remaining data. Neural networks that predict long- term percent weight loss. Four additional neural network models were trained to predict weight (kg) after one-year, weight loss (kg), day of long- term weight loss visit, and percent weight loss as continuous variables using the same input neurons as in neural networks one through four, described above. Description of input and output neurons for each of the eight neural networks appear in Table 2. RESULTS The summary of neural network quality and rank order of predictor variable importance appears in Table 3. Neural network classifiers of long-term success. Classification of weight loss success using only pre- operative markers and no information on comorbidities yielded AUCs of 0.77 and 0.78 with pre-operative information only. This means that with only pre-operative demographic, anthropometric, and comorbidity information alone, the neural networks can correctly identify which patients will result in successful weight loss over a year from surgery with 78 percent accuracy. If whether patients attended a clinical visit within the first month after surgery and if available weight loss information is included, the AUC improves to 0.82. Neural network prediction of long-term weight. The best predicted long-term output neuron was long-term weight. The Pearson Correlation C onstant ranged between 0.68 to 0.72 with one exception for the case where all pre-operative and short-term inputs were considered. In this case, the R 2 lowered to 0.47. DISCUSSION Using a carefully documented clinical database of patients undergoing eight different surgeries, we d emonstrate that application of a neural network substantially improves the capacity to predict long-term success and weight loss from pre- operative variables that are routinely o btained in clinical settings with classification of success at close to 80 percent accuracy, with 70 percent of the variance explained by the neural network. Including variables obtained i n less than one month adds to the accuracy of predictions. Because surgery type was ranked high in importance, these results suggest that pairing patients pre-operatively with o ptimal type of surgery can improve long-term outcomes. To date, pre-operatively predicting long-term success in bariatric surgery patients using standard regression has remained elusive. 34 Despite knowledge of pre-operative variables that contribute to long-term success, only a small percentage of the variance (R 2 =0.14) can be explained by these covariates. Machine-learning algorithms, like the one presented here, are designed to amplify predictions, and our analysis strongly supports this conclusion. The study's strengths involve application of real clinical data collected over a period of several years with surgeries performed by several surgeons. The results using this database bring confidence to the idea that models can inform surgical decisions in clinical practices. While our study provides preliminary evidence of improved predictions, it has several limitations. The strength of applying real clinical data also represents limitations. Unlike federally funded clinical studies, which are carefully pre-planned and designed to retain subjects and obtain measurements at specified times, 34 data housed in a clinical setting can be complex and unrefined. For example, a sizable number of patients do not return for a follow-up visit. Moreover, even if a patient attends a follow-up visit, they might not return in the first month or post-one year after surgery. Patients might come in for a follow up for the first time at 200 days and never return. The problem of nonadherence to follow up or persistence is well- known 35 and contributes to the challenge of developing informative models. These and other difficulties can provide unique challenges in cleaning databases and preparing them for model development. In fact, the deviation of one neural network's TABLE 3. The quality of predictions and rank order of variable inportance for each neural network NEURAL NETWORK QUALITY OF PREDICTION STATISTICS VARIABLE RANKING OF NORMALIZED IMPORTANCE 1 Percent correctly classified: Training= 70.4% Testing= 77.6% AUC= 0.78 Height (cm) Surgery type BMI (kg/m 2 ) Sex Weight (kg) Age (years) 2 Percent correct: Training= 73.4% Testing= 75.7% AUC= 0.77 Age (years) BMI (kg/m 2 ) Height (cm) Weight (cm) T2DM Surgery type Sex GERD S A HTN 3 Percent correctly classified: Training= 69.5% Testing= 74.1% AUC= 0.68 Short-term weight lost (kg) S hort-term day visit Height (cm) Surgery type Age Came in short term Short-term percent weight lost BMI (kg/m 2 ) Weight (kg) S ex 4 Percent correctly classified: Training= 82.4% Testing= 76.0% AUC= 0.82 Height (cm) Short-term day visit Short-term percent weight lost BMI (kg/m 2 ) Surgery type S A Short-term weight lost (kg) HTN T2DM Sex Short-term weight (kg) Weight (kg) Age GERD Came in short term 5 Percent error: Training= 27.8% Testing= 38.3% R 2 = 0.68 BMI (kg/m 2 ) Height (cm) Surgery type Age Weight (kg) Sex 6 Percent error: Training= 21.4% Testing= 51.4% R 2 = 0.72 Weight (kg) BMI (kg/m 2 ) Height (cm) Age Surgery type T2DM HTN SA GERD Sex 7 Percent error: Training= 24.5% Testing= 40.0% R 2 = 0.71 Short-term percent weight lost Weight (kg) Surgery type BMI (kg/m 2 ) Short-term weight lost (kg) Age Short-term weight (kg) Short-term day visit Came in short term Sex 8 Percent error: Training= 57.9% Testing= 48.8% R 2 = 0.47 Weight (kg) Short-term day visit Short-term percent weight lost Age Surgery type Height (cm) BMI (kg/m 2 ) T2DM AUC: area under the curve; BMI: body mass index; T2DM: type 2 diabetes mellitus; GERD: gastroesophageal reflux disease; SA: sleep apnea; HTN: hypertension

Articles in this issue

Archives of this issue

view archives of Bariatric Times - DEC 2017