Pontifical Catholic University of Paraná (PUCPR), Curitiba, Brazil.
JMIR Med Inform. 2014 Jul 8;2(2):e8. doi: 10.2196/medinform.2984.
Bariatric surgery is an important method for treatment of morbid obesity. It is known that significant nutritional deficiencies might occur after surgery, such as, calorie-protein malnutrition, iron deficiency anemia, and lack of vitamin B12, thiamine, and folic acid.
The objective of our study was to validate a computerized intelligent decision support system that suggests nutritional diagnoses of patients submitted to bariatric surgery.
There were fifteen clinical cases that were developed and sent to three dietitians in order to evaluate and define a nutritional diagnosis. After this step, the cases were sent to four bariatric surgery expert dietitians who were aiming to collaborate on a gold standard. The nutritional diagnosis was to be defined individually, and any disagreements were solved through a consensus. The final result was used as the gold standard. Bayesian networks were used to implement the system, and database training was done with Shell Netica. For the system validation, a similar answer rate was calculated, as well as the specificity and sensibility. Receiver operating characteristic (ROC) curves were projected to each nutritional diagnosis.
Among the four experts, the rate of similar answers found was 80% (48/60) to 93% (56/60), depending on the nutritional diagnosis. The rate of similar answers of the system, compared to the gold standard, was 100% (60/60). The system sensibility and specificity were 95.0%. The ROC curves projection showed that the system was able to represent the expert knowledge (gold standard), and to help them in their daily tasks.
The system that was developed was validated to be used by health care professionals for decision-making support in their nutritional diagnosis of patients submitted to bariatric surgery.
减重手术是治疗病态肥胖的重要方法。众所周知，手术后可能会出现严重的营养缺乏，如热量-蛋白质营养不良、缺铁性贫血以及维生素 B12、硫胺素和叶酸缺乏。
我们的研究目的是验证一种计算机智能决策支持系统，该系统可对接受减重手术的患者进行营养诊断。
我们开发了 15 个临床病例，并将其发送给 3 位营养师进行评估和定义营养诊断。在这一步之后，这些病例被发送给 4 位减重手术专家营养师，旨在制定一个黄金标准。营养师将单独定义营养诊断，任何分歧都将通过共识解决。最终结果将作为黄金标准。我们使用贝叶斯网络来实现该系统，并使用 Shell Netica 进行数据库培训。为了验证系统，我们计算了类似答案的比例，以及特异性和敏感性。为每个营养诊断绘制了接收者操作特征（ROC）曲线。
在这 4 位专家中，根据营养诊断，相似答案的比例为 80%（48/60）到 93%（56/60）。与黄金标准相比，系统的相似答案率为 100%（60/60）。系统的敏感性和特异性均为 95.0%。ROC 曲线的绘制表明，该系统能够代表专家知识（黄金标准），并帮助他们完成日常任务。
我们开发的系统已被验证可用于医疗保健专业人员在为接受减重手术的患者进行营养诊断时进行决策支持。
