Background

Considering the clinical heterogeneity of the bipolar disorder, difficulties are encountered in making the correct diagnosis. Although a number of common findings have been found in studies on the neurocognitive profile of bipolar disorder, the search for a neurocognitive endophenotype has failed. The aim of this study is to separate bipolar disorder patients from healthy controls with higher accuracy by using a broader neurocognitive evaluation and a novel machine-learning algorithm.

Methods

Individuals who presented to the Bipolar Outpatient Clinic of the Medical Faculty of Eskişehir Osmangazi University and met the inclusion criteria of the research are included in the study. Six neurocognitive tests from the CANTAB test battery were used for neurocognitive evaluation, Polyhedral Conic Functions algorithm was used to classify the participants.

Results

Bipolar disorder patients differentiated from healthy controls with an accuracy of 78 %.

Discussion

Our study presents a prediction algorithm that separates bipolar disorder from healthy controls with high accuracy by using CANTAB neurocognitive battery.

中文翻译：

---

认知功能在双相情感障碍诊断中的作用：机器学习模型

背景

考虑到双相情感障碍的临床异质性，在做出正确诊断时会遇到困难。尽管在关于躁郁症的神经认知特征的研究中发现了许多常见的发现，但是寻找神经认知内表型的研究却失败了。这项研究的目的是通过使用更广泛的神经认知评估和新颖的机器学习算法，以更高的准确性将双相情感障碍患者与健康对照区分开。

方法

参加了埃斯基谢希尔·奥斯曼加齐大学医学院双极门诊诊所并符合研究纳入标准的个体。来自CANTAB测试电池的六种神经认知测试用于神经认知评估，多面圆锥函数函数用于对参与者进行分类。

结果

双相情感障碍患者与健康对照组的区别为78％。

讨论区

我们的研究提出了一种预测算法，可以通过使用CANTAB神经认知电池以高准确度将双相情感障碍与健康对照区分开。