Background: The overlap between probable migraine (PM) and probable tension-type headache (PTTH) often confuses physicians in clinical practice. Although clinical decision support systems (CDSSs) have been proven to be helpful in the diagnosis of primary headaches, the existing guideline-based headache disorder CDSSs do not perform adequately due to this overlapping issue. Thus, in this study, a CDSS based on case-based reasoning (CBR) was developed in order to solve this problem.Methods: First, a case library consisting of 676 clinical cases, 56.95% of which had been diagnosed with PM and 43.05% of which had been diagnosed with PTTH, was constructed, screened by a three-member panel, and weighted by engineers. Next, the resulting case library was used to diagnose current cases based on their similarities to the previous cases. The test dataset was composed of an additional 222 historical cases, 76.1% of which had been diagnosed with PM and 23.9% of which had been diagnosed with PTTH. The cases that comprised the case library as well as the test dataset were actual clinical cases obtained from the International Headache Center in Chinese PLA General Hospital.Results: The results indicated that the PM and PTTH recall rates were equal to 97.02% and 77.78%, which were 34.31% and 16.91% higher than that of the guideline-based CDSS, respectively. Furthermore, the PM and PTTH precision rates were equal to 93.14% and 89.36%, which were7.09% and 15.68% higher than that of the guideline-based CDSS, respectively. Comparing CBR CDSS and guideline-based CDSS, the p-value of PM diagnoses was equal to 0.019, while that of PTTH diagnoses was equal to 0.002, which indicated that there was a significant difference between the two approaches.Conclusions: The experimental results indicated that the CBR CDSS developed in this study diagnosed PM and PTTH with a high degree of accuracy and performed better than the guideline-based CDSS. This system could be used as a diagnostic tool to assist general practitioners in distinguishing PM from PTTH.

Background: China may have the largest population of headache sufferers and therefore the most serious burden of disease worldwide. However, the rate of diagnosis for headache disorders is extremely low, possibly due to the relative complexity of headache subtypes and diagnostic criteria. The use of computerized clinical decision support systems (CDSS) seems to be a better choice to solve this problem. Methods: We developed a headache CDSS based on ICHD-3 beta and validated it in a prospective study that included 543 headache patients from the International Headache Center at the Chinese PLA General hospital, Beijing, China. Results: We found that the CDSS correctly recognized 159/160 (99.4%) of migraine without aura, 36/36 (100%) of migraine with aura, 20/21 (95.2%) of chronic migraine, and 37/59 (62.7%) of probable migraine. This system also correctly identified 157/180 (87.2%) of patients with tension-type headache (TTH), of which infrequent episodic TTH was diagnosed in 12/13 (92.3%), frequent episodic TTH was diagnosed in 99/101 (98.0%), chronic TTH in 18/20 (90.0%), and probable TTH in 28/46 (60.9%). The correct diagnostic rates of cluster headache and new daily persistent headache (NDPH) were 90.0% and 100%, respectively. In addition, the system recognized 32/32 (100%) of patients with medication overuse headache. Conclusions: With high diagnostic accuracy for most of the primary and some types of secondary headaches, this system can be expected to help general practitioners at primary hospitals improve diagnostic accuracy and thereby reduce the burden of headache in China.

Early recognition of abnormal gait enables physicians to determine a prompt rehabilitation plan for patients for the most effective treatment and care. The Kinect depth sensor can easily collect skeleton data describing the position of joints in the human body. However, the default human skeleton model of Kinect includes an excessive number of many joints, which limits the accuracy of the gait recognition methods and increases the computational resources required. In this study, we propose an optimized human skeleton model for the Kinect system and streamline the joints using a center-of-mass calculation. We integrate several techniques to propose an end-to-end, spatial–temporal, joint attention graph convolutional network (STJA-GCN) architecture. We conducted experiments with a fivefold cross-validation on two common datasets of information on abnormal gaits to evaluate the performance of the proposed method. The results show that the STJA-GCN achieved 93.17 and 92.08% accuracy on the two datasets, and compared to the original spatial–temporal graph convolutional network (ST-GCN), the recognition accuracy increases by 9.22 and 20.65%, respectively. Overall, the results demonstrate that the STJA-GCN can accurately recognize abnormal gaits and, thus, can support low-cost rehabilitation assessments at community hospitals or in patients’ homes.

Background Gallbladder cancer is the sixth most common malignant gastrointestinal tumor. Radical surgery is currently the only effective treatment, but patient prognosis is poor, with a 5-year survival rate of only 5–10%. Establishing an effective survival prediction model for gallbladder cancer patients is crucial for disease status assessment, early intervention, and individualized treatment approaches. The existing gallbladder cancer survival prediction model uses clinical data—radiotherapy and chemotherapy, pathology, and surgical scope—but fails to utilize laboratory examination and imaging data, limiting its prediction accuracy and preventing sufficient treatment plan guidance. Aims The aim of this work is to propose an accurate survival prediction model, based on the deep learning 3D-DenseNet network, integrated with multimodal medical data (enhanced CT imaging, laboratory test results, and data regarding systemic treatments). Methods Data were collected from 195 gallbladder cancer patients at two large tertiary hospitals in Shanghai. The 3D-DenseNet network extracted deep imaging features and constructed prognostic factors, from which a multimodal survival prediction model was established, based on the Cox regression model and incorporating patients’ laboratory test and systemic treatment data. Results The model had a C-index of 0.787 in predicting patients’ survival rate. Moreover, the area under the curve (AUC) of predicting patients’ 1-, 3-, and 5-year survival rates reached 0.827, 0.865, and 0.926, respectively. Conclusions Compared with the monomodal model based on deep imaging features and the tumor–node–metastasis (TNM) staging system—widely used in clinical practice—our model’s prediction accuracy was greatly improved, aiding the prognostic assessment of gallbladder cancer patients.

Background: Tinnitus diagnosis poses a challenge in otolaryngology owing to an extremely complex pathogenesis, lack of effective objectification methods, and factor-affected diagnosis. There is currently a lack of explainable auxiliary diagnostic tools for tinnitus in clinical practice. Objective: This study aims to develop a diagnostic model using an explainable artificial intelligence (AI) method to address the issue of low accuracy in tinnitus diagnosis. Methods: In this study, a knowledge graph–based tinnitus diagnostic method was developed by combining clinical medical knowledge with electronic medical records. Electronic medical record data from 1267 patients were integrated with traditional Chinese clinical medical knowledge to construct a tinnitus knowledge graph. Subsequently, weights were introduced, which measured patient similarity in the knowledge graph based on mutual information values. Finally, a collaborative neighbor algorithm was proposed, which scored patient similarity to obtain the recommended diagnosis. We conducted 2 group experiments and 1 case derivation to explore the effectiveness of our models and compared the models with state-of-the-art graph algorithms and other explainable machine learning models. Results: The experimental results indicate that the method achieved 99.4% accuracy, 98.5% sensitivity, 99.6% specificity, 98.7% precision, 98.6% F1-score, and 99% area under the receiver operating characteristic curve for the inference of 5 tinnitus subtypes among 253 test patients. Additionally, it demonstrated good interpretability. The topological structure of knowledge graphs provides transparency that can explain the reasons for the similarity between patients. Conclusions: This method provides doctors with a reliable and explainable diagnostic tool that is expected to improve tinnitus diagnosis accuracy.

Neuropsychological testing is an effective means for the screening of Alzheimer’s disease. Multiple neuropsychological rating scales should be used together to get subjects’ comprehensive cognitive state due to the limitation of a single scale, but it is difficult to operate in primary clinical settings because of the inadequacy of time and qualified clinicians. Aiming at identifying AD’s stages more accurately and conveniently in screening, we proposed a computer-aided diagnosis approach based on critical items extracted from multiple neuropsychological scales. The proposed hybrid intelligent approach combines the strengths of rough sets, genetic algorithm, and Bayesian network. There are two stages: one is attributes reduction technique based on rough sets and genetic algorithm, which can find out the most discriminative items for AD diagnosis in scales; the other is uncertain reasoning technique based on Bayesian network, which can forecast the probability of suffering from AD. The experimental data set consists of 500 cases collected by a top hospital in China and each case is determined by the expert panel. The results showed that the proposed approach could not only reduce items drastically with the same classification precision, but also perform better on identifying different stages of AD comparing with other existing scales.