Diagnosis of Cognitive Impairment Compatible with Early Diagnosis of Alzheimer's Disease. A Bayesian Network Model based on the Analysis of Oral Definitions of Semantic Categories

Medical informed machine learning: A scoping review and future research directions

Combining domain knowledge (DK) and machine learning is a recent research stream to overcome multiple issues like limited explainability, lack of data, and insufficient robustness. Most approaches applying informed machine learning (IML), however, are customized to solve one specific problem. This study analyzes the status of IML in medicine by conducting a scoping literature review based on an existing taxonomy. We identified 177 papers and analyzed them regarding the used DK, the implemented machine learning model, and the motives for performing IML. We find an immense role of expert knowledge and image data in medical IML. We then provide an overview and analysis of recent approaches and supply five directions for future research. This review can help develop future medical IML approaches by easily referencing existing solutions and shaping future research directions.

Differential disease diagnoses of epistaxis based on dynamic uncertain causality graph

PURPOSE

Epistaxis is a common symptom and can be caused by various diseases, including nasal diseases, systemic diseases, etc. Many misdiagnosis and missed diagnosis of epistaxis are caused by lack of clinical knowledge and experience, especially some interns and the clinicans in primary hospitals. To help inexperienced clinicans improve their diagnostic accuracies of epistaxis, a computer-aided diagnostic system based on Dynamic Uncertain Causality Graph (DUCG) was designed in this study.

METHODS

We build a visual epistaxis knowledge base based on medical experts' knowledge and experience. The knowledge base intuitively expresses the causal relationship among diseases, risk factors, symptoms, signs, laboratory checks, and image examinations. The DUCG inference algorithm well addresses the patients' clinical information with the knowledge base to deduce the currently suspected diseases and calculate the probability of each suspected disease.

RESULT

The model can differentially diagnose 24 diseases with epistaxis as the chief complaint. A third-party verification was performed, and the total diagnostic precision was 97.81%. In addition, the DUCG-based diagnostic model was applied in Jiaozhou city and Zhongxian county, China, covering hundreds of primary hospitals and clinics. So far, the clinicians using the model have all agreed with the diagnostic results. The 432 real-world application cases show that this model is good for the differential diagnoses of epistaxis.

CONCLUSION

The results show that the DUCG-based epistaxis diagnosis model has high diagnostic accuracy. It can assist primary clinicians in completing the differential diagnosis of epistaxis and can be accepted by clinicians.

Identifying neurocognitive disorder using vector representation of free conversation

In recent years, studies on the use of natural language processing (NLP) approaches to identify dementia have been reported. Most of these studies used picture description tasks or other similar tasks to encourage spontaneous speech, but the use of free conversation without requiring a task might be easier to perform in a clinical setting. Moreover, free conversation is unlikely to induce a learning effect. Therefore, the purpose of this study was to develop a machine learning model to discriminate subjects with and without dementia by extracting features from unstructured free conversation data using NLP. We recruited patients who visited a specialized outpatient clinic for dementia and healthy volunteers. Participants’ conversation was transcribed and the text data was decomposed from natural sentences into morphemes by performing a morphological analysis using NLP, and then converted into real-valued vectors that were used as features for machine learning. A total of 432 datasets were used, and the resulting machine learning model classified the data for dementia and non-dementia subjects with an accuracy of 0.900, sensitivity of 0.881, and a specificity of 0.916. Using sentence vector information, it was possible to develop a machine-learning algorithm capable of discriminating dementia from non-dementia subjects with a high accuracy based on free conversation.

Short-Term Memory Binding Distinguishing Amnestic Mild Cognitive Impairment from Healthy Aging: A Machine Learning Study

BACKGROUND

Amnestic mild cognitive impairment (aMCI) is the most common preclinical stage of Alzheimer's disease (AD). A strategy to reduce the impact of AD is the early aMCI diagnosis and clinical intervention. Neuroimaging, neurobiological, and genetic markers have proved to be sensitive and specific for the early diagnosis of AD. However, the high cost of these procedures is prohibitive in low-income and middle-income countries (LIMCs). The neuropsychological assessments currently aim to identify cognitive markers that could contribute to the early diagnosis of dementia.

OBJECTIVE

Compare machine learning (ML) architectures classifying and predicting aMCI and asset the contribution of cognitive measures including binding function in distinction and prediction of aMCI.

METHODS

We conducted a two-year follow-up assessment of a sample of 154 subjects with a comprehensive multidomain neuropsychological battery. Statistical analysis was proposed using complete ML architectures to compare subjects' performance to classify and predict aMCI. Additionally, permutation importance and Shapley additive explanations (SHAP) routines were implemented for feature importance selection.

RESULTS

AdaBoost, gradient boosting, and XGBoost had the highest performance with over 80%success classifying aMCI, and decision tree and random forest had the highest performance with over 70%success predictive routines. Feature importance points, the auditory verbal learning test, short-term memory binding tasks, and verbal and category fluency tasks were used as variables with the first grade of importance to distinguish healthy cognition and aMCI.

CONCLUSION

Although neuropsychological measures do not replace biomarkers' utility, it is a relatively sensitive and specific diagnostic tool for aMCI. Further studies with ML must identify cognitive performance that differentiates conversion from average MCI to the pathological MCI observed in AD.

Artificial intelligence and neuropsychological measures: The case of Alzheimer's disease

One of the current challenges in the field of Alzheimer's disease (AD) is to identify patients with mild cognitive impairment (MCI) that will convert to AD. Artificial intelligence, in particular machine learning (ML), has established as one of more powerful approach to extract reliable predictors and to automatically classify different AD phenotypes. It is time to accelerate the translation of this knowledge in clinical practice, mainly by using low-cost features originating from the neuropsychological assessment. We performed a meta-analysis to assess the contribution of ML and neuropsychological measures for the automated classification of MCI patients and the prediction of their conversion to AD. The pooled sensitivity and specificity of patients' classifications was obtained by means of a quantitative bivariate random-effect meta-analytic approach. Although a high heterogeneity was observed, the results of meta-analysis show that ML applied to neuropsychological measures can lead to a successful automatic classification, being more specific as screening rather than prognosis tool. Relevant categories of neuropsychological tests can be extracted by ML that maximize the classification accuracy.

Identification of Knee Osteoarthritis Based on Bayesian Network: Pilot Study

Background

Early identification of knee osteoarthritis (OA) can improve treatment outcomes and reduce medical costs. However, there are major limitations among existing classification or prediction models, including abstract data processing and complicated dataset attributes, which hinder their applications in clinical practice.

Objective

The aim of this study was to propose a Bayesian network (BN)–based classification model to classify people with knee OA. The proposed model can be treated as a prescreening tool, which can provide decision support for health professionals.

Methods

The proposed model’s structure was based on a 3-level BN structure and then retrained by the Bayesian Search (BS) learning algorithm. The model’s parameters were determined by the expectation-maximization algorithm. The used dataset included backgrounds, the target disease, and predictors. The performance of the model was evaluated based on classification accuracy, area under the curve (AUC), specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV); it was also compared with other well-known classification models. A test was also performed to explore whether physical fitness tests could improve the performance of the proposed model.

Results

A total of 249 elderly people between the ages of 60 and 80 years, living in the Kongjiang community (Shanghai), were recruited from April to September 2007. A total of 157 instances were adopted as the dataset after data preprocessing. The experimental results showed that the results of the proposed model were higher than, or equal to, the mean scores of other classification models: .754 for accuracy, .78 for AUC, .78 for specificity, and .73 for sensitivity. The proposed model provided .45 for PPV and .92 for NPV at the prevalence of 20%. The proposed model also showed a significant improvement when compared with the traditional BN model: 6.3% increase in accuracy (from .709 to .754), 4.0% increase in AUC (from .75 to .78), 6.8% increase in specificity (from .73 to .78), 5.8% increase in sensitivity (from .69 to .73), 15.4% increase in PPV (from .39 to .45), and 2.2% increase in NPV (from .90 to .92). Furthermore, the test results showed that the performance of the proposed model could be largely enhanced through physical fitness tests in 3 evaluation indices: 10.6% increase in accuracy (from .682 to .754), 16.4% increase in AUC (from .67 to .78), and 30.0% increase in specificity (from .60 to .78).

Conclusions

The proposed model presents a promising method to classify people with knee OA when compared with other classification models and the traditional BN model. It could be implemented in clinical practice as a prescreening tool for knee OA, which would not only improve the quality of health care for elderly people but also reduce overall medical costs.

A hybrid computational approach for efficient Alzheimer's disease classification based on heterogeneous data

There is currently a lack of an efficient, objective and systemic approach towards the classification of Alzheimer's disease (AD), due to its complex etiology and pathogenesis. As AD is inherently dynamic, it is also not clear how the relationships among AD indicators vary over time. To address these issues, we propose a hybrid computational approach for AD classification and evaluate it on the heterogeneous longitudinal AIBL dataset. Specifically, using clinical dementia rating as an index of AD severity, the most important indicators (mini-mental state examination, logical memory recall, grey matter and cerebrospinal volumes from MRI and active voxels from PiB-PET brain scans, ApoE, and age) can be automatically identified from parallel data mining algorithms. In this work, Bayesian network modelling across different time points is used to identify and visualize time-varying relationships among the significant features, and importantly, in an efficient way using only coarse-grained data. Crucially, our approach suggests key data features and their appropriate combinations that are relevant for AD severity classification with high accuracy. Overall, our study provides insights into AD developments and demonstrates the potential of our approach in supporting efficient AD diagnosis.

The Dissociation between Polarity, Semantic Orientation, and Emotional Tone as an Early Indicator of Cognitive Impairment

The present study aims to identify early cognitive impairment through the efficient use of therapies that can improve the quality of daily life and prevent disease progress. We propose a methodology based on the hypothesis that the dissociation between oral semantic expression and the physical expressions, facial gestures, or emotions transmitted in a person's tone of voice is a possible indicator of cognitive impairment. Experiments were carried out with phrases, analyzing the semantics of the message, and the tone of the voice of patients through unstructured interviews in healthy people and patients at an early Alzheimer's stage. The results show that the dissociation in cognitive impairment was an effective indicator, arising from patterns of inconsistency between the analyzed elements. Although the results of our study are encouraging, we believe that further studies are necessary to confirm that this dissociation is a probable indicator of cognitive impairment.