Predicting Alzheimer's Disease from Spoken and Written Language Using Fusion-Based Stacked Generalization

A machine learning stacking model accurately estimating gastric fluid volume in patients undergoing elective sedated gastrointestinal endoscopy

BACKGROUND

The current point-of-care ultrasound (POCUS) assessment of gastric fluid volume primarily relies on the traditional linear approach, which often suffers from moderate accuracy. This study aimed to develop an advanced machine learning (ML) model to estimate gastric fluid volume more accurately.

METHODS

We retrospectively analyzed the clinical data and POCUS data (D1: craniocaudal diameter, D2: anteroposterior diameter) of 1386 patients undergoing elective sedated gastrointestinal endoscopy (GIE) at Nanjing First Hospital to predict gastric fluid volume using ML techniques, including six different ML models and a stacking model. We evaluated the models using the adjusted Coefficient of Determination (R2), mean absolute error (MAE) and root mean square error (RMSE). The SHapley Additive exPlanations (SHAP) method was used to interpret the importance of the variables. Finally, a web calculator was constructed to facilitate its clinical application.

RESULTS

The stacking model (Linear regression + Multilayer perceptron) performed best, with the highest adjusted R2 of 0.718 (0.632 to 0.804). The mean prediction bias was 4 ml (MAE: 4.008 (3.68 to 4.336)), which is better than that of the linear model. D1 and D2 ranked high in the SHAP plot and performed better in the right lateral decubitus (RLD) than in the supine position. The web calculator can be accessed at https://cheason.shinyapps.io/Stacking_regressor/.

CONCLUSION

The stacking model and its web calculator can serve as practical tools for accurately estimating gastric fluid volume in patients undergoing elective sedated GIE. It is recommended that anesthesiologists measure D1 and D2 in the patient's RLD position.

Speech and language processing with deep learning for dementia diagnosis: A systematic review

Dementia is a progressive neurodegenerative disease that burdens the person living with the disease, their families, and medical and social services. Timely diagnosis of dementia could be followed by introducing interventions that may slow down its progression or reduce its burdens. However, the diagnostic process of dementia is often complex and resource intensive. Access to diagnostic services is also an issue in low and middle-income countries. The abundance and easy accessibility of speech and language data have created new possibilities for utilizing Deep Learning (DL) technologies to be part of the dementia diagnostic process. This systematic review included studies published between 2012-2022 that utilized such technologies to aid in diagnosing dementia. We identified 72 studies using the PRISMA 2020 protocol, extracted and analyzed data from these studies and reported the related DL technologies. We found these technologies effectively differentiated between healthy individuals and those with a dementia diagnosis, highlighting their potential in the diagnosis of dementia. This systematic review provides insights into the contributions of DL-based speech and language techniques to support the dementia diagnostic process. It also offers an understanding of the advancements made in this field thus far and highlights some challenges that still need to be addressed.

Deep-Stacked Convolutional Neural Networks for Brain Abnormality Classification Based on MRI Images

An automated diagnosis system is crucial for helping radiologists identify brain abnormalities efficiently. The convolutional neural network (CNN) algorithm of deep learning has the advantage of automated feature extraction beneficial for an automated diagnosis system. However, several challenges in the CNN-based classifiers of medical images, such as a lack of labeled data and class imbalance problems, can significantly hinder the performance. Meanwhile, the expertise of multiple clinicians may be required to achieve accurate diagnoses, which can be reflected in the use of multiple algorithms. In this paper, we present Deep-Stacked CNN, a deep heterogeneous model based on stacked generalization to harness the advantages of different CNN-based classifiers. The model aims to improve robustness in the task of multi-class brain disease classification when we have no opportunity to train single CNNs on sufficient data. We propose two levels of learning processes to obtain the desired model. At the first level, different pre-trained CNNs fine-tuned via transfer learning will be selected as the base classifiers through several procedures. Each base classifier has a unique expert-like character, which provides diversity to the diagnosis outcomes. At the second level, the base classifiers are stacked together through neural network, representing the meta-learner that best combines their outputs and generates the final prediction. The proposed Deep-Stacked CNN obtained an accuracy of 99.14% when evaluated on the untouched dataset. This model shows its superiority over existing methods in the same domain. It also requires fewer parameters and computations while maintaining outstanding performance.

Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review

BACKGROUND

Normal voice production depends on the synchronized cooperation of multiple physiological systems, which makes the voice sensitive to changes. Any systematic, neurological, and aerodigestive distortion is prone to affect voice production through reduced cognitive, pulmonary, and muscular functionality. This sensitivity inspired using voice as a biomarker to examine disorders that affect the voice. Technological improvements and emerging machine learning (ML) technologies have enabled possibilities of extracting digital vocal features from the voice for automated diagnosis and monitoring systems.

OBJECTIVE

This study aims to summarize a comprehensive view of research on voice-affecting disorders that uses ML techniques for diagnosis and monitoring through voice samples where systematic conditions, nonlaryngeal aerodigestive disorders, and neurological disorders are specifically of interest.

METHODS

This systematic literature review (SLR) investigated the state of the art of voice-based diagnostic and monitoring systems with ML technologies, targeting voice-affecting disorders without direct relation to the voice box from the point of view of applied health technology. Through a comprehensive search string, studies published from 2012 to 2022 from the databases Scopus, PubMed, and Web of Science were scanned and collected for assessment. To minimize bias, retrieval of the relevant references in other studies in the field was ensured, and 2 authors assessed the collected studies. Low-quality studies were removed through a quality assessment and relevant data were extracted through summary tables for analysis. The articles were checked for similarities between author groups to prevent cumulative redundancy bias during the screening process, where only 1 article was included from the same author group.

RESULTS

In the analysis of the 145 included studies, support vector machines were the most utilized ML technique (51/145, 35.2%), with the most studied disease being Parkinson disease (PD; reported in 87/145, 60%, studies). After 2017, 16 additional voice-affecting disorders were examined, in contrast to the 3 investigated previously. Furthermore, an upsurge in the use of artificial neural network-based architectures was observed after 2017. Almost half of the included studies were published in last 2 years (2021 and 2022). A broad interest from many countries was observed. Notably, nearly one-half (n=75) of the studies relied on 10 distinct data sets, and 11/145 (7.6%) used demographic data as an input for ML models.

CONCLUSIONS

This SLR revealed considerable interest across multiple countries in using ML techniques for diagnosing and monitoring voice-affecting disorders, with PD being the most studied disorder. However, the review identified several gaps, including limited and unbalanced data set usage in studies, and a focus on diagnostic test rather than disorder-specific monitoring. Despite the limitations of being constrained by only peer-reviewed publications written in English, the SLR provides valuable insights into the current state of research on ML-based voice-affecting disorder diagnosis and monitoring and highlighting areas to address in future research.

Multimodal Fusion of Smart Home and Text-based Behavior Markers for Clinical Assessment Prediction

New modes of technology are offering unprecedented opportunities to unobtrusively collect data about people's behavior. While there are many use cases for such information, we explore its utility for predicting multiple clinical assessment scores. Because clinical assessments are typically used as screening tools for impairment and disease, such as mild cognitive impairment (MCI), automatically mapping behavioral data to assessment scores can help detect changes in health and behavior across time. In this paper, we aim to extract behavior markers from two modalities, a smart home environment and a custom digital memory notebook app, for mapping to ten clinical assessments that are relevant for monitoring MCI onset and changes in cognitive health. Smart home-based behavior markers reflect hourly, daily, and weekly activity patterns, while app-based behavior markers reflect app usage and writing content/style derived from free-form journal entries. We describe machine learning techniques for fusing these multimodal behavior markers and utilizing joint prediction. We evaluate our approach using three regression algorithms and data from 14 participants with MCI living in a smart home environment. We observed moderate to large correlations between predicted and ground-truth assessment scores, ranging from r = 0.601 to r = 0.871 for each clinical assessment.

The Technology-Oriented Pathway for Auxiliary Diagnosis in the Digital Health Age: A Self-Adaptive Disease Prediction Model

The advent of the digital age has accelerated the transformation and upgrading of the traditional medical diagnosis pattern. With the rise of the concept of digital health, the emerging information technologies, such as machine learning (ML) and data mining (DM), have been extensively applied in the medical and health field, where the construction of disease prediction models is an especially effective method to realize auxiliary medical diagnosis. However, the existing related studies mostly focus on the prediction analysis for a certain disease, using models with which it might be challenging to predict other diseases effectively. To address the issues existing in the aforementioned studies, this paper constructs four novel strategies to achieve a self-adaptive disease prediction process, i.e., the hunger-state foraging strategy of producers (PHFS), the parallel strategy for exploration and exploitation (EEPS), the perturbation-exploration strategy (PES), and the parameter self-adaptive strategy (PSAS), and eventually proposes a self-adaptive disease prediction model with applied universality, strong generalization ability, and strong robustness, i.e., multi-strategies optimization-based kernel extreme learning machine (MsO-KELM). Meanwhile, this paper selects six different real-world disease datasets as the experimental samples, which include the Breast Cancer dataset (cancer), the Parkinson dataset (Parkinson's disease), the Autistic Spectrum Disorder Screening Data for Children dataset (Autism Spectrum Disorder), the Heart Disease dataset (heart disease), the Cleveland dataset (heart disease), and the Bupa dataset (liver disease). In terms of the prediction accuracy, the proposed MsO-KELM can obtain ACC values in analyzing these six diseases of 94.124%, 84.167%, 91.079%, 72.222%, 70.184%, and 70.476%, respectively. These ACC values have all been increased by nearly 2-7% compared with those obtained by the other models mentioned in this paper. This study deepens the connection between information technology and medical health by exploring the self-adaptive disease prediction model, which is an intuitive representation of digital health and could provide a scientific and reliable diagnostic basis for medical workers.

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.

A novel early diagnostic framework for chronic diseases with class imbalance

Chronic diseases are one of the most severe health issues in the world, due to their terrible clinical presentations such as long onset cycle, insidious symptoms, and various complications. Recently, machine learning has become a promising technique to assist the early diagnosis of chronic diseases. However, existing works ignore the problems of feature hiding and imbalanced class distribution in chronic disease datasets. In this paper, we present a universal and efficient diagnostic framework to alleviate the above two problems for diagnosing chronic diseases timely and accurately. Specifically, we first propose a network-limited polynomial neural network (NLPNN) algorithm to efficiently capture high-level features hidden in chronic disease datasets, which is data augmentation in terms of its feature space and can also avoid over-fitting. Then, to alleviate the class imbalance problem, we further propose an attention-empowered NLPNN algorithm to improve the diagnostic accuracy for sick cases, which is also data augmentation in terms of its sample space. We evaluate the proposed framework on nine public and two real chronic disease datasets (partly with class imbalance). Extensive experiment results demonstrate that the proposed diagnostic algorithms outperform state-of-the-art machine learning algorithms, and can achieve superior performances in terms of accuracy, recall, F1, and G_mean. The proposed framework can help to diagnose chronic diseases timely and accurately at an early stage.