Association of Snoring Characteristics with Predominant Site of Collapse of Upper Airway in Obstructive Sleep Apnoea Patients

Predictive model for novel subtypes of patients undergoing lower extremity amputation for peripheral artery disease: An unsupervised machine learning study

Background

Peripheral artery disease (PAD) represents the frequently seen circulatory condition related to a risk of critical limb ischemia and amputation. Critical lower extremity ischemia may require amputation, and the outcomes vary. In this study, we developed an artificial intelligence (AI)-driven predictive model for PAD subtypes to assess risk among patients more precisely and accurately to predict disease progression.

Methods

The present retrospective study examined clinical data in PAD patents undergoing lower extremity amputation. The data were analyzed using an unsupervised machine learning algorithm (UMLA) for subgroup identification and risk stratification. The clustering result accuracy was validated by analyzing the follow-up data of clusters. Finally, we built the prediction model with binary logistic regression.

Results

In total, we enrolled 507 cases into this work. Two distinct subgroups, consisting of Clusters 1 and 2, were identified by UMLA; those from Cluster 1 showed markedly poorer conditions and prognostic outcomes compared with those from Cluster 2. With regard to the new PAD subtype, we established a nomogram with eight predictive factors, including gender, age, smoking history, diabetes and coronary heart disease history, albumin levels, endovascular intervention, and amputation level. The nomogram could accurately categorize patients into two identified clusters, and the area under receiver operating characteristic curve was 0.861 (95 % confidence interval: 0.830-0.893).

Conclusion

In this study, UMLA was used to identify new phenotypic subgroups among PAD cases who showed different risks of amputation. Our constructed AI-driven predictive model for PAD subtypes showed that it can be used for risk stratification and clinical management with high accuracy and reliability.

Impact of palatopharyngeal sizes changing on pharyngeal airflow fluctuation and airway vibration in a pediatric airway

Snoring is common in children and is associated with many adverse consequences. One must study the relationships between pharyngeal morphology and snoring physics to understand snoring progression. Although some model studies have provided fluid-structure interaction dynamic descriptions for the correlation between airway size and snoring physics, the descriptions still need to be further investigated in patient-specific airway models. Fluid-structure interaction studies using patient-specific airway structures complement the above model studies. Based on reported cephalometric measurement methods, this study quantified and preset the size of the palatopharynx airway in a patient-specific airway and investigated how the palatopharynx size affects the pharyngeal airflow fluctuation, soft palate vibration, and glossopharynx vibration with the help of a verified FSI method. The results showed that the stenosis anterior airway of the soft palate increased airway resistance and airway resistance fluctuations, which can lead to increased sleep effort and frequent snoring. Widening of the anterior airway can reduce airflow resistance and avoid obstructing the anterior airway by the soft palate vibration. The pharyngeal airflow resistance, mouth inflow proportion, and soft palate apex displacement have components at the same frequencies in all airway models, and the glossopharynx vibration and instantaneous inflow rate have components at the same frequencies, too. The mechanism of this same frequency fluctuation phenomenon can be explained by the fluid-structure interaction dynamics of an ideal coupled model consisting of a flexible plate model and a collapsible tube model. The results of this study demonstrate the potential of FSI in studying snoring physics and clarify to some degree the mechanism of airway morphology affecting airway vibration physics.

Regular snoring is associated with uncontrolled hypertension

Snoring may be a risk factor for cardiovascular disease independent of other co-morbidities. However, most prior studies have relied on subjective, self-report, snoring evaluation. This study assessed snoring prevalence objectively over multiple months using in-home monitoring technology, and its association with hypertension prevalence. In this study, 12,287 participants were monitored nightly for approximately six months using under-the-mattress sensor technology to estimate the average percentage of sleep time spent snoring per night and the estimated apnea-hypopnea index (eAHI). Blood pressure cuff measurements from multiple daytime assessments were averaged to define uncontrolled hypertension based on mean systolic blood pressure≥140 mmHg and/or a mean diastolic blood pressure ≥90 mmHg. Associations between snoring and uncontrolled hypertension were examined using logistic regressions controlled for age, body mass index, sex, and eAHI. Participants were middle-aged (mean ± SD; 50 ± 12 y) and most were male (88%). There were 2467 cases (20%) with uncontrolled hypertension. Approximately 29, 14 and 7% of the study population snored for an average of >10, 20, and 30% per night, respectively. A higher proportion of time spent snoring (75th vs. 5th; 12% vs. 0.04%) was associated with a ~1.9-fold increase (OR [95%CI]; 1.87 [1.63, 2.15]) in uncontrolled hypertension independent of sleep apnea. Multi-night objective snoring assessments and repeat daytime blood pressure recordings in a large global consumer sample, indicate that snoring is common and positively associated with hypertension. These findings highlight the potential clinical utility of simple, objective, and noninvasive methods to detect snoring and its potential adverse health consequences.

Construction of a predictive model for blood transfusion in patients undergoing total hip arthroplasty and identification of clinical heterogeneity

A precise forecast of the need for blood transfusions (BT) in patients undergoing total hip arthroplasty (THA) is a crucial step toward the implementation of precision medicine. To achieve this goal, we utilized supervised machine learning (SML) techniques to establish a predictive model for BT requirements in THA patients. Additionally, we employed unsupervised machine learning (UML) approaches to identify clinical heterogeneity among these patients. In this study, we recruited 224 patients undergoing THA. To identify factors predictive of BT during the perioperative period of THA, we employed LASSO regression and the random forest (RF) algorithm as part of supervised machine learning (SML). Using logistic regression, we developed a predictive model for BT in THA patients. Furthermore, we utilized unsupervised machine learning (UML) techniques to cluster THA patients who required BT based on similar clinical features. The resulting clusters were subsequently visualized and validated. We constructed a predictive model for THA patients who required BT based on six predictive factors: Age, Body Mass Index (BMI), Hemoglobin (HGB), Platelet (PLT), Bleeding Volume, and Urine Volume. Before surgery, 1 h after surgery, 1 day after surgery, and 1 week after surgery, significant differences were observed in HGB and PLT levels between patients who received BT and those who did not. The predictive model achieved an AUC of 0.899. Employing UML, we identified two distinct clusters with significantly heterogeneous clinical characteristics. Age, BMI, PLT, HGB, bleeding volume, and urine volume were found to be independent predictors of BT requirement in THA patients. The predictive model incorporating these six predictors demonstrated excellent predictive performance. Furthermore, employing UML enabled us to classify a heterogeneous cohort of THA patients who received BT in a meaningful and interpretable manner.

Identification of Clinical Heterogeneity and Construction of Prediction Models for Novel Subtypes in Patients with Abdominal Aortic Aneurysm: An Unsupervised Machine Learning Study

BACKGROUND

Abdominal aortic aneurysm (AAA) is one of the most common diseases in vascular surgery. Endovascular aneurysm repair (EVAR) can effectively treat AAA. It is essential to accurately classify patients with AAA who need EVAR.

METHODS

We enrolled 266 patients with AAA who underwent EVAR. Unsupervised machine learning algorithms (UMLAs) were used to cluster subjects according to similar clinical characteristics. To verify UMLA's accuracy, the operative and postoperative results of the 2 clusters were analyzed. Finally, a prediction model was developed using binary logistic regression analysis.

RESULTS

UMLAs could correctly classify patients based on their clinical characteristics. Patients in Cluster 1 were older, had a higher BMI, and were more likely than patients in Cluster 2 to develop pneumonia, chronic obstructive pulmonary disease, and cerebrovascular disease. The aneurysm diameter, neck angulation, diameter and angulation of bilateral common iliac arteries, and incidence of iliac artery aneurysm were significantly higher in cluster 1 patients than in cluster 2. Cluster 1 had a longer operative time, a longer length of stay in the intensive care unit and hospital, a higher medical expense, and a higher incidence of reintervention. A nomogram was established based on the BMI, neck angulation, left common iliac artery (LCIA) diameter and angulation, and right common iliac artery (RCIA) diameter and angulation. The nomogram was evaluated using receiver operating characteristic curve analysis, with an area under the curve of 0.933 (95% confidence interval, 0.902-0.963) and a C-index of 0.927.

CONCLUSIONS

Our findings demonstrate that UMLAs can be used to rationally classify a heterogeneous cohort of patients with AAA effectively, and the analysis of postoperative variables also verified the accuracy of UMLAs. We established a prediction model for new subtypes of AAA, which can improve the quality of management of patients with AAA.

Application of artificial intelligence in the diagnosis of sleep apnea

STUDY OBJECTIVES

Machine learning (ML) models have been employed in the setting of sleep disorders. This review aims to summarize the existing data about the role of ML techniques in the diagnosis, classification, and treatment of sleep-related breathing disorders.

METHODS

A systematic search in Medline, EMBASE, and Cochrane databases through January 2022 was performed.

RESULTS

Our search strategy revealed 132 studies that were included in the systematic review. Existing data show that ML models have been successfully used for diagnostic purposes. Specifically, ML models showed good performance in diagnosing sleep apnea using easily obtained features from the electrocardiogram, pulse oximetry, and sound signals. Similarly, ML showed good performance for the classification of sleep apnea into obstructive and central categories, as well as predicting apnea severity. Existing data show promising results for the ML-based guided treatment of sleep apnea. Specifically, the prediction of outcomes following surgical treatment and optimization of continuous positive airway pressure therapy can be guided by ML models.

CONCLUSIONS

The adoption and implementation of ML in the field of sleep-related breathing disorders is promising. Advancements in wearable sensor technology and ML models can help clinicians predict, diagnose, and classify sleep apnea more accurately and efficiently.

CITATION

Bazoukis G, Bollepalli SC, Chung CT, et al. Application of artificial intelligence in the diagnosis of sleep apnea. J Clin Sleep Med. 2023;19(7):1337-1363.

Identification of clinical heterogeneity and construction of a novel subtype predictive model in patients with ankylosing spondylitis: An unsupervised machine learning study

BACKGROUND

Accurate classification of patients with ankylosing spondylitis (AS) is the premise of precision medicine so as to perform different medical interventions for different patient types. AS pathology is closely related to the changes in the immune microenvironment. In this study, we used unsupervised machine learning (UML) to classify patients with AS based on clinical characteristics. We then constructed a novel subtype predictive model for AS based on the clinical classification, after which we investigated the difference in the immune microenvironment to unravel the AS pathogenesis.

METHODS

Overall, 196 patients with AS were enrolled. UML was used to cluster AS patients by similar clinical characteristics. Functional ability, disease status, and grading of radiologic features were assessed to verify the accuracy and heterogeneity of UML clustering. Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest algorithm were used to screen and identify predictive factors for the novel subtype of AS. Logistic regression was also performed to construct a predictive model of this novel subtype. Datasets were downloaded from the Gene Expression Omnibus database to assess immune cell infiltration, and the results were validated using data of routine blood tests from 3671 AS patients and 5720 non-AS patients. The differential expression of Fat Mass and Obesity-Associated Protein (FTO), an m⁶A regulator, between AS patients and healthy control subjects was confirmed using immunohistochemistry.

RESULTS

UML clustering identified two clusters. The clinical characteristics of the two clusters were significantly heterogeneous. For the novel subtype of AS identified in UML clustering, a predictive model was built using three predictive factors, namely, C-reactive protein (CRP), absolute value of neutrophils (NEU), and absolute value of monocytes (MONO). The area under the curve of the predictive model was 0.983. Heterogeneity in the neutrophil and monocyte counts in AS was verified through immune cell infiltration analysis. Data from routine blood tests revealed that NEU and MONO were significantly higher in AS patients than in non-AS patients (p < 0.001). FTO expression was negatively correlated with both NEU and MONO. Immunohistochemistry analysis confirmed the downregulated expression of FTO.

CONCLUSIONS

UML provides an explicable and remarkable classification of a heterogeneous cohort of AS patients. A novel subtype of AS was identified in UML clustering. CRP, NEU, and MONO were the independent predictive factors for the novel subtype of AS. FTO expression was correlated with immune cell infiltration in AS patients.

The role of artificial intelligence in the treatment of obstructive sleep apnea

BACKGROUND

The first-line and most common treatment for obstructive sleep apnea is nasal continuous positive airway pressure, which serves as a pneumatic splint to stabilize the upper airway and is effective when used with appropriate adherence. Continuous positive airway pressure compliance rates remain significantly low despite machine improvements and compliance intervention. Other treatment options include oral appliances, myofunctional therapy, and surgery. The aim of this project is to elucidate the role of artificial intelligence within improving the treatment of obstructive sleep apnea.

METHODS

Related publications between 1999 and 2022 were reviewed from PubMed and Embase databases utilizing search terms "artificial intelligence," "machine learning," "obstructive sleep apnea," and "treatment." Both authors independently screened the results by title/abstract then by full text review. 126 non-duplicate articles were screened, 38 articles were included after title and abstract screen and 30 articles were included after full text review. The inclusion criteria are outline in the PICO framework and involved studies focused on artificial intelligence application in guiding and evaluating obstructive sleep apnea treatment. Non-English articles were excluded.

RESULTS

The role of artificial intelligence in the treatment of OSA was categorized into the following sections: Predicting treatment outcomes of various treatment options, Improving/Evaluating treatment, and Personalizing treatment with improving understanding of underlying mechanisms of OSA.

CONCLUSIONS

Artificial intelligence has the capacity to improve the treatment of OSA through predicting outcomes of treatment options, evaluating the treatment the patient is currently utilizing and increasing understanding of the mechanisms that contribute to OSA disease process and physiology. Implementing AI in guiding treatment decisions allows patients to connect with treatment methods that would be most effective on an individual basis.

Machine learning-based clustering in cervical spondylotic myelopathy patients to identify heterogeneous clinical characteristics

Background

Anterior cervical decompression and fusion can effectively treat cervical spondylotic myelopathy (CSM). Accurately classifying patients with CSM who have undergone anterior cervical decompression and fusion is the premise of precision medicine. In this study, we used machine learning algorithms to classify patients and compare the postoperative efficacy of each classification.

Methods

A total of 616 patients with cervical spondylotic myelopathy who underwent anterior cervical decompression and fusion were enrolled. Unsupervised machine learning algorithms (UMLAs) were used to cluster subjects according to similar clinical characteristics. Then, the results of clustering were visualized. The surgical outcomes were used to verify the accuracy of machine learning clustering.

Results

We identified two clusters in these patients who had significantly different baseline clinical characteristics, preoperative complications, the severity of neurological symptoms, and the range of decompression required for surgery. UMLA divided the CSM patients into two clusters according to the severity of their illness. The repose to surgical treatment between the clusters was significantly different.

Conclusions

Our results showed that UMLA could be used to rationally classify a heterogeneous cohort of CSM patients effectively, and thus, it might be used as the basis for a data-driven platform for identifying the cluster of patients who can respond to a particular treatment method.

Obstructive Sleep Apnea Detection Based on Sleep Sounds via Deep Learning

PURPOSE

This study aimed to propose a novel deep-learning method for automatic sleep apneic event detection and thus to estimate the apnea hypopnea index (AHI) and identify obstructive sleep apnea (OSA) in an event-by-event manner solely based on sleep sounds obtained by a noncontact audio recorder.

METHODS

We conducted a cross-sectional study of participants with habitual snoring or heavy breathing sounds during sleep to train and test a deep convolutional neural network named OSAnet for the detection of OSA based on sleep sounds. Polysomnography (PSG) was conducted, and sleep sounds were recorded simultaneously in a regular room without noise attenuation. The study was conducted in two phases. In phase one, eligible participants were enrolled and randomly allocated into training and validation groups for deep learning algorithm development. In phase two, eligible patients were enrolled in a test group for algorithm assessment. Sensitivity, specificity, accuracy, unweighted Cohen kappa coefficient (κ) and the area under the curve (AUC) were calculated using PSG as the reference standard.

RESULTS

A total of 135 participants were randomly divided into a training group (n, 116) and a validation group (n, 19). An independent test group of 59 participants was subsequently enrolled. Our algorithm achieved a precision of 0.81 and sensitivity of 0.78 in the test group for overall sleep event detection. The algorithm exhibited robust diagnostic performance to identify severe cases with a sensitivity of 95.6% and specificity of 91.6%.

CONCLUSION

Our results showed that a deep learning algorithm based on sleep sounds recorded by a noncontact voice recorder served as a feasible tool for apneic event detection and OSA identification. This technique may hold promise for OSA assessment in the community in a relatively comfortable and low-cost manner. Further studies to develop a tool based on a home-based setting are warranted.

Obstructive sleep apnea

Obstructive sleep apnea (OSA) is a disease that results from loss of upper airway muscle tone leading to upper airway collapse during sleep in anatomically susceptible persons, leading to recurrent periods of hypoventilation, hypoxia, and arousals from sleep. Significant clinical consequences of the disorder cover a wide spectrum and include daytime hypersomnolence, neurocognitive dysfunction, cardiovascular disease, metabolic dysfunction, respiratory failure, and pulmonary hypertension. With escalating rates of obesity a major risk factor for OSA, the public health burden from OSA and its sequalae are expected to increase, as well. In this chapter, we review the mechanisms responsible for the development of OSA and associated neurocognitive and cardiometabolic comorbidities. Emphasis is placed on the neural control of the striated muscles that control the pharyngeal passages, especially regulation of hypoglossal motoneuron activity throughout the sleep/wake cycle, the neurocognitive complications of OSA, and the therapeutic options available to treat OSA including recent pharmacotherapeutic developments.