Precision Medicine for Insomnia

Application of machine learning models in predicting insomnia severity: an integrative approach with constitution of traditional Chinese medicine

Objective

This study sought to explore the utility of machine learning models in predicting insomnia severity based on Traditional Chinese Medicine (TCM) constitution classifications, with an aim to discuss the potential applications of such models in the treatment and prevention of insomnia.

Methods

We analyzed a dataset of 165 insomnia patients from the Shanghai Minhang District Integrated Traditional Chinese and Western Medicine Hospital. TCM constitution was assessed using a standardized Constitution in Chinese Medicine (CCM) scale. Sleep quality, or insomnia severity, was evaluated using the Spiegel Sleep Questionnaire (SSQ). Machine learning models, including Random Forest Classifier (RFC), Support Vector Classifier (SVC), and K-Nearest Neighbors (KNN), were utilized. These models were optimized using Grid Search algorithm and were trained and tested on stratified patient data, with the TCM constitution classifications serving as primary predictors.

Results

The RFC outperformed others, achieving a weighted average accuracy, precision, recall, and F1-score of 0.91, 0.94, 0.92, and 0.92 respectively, it also effectively classified the severity of insomnia with high area under receiver operating characteristic curve (AUC-ROC) values. Feature importance analysis demonstrated the Damp-heat constitution as the most influential predictor, followed by Yang-deficiency, Qi-depression, Qi-deficiency, and Blood-stasis constitutions.

Conclusion

The results demonstrate the potent utility of machine learning, specifically RFC, coupled with TCM constitution classifications in predicting insomnia severity. Notably, the constitution classifications such as Damp-heat and Yang-deficiency emerged as crucial determinants, emphasizing its potential in guiding targeted insomnia treatments. This approach enables the development of more personalized and efficient interventions, thereby enhancing patient outcomes.

Can mindfulness-based interventions improve outcomes in cognitive-behavioural therapy for chronic insomnia disorder in the general population? Systematic review and meta-analysis

Cognitive-behavioural therapy for insomnia (CBT-I) is the recommended first-line therapy for adults with chronic insomnia disorder (ID), which is characterized by hyperarousal. Mindfulness-based interventions (MBIs) are protocols aimed at stress reduction based on non-judgmental attention control in the present moment. However, MBIs have been increasingly used without a clear scientific basis. The objective of this analysis was to examine if MBIs could be useful as a component of the CBT-I therapeutic system through a systematic review and meta-analysis of randomized controlled trials (RCTs) and non-randomized studies (NRS) searched in PubMed, PsycINFO, Cochrane and WoS. The Insomnia Severity Index (ISI) was the primary outcome, while the Pittsburgh Sleep Quality Index (PSQI) and a composite sleep variable (CSV) were secondary outcomes. Thirteen articles corresponding to nine studies (three pragmatic RCTs, three explanatory RCTs and three NRS) were included. The omnibus test found that MBIs had a small to medium effect size on ISI nearing signification when comparing active control groups in the pretest-posttest period [Δ = 0.44, p = 0.07], a medium, non-significant, effect size on PSQI [Δ = 0.52, p = 0.18], and a significant though small effect size on CSV [Δ = 0.05, p < 0.01]. No heterogeneity was found. The analysis could not demonstrate that MBIs, combined with CBT-I components in some studies, positively affected ID in the general adult population. This was probably due to the lack of pragmatic designs and suitable measuring instruments. Recommendations are made for designing further studies to address these issues.

The burden of untreated insomnia disorder in a sample of 1 million adults: a cohort study

BACKGROUND

Insomnia disorder is a highly prevalent, significant public health concern associated with substantial and growing health burden. There are limited real-world data assessing the burden of insomnia disorder on daytime functioning and its association with comorbidities. The objective of this study was to leverage large-scale, real-world data to assess the burden of untreated insomnia disorder in terms of daytime impairment and clinical outcomes.

METHODS

This United States medical claims database study compares patients diagnosed with insomnia disorder but not receiving treatment ('untreated insomnia' cohort) to patients without an insomnia disorder diagnosis and without treatment ('non-insomnia' cohort). International Classification of Disease, Tenth Revision codes were used as a proxy to represent the three symptom domains (Sleepiness, Alert/Cognition, Mood) of the Insomnia Daytime Symptoms and Impacts Questionnaire (IDSIQ), a newly developed and validated tool used in clinical studies to assess daytime functioning in insomnia disorder. Chronic Fatigue (R53.83) and Other Fatigue (R53.83), Somnolence (R40.0) and Disorientation (R41.0) were selected as categories representing one or more IDSIQ domains. Clinical outcomes included cardiovascular events, psychiatric disorders, cognitive impairment and metabolic disorders.

RESULTS

Approximately 1 million patients were included (untreated insomnia: n = 139,959; non-insomnia: n = 836,975). Compared with the 'non-insomnia' cohort, the 'untreated insomnia' cohort was more likely to experience daytime impairments, with mean differences in occurrences per 100 patient-years for: (a) fatigue, at 27.35 (95% confidence interval [CI] 26.81, 27.77, p < 0.01); (b) dizziness, at 4.66 (95% CI 4.40, 4.90, p < 0.01); (c) somnolence, at 4.18 (95% CI 3.94, 4.43, p < 0.01); and (d) disorientation, at 0.92 (95% CI 0.77, 1.06, p < 0.01). During the 1-year look-back period, patients in the 'untreated insomnia' cohort were also more likely to have been diagnosed with arterial hypertension (40.9% vs. 26.3%), psychiatric comorbidities (40.1% vs. 13.2%), anxiety (29.2% vs. 8.5%), depression (26.1% vs. 8.1%) or obesity (21.3% vs. 11.1%) compared with those in the 'non-insomnia' cohort.

CONCLUSIONS

This large-scale study confirms the substantial burden of insomnia disorder on patients in a real-world setting, with significant daytime impairment and numerous comorbidities. This reinforces the need for timely insomnia disorder diagnosis and treatments that improve both sleep, as well as daytime functioning.

Recommended timing of medications that impact sleep and wakefulness: A review of the American Prescribers' Digital Reference

An appreciable number of medicines have a recommended unique single time-of-day or asymmetrical or unequal-interval multiple-daily administration schedule. Many prescription and over-the-counter (OTC) products, according to administration time, can exert positive or negative impact on nighttime sleep and daytime wakefulness. Intuitively, medicines used to manage nighttime sleep and daytime wake disorders should be taken, respectively, at night before bedtime and morning after arising. However, some utilized for other medical conditions, if improperly timed, may compromise nocturnal sleep and diurnal attentiveness. We conducted a comprehensive review of the American Prescribers' Digital Reference, internet version of the Physician's Desk Reference, for the recommended scheduling of medications and OTC remedies that can impact sleep and wakefulness. The search revealed several hundred therapies of various classes -- α₂-receptor agonists, antidepressants, barbiturates, central nervous system stimulants, benzodiazepines, dopamine agonists, dopamine norepinephrine reuptake inhibitors, selective norepinephrine reuptake inhibitors, eugeroics, γ-aminobutyric acid modulators, H₁ and H₃-receptor antagonists, melatonin analogues, OTC melatonin-containing products, non-benzodiazepine benzodiazepine-receptor agonists, dual orexin-receptor antagonists, and serotonin modulators -- that have a recommended unique dosing schedule. The tables and text of this article are intended to guide the proper scheduling of these medicines to optimize desired and/or minimize undesired effects.

Translational Approaches to Influence Sleep and Arousal

Sleep disorders are widespread in society and are prevalent in military personnel and in Veterans. Disturbances of sleep and arousal mechanisms are common in neuropsychiatric disorders such as schizophrenia, post-traumatic stress disorder, anxiety and affective disorders, traumatic brain injury, dementia, and substance use disorders. Sleep disturbances exacerbate suicidal ideation, a major concern for Veterans and in the general population. These disturbances impair quality of life, affect interpersonal relationships, reduce work productivity, exacerbate clinical features of other disorders, and impair recovery. Thus, approaches to improve sleep and modulate arousal are needed. Basic science research on the brain circuitry controlling sleep and arousal led to the recent approval of new drugs targeting the orexin/hypocretin and histamine systems, complementing existing drugs which affect GABA_A receptors and monoaminergic systems. Non-invasive brain stimulation techniques to modulate sleep and arousal are safe and show potential but require further development to be widely applicable. Invasive viral vector and deep brain stimulation approaches are also in their infancy but may be used to modulate sleep and arousal in severe neurological and psychiatric conditions. Behavioral, pharmacological, non-invasive brain stimulation and cell-specific invasive approaches covered here suggest the potential to selectively influence arousal, sleep initiation, sleep maintenance or sleep-stage specific phenomena such as sleep spindles or slow wave activity. These manipulations can positively impact the treatment of a wide range of neurological and psychiatric disorders by promoting the restorative effects of sleep on memory consolidation, clearance of toxic metabolites, metabolism, and immune function and by decreasing hyperarousal.

Why Do They Fall? The Impact of Insomnia on Gait of Older Adults: A Case-Control Study

STUDY OBJECTIVES

To compare gait and cognitive performance conducted separately as a single- (ST) and simultaneously as a dual-task (DT), ie, when a cognitive task was added, among community-dwelling older adults with and without insomnia.

METHODS

Participants included: 39 (28 females) community-dwelling older adults with insomnia, 34 (21 females) controls without insomnia. Subject groups were matched for age, gender, and education. Sleep quality was evaluated based on two-week actigraphy. Gait speed and cognition were assessed as ST and DT performance. DT costs (DTCs) were calculated for both tasks. Outcomes were compared via independent samples t-tests or Mann-Whitney U-tests.

RESULTS

Older adults with insomnia demonstrated significantly slower gait speed during ST (1 ± 0.29 vs 1.27 ± 0.17 m/s, p<0.001) and DT (0.77 ± 0.26 vs 1.14 ± 0.20 m/s, p<0.001) and fewer correct responses in the cognitive task during ST (21 ± 7 vs 27 ± 11, p=0.009) and DT (19 ± 7 vs 23 ± 9, p=0.015) compared to control group. DTC for the gait task was higher among older adults with insomnia (18.32%, IQR: 9.48-30.93 vs 7.81% IQR: 4.43-14.82, p<0.001). However, no significant difference was observed in DTC for the cognitive task (14.71%, IQR: -0.89-38.84 vs 15%, IQR: -0.89-38.84%, p=0.599).

CONCLUSION

Older adults with insomnia have lower gait speed and poorer cognitive performance during ST and DT and an inefficient pattern of task prioritization during walking, compared to counterparts without insomnia. These findings may explain the higher risk of falls among older adults with insomnia. Geriatric professionals should be aware of potential interrelationships between sleep and gait.