Poor Sleep Predicts Increased Pain Perception Among Adults With Mild Cognitive Impairment

Application of machine learning approaches in predicting clinical outcomes in older adults - a systematic review and meta-analysis

BACKGROUND

Machine learning-based prediction models have the potential to have a considerable positive impact on geriatric care.

DESIGN

Systematic review and meta-analyses.

PARTICIPANTS

Older adults (≥ 65 years) in any setting.

INTERVENTION

Machine learning models for predicting clinical outcomes in older adults were evaluated. A random-effects meta-analysis was conducted in two grouped cohorts, where the predictive models were compared based on their performance in predicting mortality i) under and including 6 months ii) over 6 months.

OUTCOME MEASURES

Studies were grouped into two groups by the clinical outcome, and the models were compared based on the area under the receiver operating characteristic curve metric.

RESULTS

Thirty-seven studies that satisfied the systematic review criteria were appraised, and eight studies predicting a mortality outcome were included in the meta-analyses. We could only pool studies by mortality as there were inconsistent definitions and sparse data to pool studies for other clinical outcomes. The area under the receiver operating characteristic curve from the meta-analysis yielded a summary estimate of 0.80 (95% CI: 0.76 - 0.84) for mortality within 6 months and 0.81 (95% CI: 0.76 - 0.86) for mortality over 6 months, signifying good discriminatory power.

CONCLUSION

The meta-analysis indicates that machine learning models display good discriminatory power in predicting mortality. However, more large-scale validation studies are necessary. As electronic healthcare databases grow larger and more comprehensive, the available computational power increases and machine learning models become more sophisticated; there should be an effort to integrate these models into a larger research setting to predict various clinical outcomes.

Sleep Disturbances and Chronic Pain in People with HIV: Implications for HIV-Associated Neurocognitive Disorders

Purpose of Review

Antiretroviral therapy has significantly reduced morbidity and mortality in people with HIV. Despite being virally suppressed, sleep disturbances, chronic pain, and neurocognitive impairments persist which can negatively impact quality of life for people with HIV. This article presents relevant literature related to sleep disturbances and chronic pain in people with HIV. The potential impact of these comorbidities on cognition is discussed with implications for managing HIV-associated neurocognitive disorder (HAND).

Recent Findings

People with HIV and chronic pain report greater insomnia and depressive symptoms compared to those without chronic pain. The neurotoxic effects of HIV itself and sleep and chronic pain induced inflammation can contribute to poorer cognitive outcomes.

Summary

Sleep disturbances and chronic pain are prevalent conditions in people with HIV that may perpetuate the development and exacerbation of HAND. Sleep and pain interventions may preserve cognitive function and improve quality of life for people aging with HIV.

Differences and Correlations of Anxiety, Sleep Quality, and Pressure-Pain Threshold between Patients with Chronic Low Back Pain and Asymptomatic People

Background. Chronic low back pain (CLBP) is a clinically common and expensive disease. Patients frequently take sick leaves because of pain and dysfunction, and their unpleasant life and work experiences cause psychological depression and anxiety and affect their quality of life. Sleep disturbance is a common problem among patients with low back pain (LBP) with more than 50% complaining about poor sleep quality. This study aimed to explore the correlations between anxiety, sleep quality, and pressure-pain threshold (PPT) and their differences between patients with CLBP and asymptomatic people. Methods. Forty patients with CLBP and 40 asymptomatic people were recruited. Relevant data, including State-Trait Anxiety Inventory, Pittsburgh Sleep Quality Index, and PPT, were individually and independently collected by blinded physiotherapists with a practicing certificate and then statistically analyzed. An independent sample t-test was used to determine the intergroup differences between patients with CLBP and asymptomatic populations. Pearson correlation coefficient was employed for correlation analysis. Results. The CLBP group had significantly higher anxiety scores (41.64 ± 9.88 vs. 36.69 ± 8.31; t = −2.496, $p=0.015$ ) than the asymptomatic group. A significant difference was found in the total score of the Pittsburgh Sleep Quality Index (6.41 ± 2.43 vs. 5.09 ± 2.18; t = −2.628, $p=0.010$ ) but not in the trait anxiety (44.00 ± 7.83 vs. 42.67 ± 9.51; t = −0.695, $p=0.489$ ) of the two groups. State−Trait Anxiety Inventory showed a low to moderate negative correlation with PPT. No remarkable correlation was observed between Pittsburgh Sleep Quality Index and PPT. Conclusions. Patients with CLBP showed considerably worse state anxiety and sleep quality than asymptomatic people; however, no substantial difference in PPT was found between the two groups. The results suggest that in clinical practice, the focus should include pain and related social and psychological factors. CLBP treatment could be considered from multiple perspectives and disciplines.This trial is registered with Chinese Clinical Trial Registry (Trial registration: ChiCTR-TRC-13003701).

Prior Night Sleep Affects Next-Day Pain Interference Among Community-Dwelling Older Adults With Lower Extremity Chronic Pain

Emergent work suggests that sleep is a robust biobehavioral predictor of pain; however, it remains unclear how sleep is prospectively linked to pain on a day-to-day basis among older adults. The current prospective study examined how sleep duration (total sleep time), quality (sleep efficiency, wake after sleep onset), and late and irregular sleep timing influenced next-day pain perception among community-dwelling older adults (N = 10; 65 matched observations) with lower extremity chronic pain over 1 week. Multilevel modeling estimated the association between sleep (Actigraph GT9X Link) and pain perception (Brief Pain Inventory Short Form). Increased wake after sleep onset (B = 0.19, p = 0.04), sleep variability (B = 0.02, p = 0.01), and later midsleep time (B = 0.40, p < 0.05) were associated with increased pain interference the following day. Findings support the idea that timely sleep interventions may reduce the effect of poor sleep on next-day pain in older adults. [Research in Gerontological Nursing, 14(4), 173-179.].