To save content items to your account,
please confirm that you agree to abide by our usage policies.
If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account.
Find out more about saving content to .
To save content items to your Kindle, first ensure email@example.com
is added to your Approved Personal Document E-mail List under your Personal Document Settings
on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part
of your Kindle email address below.
Find out more about saving to your Kindle.
Note you can select to save to either the @free.kindle.com or @kindle.com variations.
‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi.
‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.
Only a limited number of patients with major depressive disorder (MDD) respond to a first course of antidepressant medication (ADM). We investigated the feasibility of creating a baseline model to determine which of these would be among patients beginning ADM treatment in the US Veterans Health Administration (VHA).
A 2018–2020 national sample of n = 660 VHA patients receiving ADM treatment for MDD completed an extensive baseline self-report assessment near the beginning of treatment and a 3-month self-report follow-up assessment. Using baseline self-report data along with administrative and geospatial data, an ensemble machine learning method was used to develop a model for 3-month treatment response defined by the Quick Inventory of Depression Symptomatology Self-Report and a modified Sheehan Disability Scale. The model was developed in a 70% training sample and tested in the remaining 30% test sample.
In total, 35.7% of patients responded to treatment. The prediction model had an area under the ROC curve (s.e.) of 0.66 (0.04) in the test sample. A strong gradient in probability (s.e.) of treatment response was found across three subsamples of the test sample using training sample thresholds for high [45.6% (5.5)], intermediate [34.5% (7.6)], and low [11.1% (4.9)] probabilities of response. Baseline symptom severity, comorbidity, treatment characteristics (expectations, history, and aspects of current treatment), and protective/resilience factors were the most important predictors.
Although these results are promising, parallel models to predict response to alternative treatments based on data collected before initiating treatment would be needed for such models to help guide treatment selection.
Fewer than half of patients with major depressive disorder (MDD) respond to psychotherapy. Pre-emptively informing patients of their likelihood of responding could be useful as part of a patient-centered treatment decision-support plan.
This prospective observational study examined a national sample of 807 patients beginning psychotherapy for MDD at the Veterans Health Administration. Patients completed a self-report survey at baseline and 3-months follow-up (data collected 2018–2020). We developed a machine learning (ML) model to predict psychotherapy response at 3 months using baseline survey, administrative, and geospatial variables in a 70% training sample. Model performance was then evaluated in the 30% test sample.
32.0% of patients responded to treatment after 3 months. The best ML model had an AUC (SE) of 0.652 (0.038) in the test sample. Among the one-third of patients ranked by the model as most likely to respond, 50.0% in the test sample responded to psychotherapy. In comparison, among the remaining two-thirds of patients, <25% responded to psychotherapy. The model selected 43 predictors, of which nearly all were self-report variables.
Patients with MDD could pre-emptively be informed of their likelihood of responding to psychotherapy using a prediction tool based on self-report data. This tool could meaningfully help patients and providers in shared decision-making, although parallel information about the likelihood of responding to alternative treatments would be needed to inform decision-making across multiple treatments.
Suicidal thoughts and behaviors (STBs) are major public health concerns among adolescents, and research is needed to identify how risk is conferred over the short term (hours and days). Sleep problems may be associated with elevated risk for STBs, but less is known about this link in youth over short time periods. The current study utilized a multimodal real-time monitoring approach to examine the association between sleep problems (via daily sleep diary and actigraphy) and next-day suicidal thinking in 48 adolescents with a history of STBs during the month following discharge from acute psychiatric care. Results indicated that specific indices of sleep problems assessed via sleep diary (i.e., greater sleep onset latency, nightmares, ruminative thoughts before sleep) predicted next-day suicidal thinking. These effects were significant even when daily sadness and baseline depression were included in the models. Moreover, several associations between daily-level sleep problems and next-day suicidal thinking were moderated by person-level measures of the construct. In contrast, sleep indices assessed objectively (via actigraphy) were either not related to suicidal thinking or were related in the opposite direction from hypothesized. Together, these findings provide some support for sleep problems as a short-term risk factor for suicidal thinking in high-risk adolescents.
OBJECTIVES/SPECIFIC AIMS: The purpose of the present secondary data analysis was to examine the effect of moderate-severe disturbed sleep before the start of radiation therapy (RT) on subsequent RT-induced pain. METHODS/STUDY POPULATION: Analyses were performed on 676 RT-naïve breast cancer patients (mean age 58, 100% female) scheduled to receive RT from a previously completed nationwide, multicenter, phase II randomized controlled trial examining the efficacy of oral curcumin on radiation dermatitis severity. The trial was conducted at 21 community oncology practices throughout the US affiliated with the University of Rochester Cancer Center NCI’s Community Oncology Research Program (URCC NCORP) Research Base. Sleep disturbance was assessed using a single item question from the modified MD Anderson Symptom Inventory (SI) on a 0–10 scale, with higher scores indicating greater sleep disturbance. Total subjective pain as well as the subdomains of pain (sensory, affective, and perceived) were assessed by the short-form McGill Pain Questionnaire. Pain at treatment site (pain-Tx) was also assessed using a single item question from the SI. These assessments were included for pre-RT (baseline) and post-RT. For the present analyses, patients were dichotomized into 2 groups: those who had moderate-severe disturbed sleep at baseline (score≥4 on the SI; n=101) Versus those who had mild or no disturbed sleep (control group; score=0–3 on the SI; n=575). RESULTS/ANTICIPATED RESULTS: Prior to the start of RT, breast cancer patients with moderate-severe disturbed sleep at baseline were younger, less likely to have had lumpectomy or partial mastectomy while more likely to have had total mastectomy and chemotherapy, more likely to be on sleep, anti-anxiety/depression, and prescription pain medications, and more likely to suffer from depression or anxiety disorder than the control group (all p’s≤0.02). Spearman rank correlations showed that changes in sleep disturbance from baseline to post-RT were significantly correlated with concurrent changes in total pain (r=0.38; p<0.001), sensory pain (r=0.35; p<0.001), affective pain (r=0.21; p<0.001), perceived pain intensity (r=0.37; p<0.001), and pain-Tx (r=0.35; p<0.001). In total, 92% of patients with moderate-severe disturbed sleep at baseline reported post-RT total pain compared with 79% of patients in the control group (p=0.006). Generalized linear estimating equations, after controlling for baseline pain and other covariates (baseline fatigue and distress, age, sleep medications, anti-anxiety/depression medications, prescription pain medications, and depression or anxiety disorder), showed that patients with moderate-severe disturbed sleep at baseline had significantly higher mean values of post-RT total pain (by 39%; p=0.033), post-RT sensory pain (by 41%; p=0.046), and post-RT affective pain (by 55%; p=0.035) than the control group. Perceived pain intensity (p=0.066) and pain-Tx (p=0.086) at post-RT were not significantly different between the 2 groups. DISCUSSION/SIGNIFICANCE OF IMPACT: These findings suggest that moderate-severe disturbed sleep prior to RT is an important predictor for worsening of pain at post-RT in breast cancer patients. There could be several plausible reasons for this. Sleep disturbance, such as sleep loss and sleep continuity disturbance, could result in impaired sleep related recovery and repair of tissue damage associated with cancer and its treatment; thus, resulting in the amplification of pain. Sleep disturbance may also reduce pain tolerance threshold through increased sensitization of the central nervous system. In addition, pain and sleep disturbance may share common neuroimmunological pathways. Sleep disturbance may modulate inflammation, which in turn may contribute to increased pain. Further research is needed to confirm these findings and whether interventions targeting sleep disturbance in early phase could be potential alternate approaches to reduce pain after RT.