Toward Concurrent Identification of Human Activities with a Single Unifying Neural Network Classification: First Step.

The characterization of human behavior in real-world contexts is critical for developing a comprehensive model of human health. Recent technological advancements have enabled wearables and sensors to passively and unobtrusively record and presumably quantify human behavior. Better understanding human activities in unobtrusive and passive ways is an indispensable tool in understanding the relationship between behavioral determinants of health and diseases. Adult individuals (N = 60) emulated the behaviors of smoking, exercising, eating, and medication (pill) taking in a laboratory setting while equipped with smartwatches that captured accelerometer data. The collected data underwent expert annotation and was used to train a deep neural network integrating convolutional and long short-term memory architectures to effectively segment time series into discrete activities. An average macro-F1 score of at least 85.1 resulted from a rigorous leave-one-subject-out cross-validation procedure conducted across participants. The score indicates the method's high performance and potential for real-world applications, such as identifying health behaviors and informing strategies to influence health. Collectively, we demonstrated the potential of AI and its contributing role to healthcare during the early phases of diagnosis, prognosis, and/or intervention. From predictive analytics to personalized treatment plans, AI has the potential to assist healthcare professionals in making informed decisions, leading to more efficient and tailored patient care.

Mesocorticolimbic system reactivity to alcohol use-related visual cues as a function of alcohol sensitivity phenotype: A pilot fMRI study.

Low sensitivity (LS) to alcohol is a risk factor for alcohol use disorder (AUD). Compared to peers with high sensitivity (HS), LS individuals drink more, report more problems, and exhibit potentiated alcohol cue reactivity (ACR). Heightened ACR suggests LS confers AUD risk via incentive sensitization, which is thought to take place in the mesocorticolimbic system. This study examined neural ACR in LS and HS individuals. Young adults (N = 32, M age=20.3) were recruited based on the Alcohol Sensitivity Questionnaire (HS: n = 16; LS: n = 16; 9 females/group). Participants completed an event-related fMRI ACR task. Group LS had higher ACR in left ventrolateral prefrontal cortex than group HS. In group LS, ACR in left caudomedial orbitofrontal cortex or left putamen was low at low alcohol use levels and high at heavier or more problematic alcohol use levels, whereas the opposite was true in group HS. Alcohol use level also was associated with the level of ACR in left substantia nigra among males in group LS. Taken together, results suggest elevated mesocorticolimbic ACR among LS individuals, especially those using alcohol at hazardous levels. Future studies with larger samples are warranted to determine the neurobiological loci underlying LS-based amplified ACR and AUD risk.

Virtual reality and neurofeedback as a supportive approach to managing cancer symptoms for patients receiving treatment: A brief report of a feasibility trial.

OBJECTIVES: Managing cancer symptoms while patients receive systemic treatment remains a challenge in oncology. The use of complementary and alternative medicine (CAM) approaches like virtual reality (VR) and neurofeedback (NF) in tandem with systemic treatment might reduce symptom burden for patients. The combination of VR + NF as a CAM intervention approach is novel and understudied, particularly as it relates to supportive cancer care. The purpose of this study is to summarize our VR + NF study protocol and share preliminary results regarding study retention (across 2 treatment sessions) and preliminary impact of VR or VR + NF on patient-reported outcomes such as anxiety and pain. METHODS: We utilized a parallel arm trial design to compare preliminary impact of VR only and VR + NF on cancer symptoms among patients who are actively receiving cancer treatment. RESULTS: Sixty-seven percent (n = 20) of participants returned to participate in a second VR session, and the rates of return were the same between the VR groups. Patients in the VR + NF group showed improvements in anxiety after both sessions, while patients in the VR only group showed significant improvements in pain and depression after both sessions. Patients in the VR + NF group showed improved pain after session 1. SIGNIFICANCE OF RESULTS: This study demonstrates that patients can be retained over multiple treatment sessions and that VR and NF remain promising treatment approaches with regard to impact on patient-reported outcomes like anxiety and pain.

A systematic review of cannabis health warning research.

Background: Cannabis legalization provides an opportunity to communicate with consumers through mandated health warnings on cannabis packaging. However, research on cannabis health warnings is a nascent field. Therefore, a review is needed to synthesize cannabis health warning research and inform ongoing policy discussions. Methods: This paper used systematic review guidelines to search online databases, including PubMed Central, Scopus, Web of Science, Jstor, Communication and Mass Media Complete, Medline, PsycINFO, and Google Scholar. Search strings combined the terms "cannabis" or "marijuana" with "health warning" or "health warning message" or "warning label" or "health warning label" or "health information label." Results were synthesized narratively. Results: The search identified 90 research articles. After screening, 17 studies on the impact of cannabis health warnings were retained. Retained studies focused on the hypothetical effects of cannabis health warnings (n = 11; 64.7 %) and "real world" effects of implementing warnings post-legalization (n = 6; 35.3 %). Evidence indicated mandated cannabis health warnings improved noticing and recall of health warning content. Cannabis health warnings describing risks of addiction were consistently rated the least effective. Pictorial cannabis health warnings generally outperformed text-only warnings when displayed on their own, while experiments with warnings on products had mixed results. Cannabis health warnings decreased product appeal, mainly when package branding was minimized. Conclusions: Health warnings on cannabis packaging are an important strategy to communicate risk to consumers. Mandating warnings increased notice, recall, and health knowledge. Warnings with pictures and describing specific risks were most effective, as was showing warnings without product branding.

Mindfulness-Oriented Recovery Enhancement for Veterans and Military Personnel on Long-Term Opioid Therapy for Chronic Pain: A Randomized Clinical Trial.

OBJECTIVE: This randomized clinical trial evaluated the efficacy of Mindfulness-Oriented Recovery Enhancement (MORE) among past and present U.S. military personnel with prescriptions for long-term opioid therapy for chronic pain. METHODS: In this clinical trial, 230 past and present military personnel with prescriptions for long-term opioid therapy were randomized in a 1:1 ratio to MORE or supportive psychotherapy (initially delivered in person and then via videoconferencing after the onset of the COVID-19 pandemic). Primary outcomes were chronic pain, measured by the Brief Pain Inventory, and aberrant drug-related behaviors, measured by the Current Opioid Misuse Measure, through 8 months of follow-up. Opioid dose was a key secondary outcome. Other outcomes included psychiatric symptoms, catastrophizing, positive affect, ecological momentary assessments of opioid craving, and opioid attentional bias. RESULTS: MORE was superior to supportive psychotherapy through the 8-month follow-up in reducing pain-related functional interference, pain severity, and opioid dose. MORE reduced daily opioid dose by 20.7%, compared with a dose reduction of 3.9% with supportive psychotherapy. Although there was no overall between-group difference in opioid misuse, the in-person MORE intervention outperformed supportive psychotherapy for reducing opioid misuse. MORE reduced anhedonia, pain catastrophizing, craving, and opioid attentional bias and increased positive affect to a greater extent than supportive psychotherapy. MORE also modulated therapeutic processes, including mindful reinterpretation of pain sensations, nonreactivity, savoring, positive attention, and reappraisal. CONCLUSIONS: Among past and present U.S. military personnel, MORE led to sustained decreases in chronic pain, opioid use, craving, and opioid cue reactivity. MORE facilitated opioid dose reduction while preserving adequate pain control and preventing mood disturbances, suggesting its utility for safe opioid tapering.