Personalized Deep Learning for Substance Use in Hawaii: Protocol for a Passive Sensing and Ecological Momentary Assessment Study.

BACKGROUND: Artificial intelligence (AI)-powered digital therapies that detect methamphetamine cravings via consumer devices have the potential to reduce health care disparities by providing remote and accessible care solutions to communities with limited care solutions, such as Native Hawaiian, Filipino, and Pacific Islander communities. However, Native Hawaiian, Filipino, and Pacific Islander communities are understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other racial groups. OBJECTIVE: In this study, we aimed to understand the feasibility of continuous remote digital monitoring and ecological momentary assessments in Native Hawaiian, Filipino, and Pacific Islander communities in Hawaii by curating a novel data set of longitudinal Fitbit (Fitbit Inc) biosignals with the corresponding craving and substance use labels. We also aimed to develop personalized AI models that predict methamphetamine craving events in real time using wearable sensor data. METHODS: We will develop personalized AI and machine learning models for methamphetamine use and craving prediction in 40 individuals from Native Hawaiian, Filipino, and Pacific Islander communities by curating a novel data set of real-time Fitbit biosensor readings and the corresponding participant annotations (ie, raw self-reported substance use data) of their methamphetamine use and cravings. In the process of collecting this data set, we will gain insights into cultural and other human factors that can challenge the proper acquisition of precise annotations. With the resulting data set, we will use self-supervised learning AI approaches, which are a new family of machine learning methods that allows a neural network to be trained without labels by being optimized to make predictions about the data. The inputs to the proposed AI models are Fitbit biosensor readings, and the outputs are predictions of methamphetamine use or craving. This paradigm is gaining increased attention in AI for health care. RESULTS: To date, more than 40 individuals have expressed interest in participating in the study, and we have successfully recruited our first 5 participants with minimal logistical challenges and proper compliance. Several logistical challenges that the research team has encountered so far and the related implications are discussed. CONCLUSIONS: We expect to develop models that significantly outperform traditional supervised methods by finetuning according to the data of a participant. Such methods will enable AI solutions that work with the limited data available from Native Hawaiian, Filipino, and Pacific Islander populations and that are inherently unbiased owing to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/46493.

Establishing a System of Care for Severe and Refractory Dual Disorder in the State of Hawai'i.

Dual disorder is the diagnosis of both substance use disorder and a psychiatric disorder in the same individual. This paper focuses on the cohort of persons with severe and refractory dual disorders (SRDD). This cohort exhibits disproportionately high use of emergency services, poor response to existing care resources, high risk of homelessness, and elevated risk of violent deaths. Clarifying the unique and problematic aspects of SRDD can provide direction for intervention and policy within the system of care in Hawai'i. Data regarding the prevalence of dual disorder in Hawai'i are reviewed along with Hawai'i data on emergency room utilization, and violent death rates relevant to a cohort of individuals with SRDD. The current system of care in Hawai'i is examined. Although not an official component of the public health system or system of care, the O'ahu Community Correctional Center is presented as a potential model for longer-term stabilization for those with SRDD. Interventions from the literature for dual disorders and their implications for SRDD are discussed. Based upon this review, the following recommendations are made: (1) strengthen specific dual disorder diagnosis data collection, including stratification of dual disorder severity, (2) enhance coordination and establish uniform state data governance across public safety, public health, and private sectors, (3) develop a care environment that makes long-term and integrated treatment available, (4) enhance case management services and patient engagement, and (5) encourage policy discussions of longer-term civil commitment for residential treatment for individuals with SRDD.

Fast Growing Plantations for Wood Production - Integration of Ecological Effects and Economic Perspectives.

Biomass crops are perceived as a feasible means to substitute sizeable amounts of fossil fuel in the future. A prospect of CO2 reduction (resp. CO2 neutrality) is credited to biomass fuels, and thus a potential contribution to mitigate climate change. Short rotation coppices (SRCs) with fast growing poplar and willow trees are an option for producing high yields of woody biomass, which is suitable for both energetic and material use. One negative effect that comes along with the establishment of SRC may be a decrease in groundwater recharge, because high rates of transpiration and interception are anticipated. Therefore, it is important to measure, analyze, and model the effects of SRC-planting on landscape water budgets. To analyze the effects on the water budget, a poplar SRC plot was studied by measuring hydrological parameters to be used in the hydrological model WaSim. Results reveal very low or even missing ground water recharge for SRC compared to agricultural land use or grassland, especially succeeding dry years. However, this strong effect on plot level is moderated on the larger spatial scale of catchment level, for which the modeling was also performed. In addition to water, nutrient fluxes and budgets were studied. Nitrogen is still a crucial issue in today's agriculture. Intensive fertilization or increased applications of manure from concentrated livestock breeding are often leading to high loads of nitrate leaching, or enhanced N2O emissions to the atmosphere on arable crop fields. SRC or agroforestry systems on former crop land may offer an option to decrease such N losses, while simultaneously producing woody biomass. This is mainly due to the generally smaller N requirements of woody vegetation, which usually entail no need for any fertilization. The trees supply deep and permanent rooting systems, which can be regarded as a "safety net" to prevent nutrient leaching. Thus, SRC altogether can help to diminish N eutrophication. It is important to offer viable and attractive economic perspectives to farmers and other land managers besides of the potential ecological benefits of SRCs. For this reason, an integrated tool for scenario analysis was developed within the BEST project ("BEAST - Bio-Energy Allocation and Scenario Tool"). It combines ecological assessments with calculations of economic revenue as a basis for a participative regional dialog on sustainable land use and climate protection goals. Results show a substantial capacity for providing renewable energy from economically competitive arable SRC sites while generating ecological synergies.