Search

We developed machine learning models to retrieve surface soil moisture (0-4 cm) from high resolution multispectral imagery, terrain attributes, and local climate covariates. Using a small unmanned aircraft system (UAS) equipped with a multispectral sensor we captured high resolution imagery in part to create a high-resolution digital elevation model (DEM) as well as quantify relative vegetation photosynthetic status. We tested four different machine learning algorithms. The boosted regression tree algorithm provided the best accuracy model with mean absolute error of 3.8 % volumetric water content. The most important variables for the prediction of soil moisture were precipitation, reflectance in the red wavelengths, potential evapotranspiration, and topographic position indices (TPI). Our results demonstrate that the dynamics of soil water status across heterogeneous terrain may be adequately described and predicted by UAS remote sensing data and machine learning. Our modeling approach and the variable importance and relationships we have assessed in this study should be useful for management and environmental modeling tasks where spatially explicit soil moisture information is important.

The article discusses the issue of polypharmacy, particularly central nervous system-active polypharmacy, in older adults with dementia. It highlights the risks associated with multiple medications, including cognitive decline, falls, and mortality. The study emphasizes the importance of communication among prescribers and the need for deprescribing efforts to reduce medication burden. It also suggests potential solutions, such as involving patients and caregivers in the deprescribing process and addressing barriers faced by primary care providers. The findings aim to inform future interventions to manage medication use in older adults with dementia. [Extracted from the article]

Background: The use of potentially inappropriate medications (PIMs) is associated with increased risk of hospitalizations and emergency room visits and varies by racial and ethnic subgroups. Medicare's nationwide medication therapy management (MTM) program requires that Part D plans offer an annual comprehensive medication review (CMR) to all beneficiaries who qualify, and provides a platform to reduce PIM use. The objective of this study was to assess the impact of CMR on PIM discontinuation in Medicare beneficiaries and whether this differed by race or ethnicity. Methods: Retrospective cohort study of community‐dwelling Medicare Part D beneficiaries ≥66 years of age who were eligible for MTM from 2013 to 2019 based on 5% Medicare fee‐for‐service claims data linked to the 100% MTM data file. Among those using a PIM, MTM‐eligible CMR recipients were matched to non‐recipients via sequential stratification. The probability of PIM discontinuation was estimated using regression models that pooled yearly subcohorts accounting for within‐beneficiary correlations. The most common PIMs that were discontinued after CMR were reported. Results: We matched 24,368 CMR recipients to 24,368 CMR non‐recipients during the observation period. Median age was 74–75, 35% were males, most were White beneficiaries (86%–87%), and the median number of PIMs was 1. In adjusted analyses, CMR receipt was positively associated with PIM discontinuation (adjusted relative risk [aRR]: 1.26, 95% CI: 1.20–1.32). There was no evidence of differential impact of CMR by race or ethnicity. The PIMs most commonly discontinued after CMR were glimepiride, zolpidem, digoxin, amitriptyline, and nitrofurantoin. Conclusions: Among Medicare beneficiaries who are using a PIM, CMR receipt was associated with PIM discontinuation, suggesting that greater CMR use could facilitate PIM reduction for all racial and ethnic groups. [ABSTRACT FROM AUTHOR]

Background: Potentially inappropriate medications (PIMs) in older adults are medications in which risks often outweigh benefits and are suggested to be avoided. Worldwide, many distinct guidelines and tools classify PIMs in older adults. Collating these guidelines and tools, mapping them to a medication classification system, and creating a crosswalk will enhance the utility of PIM guidance for research and clinical practice. Methods: We used the Anatomical Therapeutic Chemical (ATC) Classification System, a hierarchical classification system, to map PIMs from eight distinct guidelines and tools (2019 Beers Criteria, Screening Tool for Older Person's Appropriate Prescriptions [STOPP], STOPP‐Japan, German PRISCUS, European Union‐7 Potentially Inappropriate Medication [PIM] list, Centers for Medicare & Medicaid Services [CMS] High‐Risk Medication, Anticholinergic Burden Scale, and Drug Burden Index). Each PIM was mapped to ATC Level 5 (drug) and to ATC Level 4 (drug class). We then used the crosswalk (1) to compare PIMs and PIM drug classes across guidelines and tools to determine the number of PIMs that were index (drug‐induced adverse event) or marker (treatment of drug‐induced adverse event) drug of prescribing cascades, and (2) estimate the prevalence of PIM use in older adults continuously enrolled with fee‐for‐service Medicare in 2018 as use cases. Data visualization and descriptive statistics were used to assess guidelines and tools for both use cases. Results: Out of 480 unique PIMs identified, only three medications—amitriptyline, clomipramine, and imipramine and two drug classes—N06AA (tricyclic antidepressants) and N06AB (selective serotonin reuptake inhibitors), were noted in all eight guidelines and tools. Using the crosswalk, 50% of classes of index drugs and 47% of classes of marker drugs of known prescribing cascades were PIMs. Additionally, 88% of Medicare beneficiaries were dispensed ≥1 PIM across the eight guidelines and tools. Conclusion: We created a crosswalk of eight PIM guidelines and tools to the ATC classification system and created two use cases. Our findings could be used to expand the ease of PIM identification and harmonization for research and clinical practice purposes. [ABSTRACT FROM AUTHOR]

PURPOSE: Several novel therapies for castration-resistant prostate cancer (CRPC) have been approved with randomized phase III studies with continuing observational research either planned or ongoing. Accurately identifying patients with CRPC in electronic health care data is critical for quality observational research, resource allocation, and quality improvement. Previous work in this area has relied on either structured laboratory results and medication data or natural language processing (NLP) methods. However, a computable phenotype using both structured data and NLP identifies these patients with more accuracy. METHODS: The Corporate Data Warehouse (CDW) of the Veterans Health Administration (VHA) was used to collect PCa diagnoses, prostate-specific antigen test results, and information regarding patient characteristics and medication use. The final system used for validation and subsequent analysis combined the NLP system and an algorithm of structured laboratory and medication data to identify patients as being diagnosed with CRPC. Patients with both a documented diagnosis of CRPC and a documented diagnosis of metastatic PCa were classified as having mCRPC by this system. RESULTS: Among 1.2 million veterans with PCa, the International Classification of Diseases (ICD)-10 diagnosis code for CRPC (Z19.2) identifies 3,791 patients from 2016 when the code was created until 2022, compared with the combined algorithm which identifies 14,103, 10,312 more than ICD-10 codes alone, from 2016 to 2022. The combined algorithm showed a sensitivity of 97.9% and a specificity of 99.2%. CONCLUSION: ICD-10 codes proved to be insufficient for capturing CRPC in the VHA CDW data. Using both structured and unstructured data identified more than double the number of patients compared with ICD-10 codes alone. Application of this combined approach drastically improved identification of real-world patients and enables high-quality observational research in mCRPC. [ABSTRACT FROM AUTHOR]