Principles and Practices of Plant-based Irrigation Management

Many consider tools for plant-based irrigation management methods to be the most precise way to manage irrigation in either a research or a commercial settings. Although many types of tools are available, they all measure some aspect of water movement along the soil–plant–atmosphere continuum. This article presents some of the more commonly used tools and the methods involved to properly employ them. In addition, recent literature is reviewed to provide context to the methods themselves and also to highlight each one’s specific advantages and disadvantages. Ultimately, there is no clear winner or “best” tool as all have disadvantages, either due to prohibitive cost, the amount of data output, the difficulty of data interpretation, lack of signal resolution, or lack of dynamic ability to provide decision support. Therefore, we conclude that the user should carefully weigh these varied advantages and disadvantages in the context of their production goals before deciding on a given tool for irrigation management.

A Framework for “Just-in-Time Learning” Decision Support in Organizations

This article describes an integrated “Just-in-Time Learning” framework for providing decision support in organizations. The framework emerges from years of work with the national laboratories and facilities that are under the direction of the United States Department of Energy. The article begins by describing expert systems technology and how it has been used to provide decision support in organizations. This is followed by a discussion of the strengths and weaknesses of expert systems technology for this purpose. Next, a “Just-in-Time Learning” framework is introduced where the theoretical foundation for the framework is described. Afterwards, the other aspects of the framework including the types of knowledge, learners it serves, and how the framework can be utilized for decision support are detailed. Finally, a discussion section summarizes how a Just-in-Time Learning Framework can achieve some of the strengths -- while overcoming some of the weaknesses -- of expert system technology for providing decision support in organizations.

Using Deep Learning Artificial Intelligence Algorithms to Verify N-Nitroso-N-Methylurea and Urethane Positive Control Proliferative Changes in Tg-RasH2 Mouse Carcinogenicity Studies

In Tg-rasH2 carcinogenicity mouse models, a positive control group is treated with a carcinogen such as urethane or N-nitroso-N-methylurea to test study validity based on the presence of the expected proliferative lesions in the transgenic mice. We hypothesized that artificial intelligence–based deep learning (DL) could provide decision support for the toxicologic pathologist by screening for the proliferative changes, verifying the expected pattern for the positive control groups. Whole slide images (WSIs) of the lungs, thymus, and stomach from positive control groups were used for supervised training of a convolutional neural network (CNN). A single pathologist annotated WSIs of normal and abnormal tissue regions for training the CNN-based supervised classifier using INHAND criteria. The algorithm was evaluated using a subset of tissue regions that were not used for training and then additional tissues were evaluated blindly by 2 independent pathologists. A binary output (proliferative classes present or not) from the pathologists was compared to that of the CNN classifier. The CNN model grouped proliferative lesion positive and negative animals at high concordance with the pathologists. This process simulated a workflow for review of these studies, whereby a DL algorithm could provide decision support for the pathologists in a nonclinical study.

Foul accumulation in the NBA

This paper investigates the fouling time distribution of players in the National Basketball Association. A Bayesian analysis is presented based on the assumption that fouling time distributions follow a gamma distribution. Various insights are obtained including the observation that players accumulate fouls at a rate that increases with the current number of fouls. We demonstrate possible ways to incorporate the fouling time distributions to provide decision support to coaches in the management of playing time.

Going off pathway: Problem or good care?

7014 Background: Clinical oncology pathways (COP) provide decision support and benchmarking against national standards. Some organizations provide financial incentives for using COP-recommended treatment (on pathway: OnP). Treatment (Rx) other than COP recommended Rx (off pathway: OffP) is appropriate for some cases. There are limited data on the appropriateness of OffP Rx. This study examines rates and reasons for OffP Rx in one cancer center. Methods: All systemic Rx decisions entered in the ClinicalPath COP from 10/1/18 - 9/30/19 were classified as OnP (including Rx on a clinical trial) or OffP and as adjuvant/neoadjuvant therapy (ADJ) or for metastatic cancer (MET). Oncologists must provide free text reasons for OffP Rx. Records of all OffP care were reviewed by a senior nurse-led team and physician to verify and classify OffP reasons. Cases without clear documentation were referred to the treating oncologist and/or multidisciplinary team for review. Justified OffP reasons (R1-6) were classified as: R1. Documented drug toxicity and/or treatment-limiting co-morbidity; R2. Prior treatment precluding pathway Rx; R3. New drug indication or molecular targeted therapy not in COP; R4. Continuation of Rx started prior to referral; R5. Other clearly documented and reviewed provider or multidisciplinary team rationale; and R6. Patient preference. Results: There were 2,997 COP treatment decisions for 2,389 patients. The OnP rate was higher for ADJ than for MET Rx (87% vs. 78%). Non-justified OffP care accounted for 1% of cases. 69% of OffP Rx was because of known drug toxicity, co-morbidity limiting therapy, prior therapy precluding COP choice, and new drug indications (Table). Conclusions: COPs provide decision support and practice benchmarking. Lower OnP rates for MET Rx likely reflect the nuances of Rx for advanced cancer. Most OffP care was justified and appropriate. Financial incentives that focus on the percentage of COP OnP care could paradoxically harm the quality of care, especially given the high percentage of OffP decisions for reasons of drug toxicity, co-morbidity and new drug indications. [Table: see text]