Temporal detection and analysis of guideline interactions

Anselma, Luca; Piovesan, Luca; Terenziani, Paolo

doi:10.1016/j.artmed.2017.01.001

Cited by 28 publications

(26 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first step in the extension of GLARE to cope with comorbidities was the identification of the different tasks to be solved. In strict cooperation with the physicians in our team, we identified the following tasks: (1) The detection of interactions occurring between CIGs 2The management of the interactions 3The final merging of the CIGs We have separately discussed in technical detail our techniques to cope with each task independently of the others in previous publications, mostly in conference papers (interaction detection [9], interaction management [10], conciliation [11] and temporal reasoning for comorbidities [12], [13]). Notably, to cope with the medical problem, several advances with respect to the AI state of the art were achieved, such as the treatment of complexand not explored yettemporal issues [13], and an innovative approach to conditional plan merging [11].…”

Section: Glare-sscpm: General Architecture and Behavior Of The Systemmentioning

confidence: 99%

“…For instance, during interaction detection, temporal reasoning must be used to check whether possible interaction can actually occur or not, given the temporal information available in the knowledge base (temporal constraints between actions and the variations they cause) and in the CIGs (temporal constraints between actions), and the time of execution of previous actions on the patient. We have chosen to devote a specific module, the Temporal module [13] in Figure 1, operating as a knowledge server, to cope with temporal constraints and temporal reasoning. Our treatment of temporal constraints is grounded on the STP framework, that we have extended along several directions to support several facilities, such as checking whether two actions may temporally interact, or determining execution times of some future actions to avoid some interactions.…”

Section: Temporal Modulementioning

confidence: 99%

See 1 more Smart Citation

GLARE-SSCPM: an Intelligent Systemto Support the Treatment of Comorbid Patients

2024

Self Cite

View full text Add to dashboard Cite

The development of software tools supporting physicians in the treatment of comorbid patients is a challenging goal and a "hot topic" in Medical Informatics and Artificial Intelligence. Computer Interpretable Guidelines (CIGs) are consolidated tools to support physicians with evidencebased recommendations in the treatment of patients affected by a specific disease. However, the applications of two or more CIGs on comorbid patients is critical, since dangerous interactions between actions from different CIGs may arise. GLARE-SSCPM is the first tool supporting, in an integrated way, (i) the knowledge-based detection of interactions, (ii) the management of the interactions, and (iii) the final "merge" of (part of) the CIGs operating on the patient. GLARE-SSCPM is characterized by being very supportive to physicians, providing them support for focusing, interaction detection, and for an "hypothesize and test" approach to manage the detected interactions. To achieve such goals, it provides advanced Artificial Intelligence techniques. Preliminary tests in the educational context, within the RoPHS project, have provided encouraging results.

show abstract

Section: Glare-sscpm: General Architecture and Behavior Of The Systemmentioning

confidence: 99%

Section: Temporal Modulementioning

confidence: 99%

GLARE-SSCPM: an Intelligent Systemto Support the Treatment of Comorbid Patients

2024

Self Cite

View full text Add to dashboard Cite

show abstract

“…, … , -∈ " denote the s lowest qualitative values in the scale " (i.e., # = " ( ), 1 ≤ ≤ ). ■ For instance, the constraint between two consecutive administrations of NA (NA1 and NA2) in Example 2 can be represented through the "compact" PyP_STP constraint ⟨ 1, 2, ⟨⟨ [10,15], ⟩, ⟨ [11,13], ⟩, ⟨ [12,12], ℎ ℎ⟩⟩⟩.…”

Section: Definition 2 Pyramid Preference Function (Ppf) a Pyramid Pmentioning

confidence: 99%

“…For example, the "compact" PyP_STP ⟨ 1, 2, ⟨⟨ [10,15], ⟩, ⟨ [11,13], ⟩, ⟨ [12,12], ℎ ℎ⟩⟩⟩ represents the fact that the difference between NA2 and NA1 has preference "high" if it is exactly 12, "medium" if it is 11 or 13, and "low" if it is 10, or between 14 and 15.…”

Section: Definition 2 Pyramid Preference Function (Ppf) a Pyramid Pmentioning

confidence: 99%

Temporal Reasoning with Layered Preferences

Anselma

Mazzei

Piovesan

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Temporal representation and temporal reasoning is a central in Artificial Intelligence. The literature is moving to the treatment of "non-crisp" temporal constraints, in which also preferences or probabilities are considered. However, most approaches only support numeric preferences, while, in many domain applications, users naturally operate on "layered" scales of values (e.g., Low, Medium, High), which are domain-and task-dependent. For many tasks, including decision support, the evaluation of the minimal network of the constraints (i.e., the tightest constraints) is of primary importance. We propose the first approach in the literature coping with layered preferences on quantitative temporal constraints. We extend the widely used simple temporal problem (STP) framework to consider layered user-defined preferences, proposing (i) a formal representation of quantitative constraints with layered preferences, and (ii) a temporal reasoning algorithm, based on the general algorithm Compute-Summaries, for the propagation of such temporal constraints. We also prove that our temporal reasoning algorithm evaluates the minimal network.

show abstract

“…The quality of timing fragments directly affects the temporal accuracy for recognizing the behavior. Many methods use the approach of generating candidate regions and then categorizing the candidates [12]. The important factor is that the candidate quality must be high, so the number of candidates is reduced as much as possible while ensuring the average recall rate.…”

Section: Introductionmentioning

confidence: 99%

Human Activity Recognition and Location Based on Temporal Analysis

Ding

Gong

et al. 2018

Journal of Engineering

View full text Add to dashboard Cite

Current methods of human activity recognition face many challenges, such as the need for multiple sensors, poor implementation, unreliable real-time performance, and lack of temporal location. In this research, we developed a method for recognizing and locating human activities based on temporal action recognition. For this work, we used a multilayer convolutional neural network (CNN) to extract features. In addition, we used refined actionness grouping to generate precise region proposals. Then, we classified the candidate regions by employing an activity classifier based on a structured segmented network and a cascade design for end-to-end training. Compared with previous methods of action classification, the proposed method adds the time boundary and effectively improves the detection accuracy. To test this method empirically, we conducted experiments utilizing surveillance video of an offshore oil production plant. Three activities were recognized and located in the untrimmed long video: standing, walking, and falling. The accuracy of the results proved the effectiveness and real-time performance of the proposed method, demonstrating that this approach has great potential for practical application.

show abstract

Temporal detection and analysis of guideline interactions

Cited by 28 publications

References 36 publications

GLARE-SSCPM: an Intelligent Systemto Support the Treatment of Comorbid Patients

GLARE-SSCPM: an Intelligent Systemto Support the Treatment of Comorbid Patients

Temporal Reasoning with Layered Preferences

Human Activity Recognition and Location Based on Temporal Analysis

Contact Info

Product

Resources

About