scholarly journals Exploring Interval Graphs of Rare Diseases in Retrospective Analysis of Outpatient Records

10.29007/l7v8 ◽  
2018 ◽  
Author(s):  
Svetla Boytcheva
Keyword(s):  
Pattern Mining ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Interval Graphs ◽  
Insurance Fund ◽  
Free Text ◽  
Rare Disorders ◽  
Patient History ◽  
Structured Information ◽  
Data Collections

This paper deals with investigation of complex temporal relations between some rare disorders. It proposes an interval graphs approach combined with data mining for patient history pattern mining. The processed data are enriched with context information. Some text mining tools extract entities from free text and deliver additional attributes beyond the structured information about the patients. The test corpora contain pseudonymised reimbursement requests submitted to the Bulgarian National Health Insurance Fund in 2010-2015 for more than 5 million citizens yearly. Experiments were run on 2 data collections. Findings in these two collections are discussed on the basis of comparison between patients with and without rare disorders. Exploration of complex relations in rare-disease data can support analyzes of small size patient pools and assist clinical decision making.

scholarly journals SP2.2.9Using high fidelity simulation to improve hospital-based medical student education

2021 ◽  
Vol 108 (Supplement_7) ◽  
Author(s):  
Marc Huttman ◽  
Hui Fen Koo ◽  
Charlotte Boardman ◽  
Michael Saunders
Keyword(s):  
Medical Students ◽  
Clinical Decision Making ◽  
Medical Student Education ◽  
District General Hospital ◽  
Clinical Decision ◽  
Free Text ◽  
High Fidelity ◽  
High Fidelity Simulation ◽  
Qualitative Feedback ◽  
Before And After

Abstract Introduction The evidence shows that experiential learning has multiple benefits in preparing medical students for foundation training. An immersive ‘on call simulation’ session was designed for final-year medical students at a district general hospital. The aim of this project was to assess how beneficial the sessions were and how they can be improved. Methods Pairs of students received 12 bleeps over 2 hours directing them to wards where mock patient folders were placed. Students prioritised bleeps involving deteriorating patients, chasing results and dealing with nursing queries. Simulated senior input was available from the session facilitator. A structured debrief session allowed discussion of each case. Quantitative feedback was gathered using a sliding scale (measured in percentage) for confidence before and after the session. Qualitative feedback was gathered using a free-text box. Results Four sessions were held between October 2020 and January 2021 for a total of 28 students, of which 26 provided feedback. Average confidence increased from 38% to 66%. 96% of students were ‘extremely satisfied’ with the session. Feedback included: “Incredibly immersive and fun” and “I was made to think through my priorities and decisions”. Improvements could be made by using actors/mannequins to simulate unwell patients and by use of skills models. Conclusion High fidelity simulation training is valuable and should be considered a standard part of the student curriculum. It is particularly suited to final year students who have the required clinical knowledge for foundation training but are still developing confidence in clinical decision making and prioritisation.

scholarly journals DICE: A Drug Indication Classification and Encyclopedia for AI-Based Indication Extraction

2021 ◽  
Vol 4 ◽  
Author(s):  
Arjun Bhatt ◽  
Ruth Roberts ◽  
Xi Chen ◽  
Ting Li ◽  
Skylar Connor ◽  
...  
Keyword(s):  
Language Processing ◽  
Clinical Decision Making ◽  
Short Term Memory ◽  
Drug Repositioning ◽  
External Validation ◽  
Clinical Decision ◽  
Language Models ◽  
Free Text ◽  
Drug Labeling ◽  
Real World Evidence

Drug labeling contains an ‘INDICATIONS AND USAGE’ that provides vital information to support clinical decision making and regulatory management. Effective extraction of drug indication information from free-text based resources could facilitate drug repositioning projects and help collect real-world evidence in support of secondary use of approved medicines. To enable AI-powered language models for the extraction of drug indication information, we used manual reading and curation to develop a Drug Indication Classification and Encyclopedia (DICE) based on FDA approved human prescription drug labeling. A DICE scheme with 7,231 sentences categorized into five classes (indications, contradictions, side effects, usage instructions, and clinical observations) was developed. To further elucidate the utility of the DICE, we developed nine different AI-based classifiers for the prediction of indications based on the developed DICE to comprehensively assess their performance. We found that the transformer-based language models yielded an average MCC of 0.887, outperforming the word embedding-based Bidirectional long short-term memory (BiLSTM) models (0.862) with a 2.82% improvement on the test set. The best classifiers were also used to extract drug indication information in DrugBank and achieved a high enrichment rate (>0.930) for this task. We found that domain-specific training could provide more explainable models without performance sacrifices and better generalization for external validation datasets. Altogether, the proposed DICE could be a standard resource for the development and evaluation of task-specific AI-powered, natural language processing (NLP) models.

scholarly journals Unstructured Text in EMR Improves Prediction of Death after Surgery in Children

2018 ◽  
Author(s):  
Oguz Akbilgic ◽  
Ramin Homayouni ◽  
Kevin Heinrich ◽  
Max Raymond langham, Jr ◽  
Robert Lowell Davis
Keyword(s):  
Risk Score ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Structured Data ◽  
Risk Scores ◽  
Free Text ◽  
Significant Information ◽  
C Statistic ◽  
Surgery Outcomes ◽  
Fold Cross Validation

Text fields in electronic medical records (EMR) contain information on important factors that influence health outcomes, however, they are underutilized in clinical decision making due to their unstructured nature. We analyzed 6,497 inpatient surgical cases with 719,308 free text notes from Le Bonheur Children’s Hospital EMR. We used a text mining approach on preoperative notes to obtain the text-based risk score algorithm as predictive of death within 30 days of surgery. We studied the additional performance obtained by including text-based risk score as a predictor of death along with other structured data based clinical risk factors. The C-statistic of a logistic regression model with 5-fold cross-validation significantly improved from 0.76 to 0.92 when text-based risk scores were included in addition to structured data. We conclude that preoperative free text notes in EMR include significant information that can predict adverse surgery outcomes.

scholarly journals Unstructured Text in EMR Improves Prediction of Death after Surgery in Children

Informatics ◽  
2019 ◽  
Vol 6 (1) ◽  
pp. 4 ◽  
Author(s):  
Oguz Akbilgic ◽  
Ramin Homayouni ◽  
Kevin Heinrich ◽  
Max Langham ◽  
Robert Davis
Keyword(s):  
Risk Score ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Structured Data ◽  
Risk Scores ◽  
Free Text ◽  
Significant Information ◽  
C Statistic ◽  
Surgery Outcomes ◽  
Fold Cross Validation

Text fields in electronic medical records (EMR) contain information on important factors that influence health outcomes, however, they are underutilized in clinical decision making due to their unstructured nature. We analyzed 6497 inpatient surgical cases with 719,308 free text notes from Le Bonheur Children’s Hospital EMR. We used a text mining approach on preoperative notes to obtain a text-based risk score to predict death within 30 days of surgery. In addition, we evaluated the performance of a hybrid model that included the text-based risk score along with structured data pertaining to clinical risk factors. The C-statistic of a logistic regression model with five-fold cross-validation significantly improved from 0.76 to 0.92 when text-based risk scores were included in addition to structured data. We conclude that preoperative free text notes in EMR include significant information that can predict adverse surgery outcomes.

Multiple Approaches to the Diagnosis of Attention Deficit Hyperactivity Disorder

2013 ◽  
Vol 8 (4) ◽  
pp. 44-57 ◽  
Author(s):  
Rui Rijo ◽  
Ricardo Martinho ◽  
Xiaocheng Ge
Keyword(s):  
Decision Making ◽  
Attention Deficit Hyperactivity Disorder ◽  
Attention Deficit ◽  
Clinical Decision Making ◽  
Adult Life ◽  
Clinical Decision ◽  
School Age Children ◽  
Free Text ◽  
Clinical Decisions ◽  
Hyperactivity Disorder

Studies indicate that about 3-7% of school-age children have attention deficit hyperactivity disorder (ADHD). If these disorders are not diagnosed and treated early, its consequences can harshly impair the adult life of the individual. In this context, early diagnosis is critical. Clinical reasoning is a key contributor to the quality of health care. Clinical decisions at the policy level are made within a stochastic domain; decisions for individuals are usually more qualitative. In both cases, poor reasoning can result in an undesirable outcome. Clinical decisions are most typically communicated in a document through free text. Text has significant limitations (particularly ambiguity and poor structuring) whether used for analysis, or to explain the decision-making process. In safety engineering, similar problems are faced in conveying safety arguments to support certification. As a result, approaches have been developed to conveying arguments in ways which improve communication and which are more amenable to analysis. The Goal Structuring Notation (GSN) – a graphical argumentation notation for safety – was developed for those reasons. It has evolved to be one of the most widely used techniques for representing safety arguments. The use of text-mining techniques is another approach in the process of achieving or suggesting a diagnosis to the physician. This paper investigates the relative feasibility of these two approaches and discuss their complementation. Based on a case example, the benefits and problems of adopting GSN and ontology approach in clinical decision-making for ADHD are discussed and illustrated.

scholarly journals KLOSURE: Closing in on open–ended patient questionnaires with text mining

2019 ◽  
Vol 10 (S1) ◽  
Author(s):  
Irena Spasić ◽  
David Owen ◽  
Andrew Smith ◽  
Kate Button
Keyword(s):  
Feature Extraction ◽  
Text Mining ◽  
Clinical Decision Making ◽  
Named Entity Recognition ◽  
Clinical Decision ◽  
Entity Recognition ◽  
Free Text ◽  
Feature Vectors ◽  
Patient Questionnaires

Abstract Background Knee injury and Osteoarthritis Outcome Score (KOOS) is an instrument used to quantify patients’ perceptions about their knee condition and associated problems. It is administered as a 42-item closed-ended questionnaire in which patients are asked to self-assess five outcomes: pain, other symptoms, activities of daily living, sport and recreation activities, and quality of life. We developed KLOG as a 10-item open-ended version of the KOOS questionnaire in an attempt to obtain deeper insight into patients’ opinions including their unmet needs. However, the open–ended nature of the questionnaire incurs analytical overhead associated with the interpretation of responses. The goal of this study was to automate such analysis. We implemented KLOSURE as a system for mining free–text responses to the KLOG questionnaire. It consists of two subsystems, one concerned with feature extraction and the other one concerned with classification of feature vectors. Feature extraction is performed by a set of four modules whose main functionalities are linguistic pre-processing, sentiment analysis, named entity recognition and lexicon lookup respectively. Outputs produced by each module are combined into feature vectors. The structure of feature vectors will vary across the KLOG questions. Finally, Weka, a machine learning workbench, was used for classification of feature vectors. Results The precision of the system varied between 62.8 and 95.3%, whereas the recall varied from 58.3 to 87.6% across the 10 questions. The overall performance in terms of F–measure varied between 59.0 and 91.3% with an average of 74.4% and a standard deviation of 8.8. Conclusions We demonstrated the feasibility of mining open-ended patient questionnaires. By automatically mapping free text answers onto a Likert scale, we can effectively measure the progress of rehabilitation over time. In comparison to traditional closed-ended questionnaires, our approach offers much richer information that can be utilised to support clinical decision making. In conclusion, we demonstrated how text mining can be used to combine the benefits of qualitative and quantitative analysis of patient experiences.

scholarly journals Structured Reporting Using CEUS LI-RADS for the Diagnosis of Hepatocellular Carcinoma (HCC)—Impact and Advantages on Report Integrity, Quality and Interdisciplinary Communication

Cancers ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 534
Author(s):  
Thomas Geyer ◽  
Johannes Rübenthaler ◽  
Constantin Marschner ◽  
Malte von Hake ◽  
Matthias P. Fabritius ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Information Extraction ◽  
Interdisciplinary Communication ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Structured Reporting ◽  
Free Text ◽  
Report Quality ◽  
Quality Of Reports ◽  
The Impact

Background: Our retrospective single-center study aims to evaluate the impact of structured reporting (SR) using a CEUS LI-RADS template on report quality compared to conventional free-text reporting (FTR) in contrast-enhanced ultrasound (CEUS) for the diagnosis of hepatocellular carcinoma (HCC). Methods: We included 50 patients who underwent CEUS for HCC staging. FTR created after these examinations were compared to SR retrospectively generated by using template-based online software with clickable decision trees. The reports were evaluated regarding report completeness, information extraction, linguistic quality and overall report quality by two readers specialized in internal medicine and visceral surgery. Results: SR significantly increased report completeness with at least one key feature missing in 31% of FTR vs. 2% of SR (p < 0.001). Information extraction was considered easy in 98% of SR vs. 86% of FTR (p = 0.004). The trust of referring physicians in the report was significantly increased by SR with a mean of 5.68 for SR vs. 4.96 for FTR (p < 0.001). SR received significantly higher ratings regarding linguistic quality (5.79 for SR vs. 4.83 for FTR (p < 0.001)) and overall report quality (5.75 for SR vs. 5.01 for FTR (p < 0.001)). Conclusions: Using SR instead of conventional FTR increases the overall quality of reports in CEUS examinations of HCC patients and may represent a valuable tool to facilitate clinical decision-making and improve interdisciplinary communication in the future.

Assessing  clinical appropriateness on a population basis within a regional cancer network.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. TPS9155-TPS9155
Author(s):  
Paolo Giovanni Casali ◽  
Lisa F. Licitra ◽  
Rosaria Bufalino ◽  
Fabrizio Pizzo ◽  
Marco Tricomi ◽  
...  
Keyword(s):  
Information Systems ◽  
Cancer Care ◽  
Clinical Decision Making ◽  
Treatment Options ◽  
Clinical Decision ◽  
Medical Decision ◽  
Free Text ◽  
Solid Cancer ◽  
Regional Health Care ◽  
Cancer Network

TPS9155 Background: The Lombardia Cancer Network (ROL: “Rete Oncologica Lombarda”) connects all cancer resources of the Lombardia region, with 9,000,000-plus citizens, to improve quality of cancer care and patient data sharing. Assessment of appropriateness of cancer care on a population basis is an aim. Implementation of electronic records is partial and heterogeneous. However, clinical discharge reports for both inpatients and oupatients are released as “pdf” files onto a secure regional health care information system, accessible by physicians. Methods: ROL includes 58 oncology premises. Clinical practice guidelines are annually updated within this oncology community. For each solid cancer, guidelines enlist all main clinical presentations (“disease phases”), along with their “treatment options” (either “standard”, “individualized”, or “investigational”). ROL upgraded the existing non-structured electronic clinical discharge report into a field-based resource, with both free-text (17) and codified (25) fields. Two codified fields enlist, respectively, disease phases as per guidelines, and the corresponding treatment options. If they match, the strategic medical decision is considered tentatively “appropriate”. Even the report of a single encounter within a disease phase is enough to make this work. Results: Currently, the instrument is being incorporated stepwisely within the information systems of all oncology facilities, though a central web-based tool is also available. More than 36,000 reports were released in 2011. Appropriateness assessment proved feasible on a pilot set of patients. A research project is underway to detect causes of mistakes and mismatches, by automatically analyzing free-text fields. A training effort is ongoing to improve clinicians’ learning curve on semantics. Conclusions: To assess clinical appropriateness on a population basis in a large region, we exploited two key bottlenecks: 1) the electronic discharge report, within patient information flows, to cope with a variety of local information systems; 2) the disease phase, within the cancer-specific clinical decision-making process, to cope with a likely lack of reports from a substantial proportion of encounters.

Preliminary Findings on the Use of Session Questionnaires to Improve Clinician-Client Alliance With Special Consideration to Clinical Education

2015 ◽  
Vol 25 (1) ◽  
pp. 50-60
Author(s):  
Anu Subramanian
Keyword(s):  
Graduate Students ◽  
Clinical Education ◽  
Clinical Decision Making ◽  
Rating Scale ◽  
Treatment Effectiveness ◽  
Clinical Decision ◽  
Added Value ◽  
Therapeutic Outcomes ◽  
Specific Feedback ◽  
Stakeholder Perspective

ASHA's focus on evidence-based practice (EBP) includes the family/stakeholder perspective as an important tenet in clinical decision making. The common factors model for treatment effectiveness postulates that clinician-client alliance positively impacts therapeutic outcomes and may be the most important factor for success. One strategy to improve alliance between a client and clinician is the use of outcome questionnaires. In the current study, eight parents of toddlers who attended therapy sessions at a university clinic responded to a session outcome questionnaire that included both rating scale and descriptive questions. Six graduate students completed a survey that included a question about the utility of the questionnaire. Results indicated that the descriptive questions added value and information compared to using only the rating scale. The students were varied in their responses regarding the effectiveness of the questionnaire to increase their comfort with parents. Information gathered from the questionnaire allowed for specific feedback to graduate students to change behaviors and created opportunities for general discussions regarding effective therapy techniques. In addition, the responses generated conversations between the client and clinician focused on clients' concerns. Involving the stakeholder in identifying both effective and ineffective aspects of therapy has advantages for clinical practice and education.

Clinical Decision-Making for Stroke and Aphasia in the Older Adult

2009 ◽  
Vol 14 (1) ◽  
pp. 4-11 ◽  
Author(s):  
Jacqueline Hinckley
Keyword(s):  
Executive Function ◽  
Cerebrovascular Disease ◽  
Cognitive Abilities ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Cognitive Profile ◽  
Focal Lesion ◽  
Cognitive Profiles ◽  
Supportive Communication ◽  
Spaced Retrieval

Abstract A patient with aphasia that is uncomplicated by other cognitive abilities will usually show a primary impairment of language. The frequency of additional cognitive impairments associated with cerebrovascular disease, multiple (silent or diagnosed) infarcts, or dementia increases with age and can complicate a single focal lesion that produces aphasia. The typical cognitive profiles of vascular dementia or dementia due to cerebrovascular disease may differ from the cognitive profile of patients with Alzheimer's dementia. In order to complete effective treatment selection, clinicians must know the cognitive profile of the patient and choose treatments accordingly. When attention, memory, and executive function are relatively preserved, strategy-based and conversation-based interventions provide the best choices to target personally relevant communication abilities. Examples of treatments in this category include PACE and Response Elaboration Training. When patients with aphasia have co-occurring episodic memory or executive function impairments, treatments that rely less on these abilities should be selected. Examples of treatments that fit these selection criteria include spaced retrieval and errorless learning. Finally, training caregivers in the use of supportive communication strategies is helpful to patients with aphasia, with or without additional cognitive complications.

Sign in / Sign up

Export Citation Format

Share Document