scholarly journals Contextual Autocomplete: A Novel User Interface Using Machine Learning to Improve Ontology Usage and Structured Data Capture for Presenting Problems in the Emergency Department

2017 ◽  
Author(s):  
Nathaniel R. Greenbaum ◽  
Yacine Jernite ◽  
Yoni Halpern ◽  
Shelley Calder ◽  
Larry A. Nathanson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
User Interface ◽  
Vital Signs ◽  
Structured Data ◽  
Data Capture ◽  
Free Text ◽  
Presenting Problems ◽  
Before And After

AbstractObjectiveTo determine the effect of contextual autocomplete, a user interface that uses machine learning, on the efficiency and quality of documentation of presenting problems (chief complaints) in the emergency department (ED).Materials and MethodsWe used contextual autocomplete, a user interface that ranks concepts by their predicted probability, to help nurses enter data about a patient’s reason for visiting the ED. Predicted probabilities were calculated using a previously derived model based on triage vital signs and a brief free text note. We evaluated the percentage and quality of structured data captured using a prospective before-and-after study design.ResultsA total of 279,231 patient encounters were analyzed. Structured data capture improved from 26.2% to 97.2% (p<0.0001). During the post-implementation period, presenting problems were more complete (3.35 vs 3.66; p=0.0004), as precise (3.59 vs. 3.74; p=0.1), and higher in overall quality (3.38 vs. 3.72; p=0.0002). Our system reduced the mean number of keystrokes required to document a presenting problem from 11.6 to 0.6 (p<0.0001), a 95% improvement.DiscussionWe have demonstrated a technique that captures structured data on nearly all patients. We estimate that our system reduces the number of man-hours required annually to type presenting problems at our institution from 92.5 hours to 4.8 hours.ConclusionImplementation of a contextual autocomplete system resulted in improved structured data capture, ontology usage compliance, and data quality.

scholarly journals Predicting adult neuroscience intensive care unit admission from emergency department triage using a retrospective, tabular-free text machine learning approach

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Eyal Klang ◽  
Benjamin R. Kummer ◽  
Neha S. Dangayach ◽  
Amy Zhong ◽  
M. Arash Kia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Learning Model ◽  
Free Text ◽  
Combined Model ◽  
Text Data ◽  
Machine Learning Model ◽  
Record Data

AbstractEarly admission to the neurosciences intensive care unit (NSICU) is associated with improved patient outcomes. Natural language processing offers new possibilities for mining free text in electronic health record data. We sought to develop a machine learning model using both tabular and free text data to identify patients requiring NSICU admission shortly after arrival to the emergency department (ED). We conducted a single-center, retrospective cohort study of adult patients at the Mount Sinai Hospital, an academic medical center in New York City. All patients presenting to our institutional ED between January 2014 and December 2018 were included. Structured (tabular) demographic, clinical, bed movement record data, and free text data from triage notes were extracted from our institutional data warehouse. A machine learning model was trained to predict likelihood of NSICU admission at 30 min from arrival to the ED. We identified 412,858 patients presenting to the ED over the study period, of whom 1900 (0.5%) were admitted to the NSICU. The daily median number of ED presentations was 231 (IQR 200–256) and the median time from ED presentation to the decision for NSICU admission was 169 min (IQR 80–324). A model trained only with text data had an area under the receiver-operating curve (AUC) of 0.90 (95% confidence interval (CI) 0.87–0.91). A structured data-only model had an AUC of 0.92 (95% CI 0.91–0.94). A combined model trained on structured and text data had an AUC of 0.93 (95% CI 0.92–0.95). At a false positive rate of 1:100 (99% specificity), the combined model was 58% sensitive for identifying NSICU admission. A machine learning model using structured and free text data can predict NSICU admission soon after ED arrival. This may potentially improve ED and NSICU resource allocation. Further studies should validate our findings.

scholarly journals Bowel preparation for performing a colonoscopy: prospective randomized comparison study between a low-volume solution of polyethylene glycol and bisacodyl versus bisacodyl and a mannitol solution

2012 ◽  
Vol 49 (2) ◽  
pp. 162-168 ◽  
Author(s):  
Manoel Carlos Vieira ◽  
Claudio Lyoiti Hashimoto ◽  
Flair José Carrilho
Keyword(s):  
Polyethylene Glycol ◽  
Vital Signs ◽  
Abdominal Distension ◽  
Similar Efficacy ◽  
Preparation Methods ◽  
Gold Standard Method ◽  
Mannitol Solution ◽  
Before And After ◽  
Glycol Solution

CONTEXT: Colonoscopy is currently the gold standard method to examine the colon, the rectum and the terminal ileum. In order to perform the colonoscopy, it is necessary to clean the bowel and use medications that are generally poorly tolerated by the patients. OBJECTIVE: Compare the tolerability, acceptability, safety and efficacy of two solutions used for intestinal preparation for a colonoscopy. METHODS: One hundred patients matched for sex and age were prospective randomized into two groups. Polyethylene glycol group received bisacodyl 10 mg plus 1 L of polyethylene glycol the night before and 1 L on the day of the exam. Mannitol group received bisacodyl 20 mg the day before and 1 L of a 10% mannitol solution on the day of the exam. The diet was the same for both groups. Tolerability and acceptability were measured using previously validated questionnaires. In terms of safety, variations in vital signs before and after the preparation were recorded, in addition to any complications. The quality of the preparation was graded based on the Boston and Ottawa scales. RESULTS: Ninety-six percent (96%) completed the study. As for tolerability, the mannitol preparation group exhibited a significantly higher frequency of nausea, vomiting, abdominal pain, and abdominal distension than polyethylene glycol group (P < 0.05). Acceptability was significantly better in polyethylene glycol group. The polyethylene glycol solution has also previously been shown to be safer than mannitol. No difference was observed in the quality of the preparation between the two preparation methods. CONCLUSIONS: The following conclusions can be made: polyethylene glycol solution had higher tolerability, acceptability, and safety than the mannitol and should be used instead of mannitol. Both preparation solutions have similar efficacy.

scholarly journals Audit of documentation proficiency of emergency department patients who are discharged against medical advice before and after implementation of a checklist

2016 ◽  
Vol 5 (4) ◽  
pp. 28
Author(s):  
Sze Joo Juan ◽  
Ghee Hian Lim ◽  
Beng Leong Lim
Keyword(s):  
Emergency Department ◽  
Primary Outcome ◽  
Medical Advice ◽  
Against Medical Advice ◽  
Documentation Quality ◽  
Before And After ◽  
Discharge Against Medical Advice ◽  
Emergency Department Patients ◽  
A Prospective Study

Objective: Documentation of the discharge against medical advice (AMA) is poorly performed in the emergency department (ED). Little is known about the impacts of a checklist on this. Our study aimed to compare the quality of AMA documentation before and after implementation of a checklist.Methods: A retrospective review was conducted followed by a prospective study; each over three months of AMA interactions in our ED pre and post implementation of a checklist. An 11-point checklist was used to determine documentation quality during these two periods. Quality was assessed based on the number of points fulfilled on this tool. Documentation was classified as “good” (8-11), “average” (4-7) and “poor” (0-3). The primary outcome measured was the proportions of discharged AMA records that showed “good”, “average” and “poor” documentation. Secondary outcomes were compliance rates to each of the categories of the checklist before and after its use.Results: 339 and 309 complete records were retrieved from the retrospective and prospective arms respectively. The proportions of case records in the three grades before and after use of the checklist respectively were: poor, 199/339 (59%) vs. 7/313 (2%); fair, 133/339 (39%) vs. 66/313 (21%) and good 7/339 (2%) vs. 240/313 (77%); all p-values were statistically significant. There were also statistically significant differences in compliance rates to each of the categories of the checklist pre and post checklist implementation.Conclusions: This study shows improvement in quality and compliance rates in the audit categories after the implementation of an AMA checklist.

scholarly journals Comparison of machine learning classifiers for influenza detection from emergency department free-text reports

2015 ◽  
Vol 58 ◽  
pp. 60-69 ◽  
Author(s):  
Arturo López Pineda ◽  
Ye Ye ◽  
Shyam Visweswaran ◽  
Gregory F. Cooper ◽  
Michael M. Wagner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Free Text ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

scholarly journals Technologies for Complex Intelligent Clinical Data Analysis

2016 ◽  
Vol 71 (2) ◽  
pp. 160-171 ◽  
Author(s):  
A. A. Baranov ◽  
L. S. Namazova-Baranova ◽  
I. V. Smirnov ◽  
D. A. Devyatkin ◽  
A. O. Shelmanov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Chronic Diseases ◽  
Clinical Information ◽  
Structured Data ◽  
Unstructured Data ◽  
Intelligent Analysis ◽  
Pediatric Center

The paper presents the system for intelligent analysis of clinical information. Authors describe methods implemented in the system for clinical information retrieval, intelligent diagnostics of chronic diseases, patient’s features importance and for detection of hidden dependencies between features. Results of the experimental evaluation of these methods are also presented.Background: Healthcare facilities generate a large flow of both structured and unstructured data which contain important information about patients. Test results are usually retained as structured data but some data is retained in the form of natural language texts (medical history, the results of physical examination, and the results of other examinations, such as ultrasound, ECG or X-ray studies). Many tasks arising in clinical practice can be automated applying methods for intelligent analysis of accumulated structured array and unstructured data that leads to improvement of the healthcare quality.Aims: the creation of the complex system for intelligent data analysis in the multi-disciplinary pediatric center.Materials and methods: Authors propose methods for information extraction from clinical texts in Russian. The methods are carried out on the basis of deep linguistic analysis. They retrieve terms of diseases, symptoms, areas of the body and drugs. The methods can recognize additional attributes such as «negation» (indicates that the disease is absent), «no patient» (indicates that the disease refers to the patient’s family member, but not to the patient), «severity of illness», «disease course», «body region to which the disease refers». Authors use a set of hand-drawn templates and various techniques based on machine learning to retrieve information using a medical thesaurus. The extracted information is used to solve the problem of automatic diagnosis of chronic diseases. A machine learning method for classification of patients with similar nosology and the method for determining the most informative patients’ features are also proposed.Results: Authors have processed anonymized health records from the pediatric center to estimate the proposed methods. The results show the applicability of the information extracted from the texts for solving practical problems. The records of patients with allergic, glomerular and rheumatic diseases were used for experimental assessment of the method of automatic diagnostic. Authors have also determined the most appropriate machine learning methods for classification of patients for each group of diseases, as well as the most informative disease signs. It has been found that using additional information extracted from clinical texts, together with structured data helps to improve the quality of diagnosis of chronic diseases. Authors have also obtained pattern combinations of signs of diseases.Conclusions: The proposed methods have been implemented in the intelligent data processing system for a multidisciplinary pediatric center. The experimental results show the availability of the system to improve the quality of pediatric healthcare. 

scholarly journals EP11 Using machine learning to recover unrecorded prehospital data

2021 ◽  
Vol 38 (9) ◽  
pp. A5.3-A6
Author(s):  
Thilo Reich ◽  
Adam Bancroft ◽  
Marcin Budka
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Vital Signs ◽  
Machine Learning Algorithms ◽  
Free Text ◽  
Patient Records ◽  
Electronic Patient Records ◽  
Minority Class ◽  
South Central ◽  
Tree Classifier

BackgroundThe recording practices, of electronic patient records for ambulance crews, are continuously developing. South Central Ambulance Service (SCAS) adapted the common AVPU-scale (Alert, Voice, Pain, Unresponsive) in 2019 to include an option for ‘New Confusion’. Progressing to this new AVCPU-scale made comparisons with older data impossible. We demonstrate a method to retrospectively classify patients into the alertness levels most influenced by this update.MethodsSCAS provided ~1.6 million Electronic Patient Records, including vital signs, demographics, and presenting complaint free-text, these were split into training, validation, and testing datasets (80%, 10%, 10% respectively), and under sampled to the minority class. These data were used to train and validate predictions of the classes most affected by the modification of the scale (Alert, New Confusion, Voice).A transfer-learning natural language processing (NLP) classifier was used, using a language model described by Smerity et al. (2017) to classify the presenting complaint free-text.A second approach used vital signs, demographics, conveyance, and assessments (30 metrics) for classification. Categorical data were binary encoded and continuous variables were normalised. 20 machine learning algorithms were empirically tested and the best 3 combined into a voting ensemble combining three vital-sign based algorithms (Random Forest, Extra Tree Classifier, Decision Tree) with the NLP classifier using a Random Forest output layer.ResultsThe ensemble method resulted in a weighted F1 of 0.78 for the test set. The sensitivities/specificities for each of the classes are: 84%/ 90% (Alert), 73%/ 89% (Newly Confused) and 68%/ 93% (Voice).ConclusionsThe ensemble combining free text and vital signs resulted in high sensitivity and specificity when reclassifying the alertness levels of prehospital patients. This study demonstrates the capabilities of machine learning classifiers to recover missing data, allowing the comparison of data collected with different recording standards.

scholarly journals Leveraging AI and Machine Learning for National Student Survey: Actionable Insights from Textual Feedback to Enhance Quality of Teaching and Learning in UK’s Higher Education

2022 ◽  
Vol 12 (1) ◽  
pp. 514
Author(s):  
Raheel Nawaz ◽  
Quanbin Sun ◽  
Matthew Shardlow ◽  
Georgios Kontonatsios ◽  
Naif R. Aljohani ◽  
...  
Keyword(s):  
Higher Education ◽  
Machine Learning ◽  
Teaching And Learning ◽  
Tertiary Education ◽  
Likert Scale ◽  
Supervised Machine Learning ◽  
Free Text ◽  
Student Survey ◽  
Quality Of Teaching

Students’ evaluation of teaching, for instance, through feedback surveys, constitutes an integral mechanism for quality assurance and enhancement of teaching and learning in higher education. These surveys usually comprise both the Likert scale and free-text responses. Since the discrete Likert scale responses are easy to analyze, they feature more prominently in survey analyses. However, the free-text responses often contain richer, detailed, and nuanced information with actionable insights. Mining these insights is more challenging, as it requires a higher degree of processing by human experts, making the process time-consuming and resource intensive. Consequently, the free-text analyses are often restricted in scale, scope, and impact. To address these issues, we propose a novel automated analysis framework for extracting actionable information from free-text responses to open-ended questions in student feedback questionnaires. By leveraging state-of-the-art supervised machine learning techniques and unsupervised clustering methods, we implemented our framework as a case study to analyze a large-scale dataset of 4400 open-ended responses to the National Student Survey (NSS) at a UK university. These analyses then led to the identification, design, implementation, and evaluation of a series of teaching and learning interventions over a two-year period. The highly encouraging results demonstrate our approach’s validity and broad (national and international) application potential—covering tertiary education, commercial training, and apprenticeship programs, etc., where textual feedback is collected to enhance the quality of teaching and learning.

scholarly journals The association between the transfer of emergency department admitted patients to inpatient hallways and outcomes of oncology patients

2015 ◽  
Vol 4 (2) ◽  
pp. 1 ◽  
Author(s):  
Charles Lim ◽  
Matthew C. Cheung ◽  
Maureen E. Trudeau ◽  
Kevin R. Imrie ◽  
Ben De Mendonca ◽  
...  
Keyword(s):  
Emergency Department ◽  
Length Of Stay ◽  
Patient Flow ◽  
Vital Signs ◽  
Medication Administration ◽  
Oncology Patients ◽  
Flow Quality ◽  
Ed Crowding ◽  
The Impact

Objective: A protocol was implemented to ease Emergency Department (ED) crowding by moving suitable admitted patients into inpatient hallway beds (HALL) or off-service beds (OFF) when beds on an admitting service’s designated ward (ON) were not available. This study assessed the impact of hallway and off-service oncology admissions on ED patient flow, quality of care and patient satisfaction.Methods: Retrospective and prospective data were collected on patients admitted to the medical oncology service from Jan 1 to Dec 31, 2011. Data on clinician assessments and time performance measures were collected. Satisfaction surveys were prospectively administered to all patients. Results: Two hundred and ninty-seven patients (117 HALL, 90 OFF, 90 ON) were included in this study. There were no significant differences between groups for frequency of physician assessments, physical exam maneuvers at initial physician visit, time to complete vital signs or time to medication administration. The median (IQR) time spent admitted in the ED prior to departure from the ED was significantly longer for HALL patients (5.53 hrs [1.59-13.03 hrs]) compared to OFF patients (2.00 hrs [0.37-3.69 hrs]) and ON patients (2.18 hrs [0.15-5.57 hrs]) (p < .01). Similarly, the median (IQR) total ED length of stay was significantly longer for HALL patients (13.82 hrs [7.43-20.72 hrs]) compared to OFF patients (7.18 hrs [5.72-11.42 hrs]) and ON patients (9.34 hrs [5.43-14.06 hrs]) (p < .01). HALL patients gave significantly lower overall satisfaction scores with mean (SD) satisfaction scores for HALL, OFF and ON patients being 3.58 (1.20), 4.23 (0.58) and 4.29 (0.69) respectively (p < .01). Among HALL patients, 58% were not comfortable being transferred into the hallway and 4% discharged themselves against medical advice. Conclusions: The protocol for transferring ED admitted patients to inpatient hallway beds did not reduce ED length of stay for oncology patients. The timeliness and frequency of clinical assessments were not compromised; however, patient satisfaction was decreased.

scholarly journals P019: Prehospital diversion of intoxicated patients to a detoxification facility vs the emergency department: safety and compliance of an EMS direct transport protocol

CJEM ◽  
2017 ◽  
Vol 19 (S1) ◽  
pp. S84
Author(s):  
V. Bismah ◽  
J. Prpic ◽  
S. Michaud ◽  
N. Sykes
Keyword(s):  
Emergency Department ◽  
Medical Records ◽  
Vital Signs ◽  
Transport Protocol ◽  
Improve Quality ◽  
Danger Zone ◽  
Patient Morbidity ◽  
Protocol Compliance ◽  
Withdrawal Management

Introduction: Prehospital transport of patients to an alternative destination (diversion) has been proposed as part of a solution to overcrowding in emergency departments (ED). We evaluated compliance and safety of an EMS bypass protocol allowing paramedics to transport intoxicated patients directly to an alternate facility [Withdrawal Management Services (WMS)], bypassing the ED. Patients were eligible for diversion if they were ≥18 years old, classified as CTAS level III-IV, scored &lt;4 on the Prehospital Early Warning (PHEW) score, and did not have any vital sign parameters in a danger zone (as per PHEW score criteria). Methods: A retrospective analysis was conducted on intoxicated patients presenting to Sudbury EMS. Data was abstracted from EMS reports, hospital medical records, and discharge forms from WMS. Protocol compliance was measured using missed protocol opportunities (patients eligible for diversion but taken directly to the ED) and protocol noncompliance rates; protocol safety was measured using protocol failure (presentation to ED within 48 hours of appropriate diversion) and patient morbidity rates (hospital admission within 48 hours of diversion). Data was analysed qualitatively and quantitatively using proportions. Results: EMS responded to 681 calls for intoxication. Of the 568 taken directly to the ED, 65 met diversion criteria; these were missed protocol opportunities (11%). 113 patients were diverted. There was protocol noncompliance in 41 cases (36%), but 35 were due to incomplete recording of vital signs. There were direct protocol violations in only 6 cases (5%). There was protocol failure in 16 cases (22%), and patient morbidity in 1 case (1%). No patients died within 48 hours of diversion. Conclusion: EMS providers were fairly compliant with the protocol when transporting patients directly to the ED. There was some protocol non-compliance with patients diverted to WMS, though this is largely attributed to incomplete recording of vital signs; direct protocol violations were low. The protocol provides high levels of safety for patients diverted to WMS. Broader implementation of the protocol could reduce the volume of intoxicated patients seen in the ED, and improve quality of care received by this population.

scholarly journals Care coordination in the Emergency Department: improving outcomes for older patients

2005 ◽  
Vol 29 (1) ◽  
pp. 43 ◽  
Author(s):  
Helen M Corbett ◽  
Wen K Lim ◽  
Sandra J Davis ◽  
Ann M Elkins
Keyword(s):  
Quality Of Life ◽  
Emergency Department ◽  
Patient Satisfaction ◽  
Care Coordination ◽  
Baseline Measure ◽  
Significant Difference ◽  
Before And After ◽  
Patient Health ◽  
Related Quality

This study aimed to evaluate the effectiveness of the care coordination (CC) program operating in the Emergency Department (ED) of The Northern Hospital in improving outcomes for older people and reducing ED admissions and re-presentations. This was achieved by comparing admissions from ED to wards pre and post commencement of the CC program, and measuring patient health-related quality of life pre and post CC intervention. Patient readmission rates and staff and patient satisfaction with the service were also investigated. Results indicate a statistically significant reduction in the proportion of patients admitted from the ED to a ward since the inception of the program, a significant difference in the mean-related quality of life scores before and after intervention by care coordination, and staff and patient satisfaction with the service. The readmission data collected in the present evaluation will serve as a baseline measure for future evaluations.

Sign in / Sign up

Export Citation Format

Share Document