Figure - available via license: CC BY
Content may be subject to copyright.
Source publication
Background
The amount of patient-related information within clinical information systems accumulates over time, especially in cases where patients suffer from chronic diseases with many hospitalizations and consultations. The diagnosis or problem list is an important feature of the electronic health record, which provides a dynamic account of a pat...
Context in source publication
Context 1
... Table 2 we see that for the inter-patient setting almost all non-coded list items get a post-assigned ICD-10 code with an overall F-measure of 0.87. This result is quite remarkable compared to the literature review and considering the not optimal cut-off we inferred for the inter-patient inspection accomplished by a lower precision compared to the intra-patient results in Table 1. ...Citations
... The tools in the EHR for cleanup are limited to a single patient and do not allow for automated processing or opportunities to categorize or define the state of the PL or large-scale maintenance at the population level. Multiple interventions, including reconfiguration of the EHR PL and re-education, have been met with limited success [20]. Despite these attempts, PL bloat and inaccuracy are widely recognized as issues affecting clinical care and secondary downstream uses of the data [3]. ...
Background
The problem list (PL) is a repository of diagnoses for patients’ medical conditions and health-related issues. Unfortunately, over time, our PLs have become overloaded with duplications, conflicting entries, and no-longer-valid diagnoses. The lack of a standardized structure for review adds to the challenges of clinical use. Previously, our default electronic health record (EHR) organized the PL primarily via alphabetization, with other options available, for example, organization by clinical systems or priority settings. The system’s PL was built with limited groupers, resulting in many diagnoses that were inconsistent with the expected clinical systems or not associated with any clinical systems at all. As a consequence of these limited EHR configuration options, our PL organization has poorly supported clinical use over time, particularly as the number of diagnoses on the PL has increased.
Objective
We aimed to measure the accuracy of sorting PL diagnoses into PL system groupers based on Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) concept groupers implemented in our EHR.
Methods
We transformed and developed 21 system- or condition-based groupers, using 1211 SNOMED CT hierarchal concepts refined with Boolean logic, to reorganize the PL in our EHR. To evaluate the clinical utility of our new groupers, we extracted all diagnoses on the PLs from a convenience sample of 50 patients with 3 or more encounters in the previous year. To provide a spectrum of clinical diagnoses, we included patients from all ages and divided them by sex in a deidentified format. Two physicians independently determined whether each diagnosis was correctly attributed to the expected clinical system grouper. Discrepancies were discussed, and if no consensus was reached, they were adjudicated by a third physician. Descriptive statistics and Cohen κ statistics for interrater reliability were calculated.
Results
Our 50-patient sample had a total of 869 diagnoses (range 4-59; median 12, IQR 9-24). The reviewers initially agreed on 821 system attributions. Of the remaining 48 items, 16 required adjudication with the tie-breaking third physician. The calculated κ statistic was 0.7. The PL groupers appropriately associated diagnoses to the expected clinical system with a sensitivity of 97.6%, a specificity of 58.7%, a positive predictive value of 96.8%, and an F 1 -score of 0.972.
Conclusions
We found that PL organization by clinical specialty or condition using SNOMED CT concept groupers accurately reflects clinical systems. Our system groupers were subsequently adopted by our vendor EHR in their foundation system for PL organization.
... NLP has largely been used to automate or partially automate the generation of problem lists from clinical notes [11][12][13][14][15] . NLP has also been used to identify domain-specific problems 16 , association discovery 17 , data linkage from problems for decision support 18 , and clustering of similar problems 19 . The importance of having an accurate tobacco-use status in an EHR is well-documented 20 . ...
We present findings on using natural language processing to classify tobacco-related entries from problem lists found within patient's electronic health records. Problem lists describe health-related issues recorded during a patient's medical visit; these problems are typically followed up upon during subsequent visits and are updated for relevance or accuracy. The mechanics of problem lists vary across different electronic health record systems. In general, they either manifest as pre-generated generic problems that may be selected from a master list or as text boxes where a healthcare professional may enter free text describing the problem. Using commonly-available natural language processing tools, we classified tobacco-related problems into three classes: active-user, former-user, and non-user; we further demonstrate that rule-based post-processing may significantly increase precision in identifying these classes (+32%, +22%, +35% respectively). We used these classes to generate tobacco time-spans that reconstruct a patient's tobacco-use history and better support secondary data analysis. We bundle this as an open-source toolkit with flow visualizations indicating how patient tobacco-related behavior changes longitudinally, which can also capture and visualize contradicting information such as smokers being flagged as having never smoked.
... Their method generated prioritized and meaningful problem lists corresponding to specific practice settings. Kreuzthaler et al. [9] proposed a clustering approach to compress redundant problem lists in electronic health records and create semantic topic spaces. ...
Background
Since the creation of the problem-oriented medical record, the building of problem lists has been the focus of many studies. To date, this issue is not well resolved, and building an appropriate contextualized problem list is still a challenge.
Objective
This paper aims to present the process of building a shared multipurpose common problem list at the Geneva University Hospitals. This list aims to bridge the gap between clinicians’ language expressed in free text and secondary uses requiring structured information.
Methods
We focused on the needs of clinicians by building a list of uniquely identified expressions to support their daily activities. In the second stage, these expressions were connected to additional information to build a complex graph of information. A list of 45,946 expressions manually extracted from clinical documents was manually curated and encoded in multiple semantic dimensions, such as International Classification of Diseases, 10th revision; International Classification of Primary Care 2nd edition; Systematized Nomenclature of Medicine Clinical Terms; or dimensions dictated by specific usages, such as identifying expressions specific to a domain, a gender, or an intervention. The list was progressively deployed for clinicians with an iterative process of quality control, maintenance, and improvements, including the addition of new expressions or dimensions for specific needs. The problem management of the electronic health record allowed the measurement and correction of encoding based on real-world use.
Results
The list was deployed in production in January 2017 and was regularly updated and deployed in new divisions of the hospital. Over 4 years, 684,102 problems were created using the list. The proportion of free-text entries decreased progressively from 37.47% (8321/22,206) in December 2017 to 18.38% (4547/24,738) in December 2020. In the last version of the list, over 14 dimensions were mapped to expressions, among which 5 were international classifications and 8 were other classifications for specific uses. The list became a central axis in the electronic health record, being used for many different purposes linked to care, such as surgical planning or emergency wards, or in research, for various predictions using machine learning techniques.
Conclusions
This study breaks with common approaches primarily by focusing on real clinicians’ language when expressing patients’ problems and secondarily by mapping whatever is required, including controlled vocabularies to answer specific needs. This approach improves the quality of the expression of patients’ problems while allowing the building of as many structured dimensions as needed to convey semantics according to specific contexts. The method is shown to be scalable, sustainable, and efficient at hiding the complexity of semantics or the burden of constraint-structured problem list entry for clinicians. Ongoing work is analyzing the impact of this approach on how clinicians express patients’ problems.
Background Neurologists perform a significant amount of consultative work. Aggregative electronic health record (EHR) dashboards may help to reduce consultation turnaround time (TAT) which may reflect time spent interfacing with the EHR.
Objectives This study was aimed to measure the difference in TAT before and after the implementation of a neurological dashboard.
Methods We retrospectively studied a neurological dashboard in a read-only, web-based, clinical data review platform at an academic medical center that was separate from our institutional EHR. Using our EHR, we identified all distinct initial neurological consultations at our institution that were completed in the 5 months before, 5 months after, and 12 months after the dashboard go-live in December 2017. Using log data, we determined total dashboard users, unique page hits, patient-chart accesses, and user departments at 5 months after go-live. We calculated TAT as the difference in time between the placement of the consultation order and completion of the consultation note in the EHR.
Results By April 30th in 2018, we identified 269 unique users, 684 dashboard page hits (median hits/user 1.0, interquartile range [IQR] = 1.0), and 510 unique patient-chart accesses. In 5 months before the go-live, 1,434 neurology consultations were completed with a median TAT of 2.0 hours (IQR = 2.5) which was significantly longer than during 5 months after the go-live, with 1,672 neurology consultations completed with a median TAT of 1.8 hours (IQR = 2.2; p = 0.001). Over the following 7 months, 2,160 consultations were completed and median TAT remained unchanged at 1.8 hours (IQR = 2.5).
Conclusion At a large academic institution, we found a significant decrease in inpatient consult TAT 5 and 12 months after the implementation of a neurological dashboard. Further study is necessary to investigate the cognitive and operational effects of aggregative dashboards in neurology and to optimize their use.
