Quantifying care coordination using natural language processing and domain-specific ontology

Natural Language Processing Applied to Clinical Documentation in Post-acute Care Settings: A Scoping Review

OBJECTIVES

To determine the scope of the application of natural language processing to free-text clinical notes in post-acute care and provide a foundation for future natural language processing-based research in these settings.

DESIGN

Scoping review; reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines.

SETTING AND PARTICIPANTS

Post-acute care (ie, home health care, long-term care, skilled nursing facilities, and inpatient rehabilitation facilities).

METHODS

PubMed, Cumulative Index of Nursing and Allied Health Literature, and Embase were searched in February 2023. Eligible studies had quantitative designs that used natural language processing applied to clinical documentation in post-acute care settings. The quality of each study was appraised.

RESULTS

Twenty-one studies were included. Almost all studies were conducted in home health care settings. Most studies extracted data from electronic health records to examine the risk for negative outcomes, including acute care utilization, medication errors, and suicide mortality. About half of the studies did not report age, sex, race, or ethnicity data or use standardized terminologies. Only 8 studies included variables from socio-behavioral domains. Most studies fulfilled all quality appraisal indicators.

CONCLUSIONS AND IMPLICATIONS

The application of natural language processing is nascent in post-acute care settings. Future research should apply natural language processing using standardized terminologies to leverage free-text clinical notes in post-acute care to promote timely, comprehensive, and equitable care. Natural language processing could be integrated with predictive models to help identify patients who are at risk of negative outcomes. Future research should incorporate socio-behavioral determinants and diverse samples to improve health equity in informatics tools.

Extracting cancer concepts from clinical notes using natural language processing: a systematic review

BACKGROUND

Extracting information from free texts using natural language processing (NLP) can save time and reduce the hassle of manually extracting large quantities of data from incredibly complex clinical notes of cancer patients. This study aimed to systematically review studies that used NLP methods to identify cancer concepts from clinical notes automatically.

METHODS

PubMed, Scopus, Web of Science, and Embase were searched for English language papers using a combination of the terms concerning "Cancer", "NLP", "Coding", and "Registries" until June 29, 2021. Two reviewers independently assessed the eligibility of papers for inclusion in the review.

RESULTS

Most of the software programs used for concept extraction reported were developed by the researchers (n = 7). Rule-based algorithms were the most frequently used algorithms for developing these programs. In most articles, the criteria of accuracy (n = 14) and sensitivity (n = 12) were used to evaluate the algorithms. In addition, Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) and Unified Medical Language System (UMLS) were the most commonly used terminologies to identify concepts. Most studies focused on breast cancer (n = 4, 19%) and lung cancer (n = 4, 19%).

CONCLUSION

The use of NLP for extracting the concepts and symptoms of cancer has increased in recent years. The rule-based algorithms are well-liked algorithms by developers. Due to these algorithms' high accuracy and sensitivity in identifying and extracting cancer concepts, we suggested that future studies use these algorithms to extract the concepts of other diseases as well.

Natural Language Processing of Nursing Notes: An Integrative Review

Natural language processing includes a variety of techniques that help to extract meaning from narrative data. In healthcare, medical natural language processing has been a growing field of study; however, little is known about its use in nursing. We searched PubMed, EMBASE, and CINAHL and found 689 studies, narrowed to 43 eligible studies using natural language processing in nursing notes. Data related to the study purpose, patient population, methodology, performance evaluation metrics, and quality indicators were extracted for each study. The majority (86%) of the studies were conducted from 2015 to 2021. Most of the studies (58%) used inpatient data. One of four studies used data from open-source databases. The most common standard terminologies used were the Unified Medical Language System and Systematized Nomenclature of Medicine, whereas nursing-specific standard terminologies were used only in eight studies. Full system performance metrics (eg, F score) were reported for 61% of applicable studies. The overall number of nursing natural language processing publications remains relatively small compared with the other medical literature. Future studies should evaluate and report appropriate performance metrics and use existing standard nursing terminologies to enable future scalability of the methods and findings.

AI in predicting COPD in the Canadian population

Chronic obstructive pulmonary disease (COPD) is a progressive lung disease that produces non-reversible airflow limitations. Approximately 10% of Canadians aged 35 years or older are living with COPD. Primary care is often the first contact an individual will have with the healthcare system providing acute care, chronic disease management, and services aimed at health maintenance. This study used Electronic Medical Record (EMR) data from primary care clinics in seven provinces across Canada to develop predictive models to identify COPD in the Canadian population. The comprehensive nature of this primary care EMR data containing structured numeric, categorical, hybrid, and unstructured text data, enables the predictive models to capture symptoms of COPD and discriminate it from diseases with similar symptoms. We applied two supervised machine learning models, a Multilayer Neural Networks (MLNN) model and an Extreme Gradient Boosting (XGB) to identify COPD patients. The XGB model achieved an accuracy of 86% in the test dataset compared to 83% achieved by the MLNN. Utilizing feature importance, we identified a set of key symptoms from the EMR for diagnosing COPD, which included medications, health conditions, risk factors, and patient age. Application of this XGB model to primary care structured EMR data can identify patients with COPD from others having similar chronic conditions for disease surveillance, and improve evidence-based care delivery.

Transitional Care Models for High-Need, High-Cost Adults in the United States: A Scoping Review and Gap Analysis

Purpose of Study:

This scoping review explored research literature on the integration and coordination of services for high-need, high-cost (HNHC) patients in an attempt to answer the following questions: What models of transitional care are utilized to manage HNHC patients in the United States ? and How effective are they in reducing low-value utilization and in improving continuity ?

Primary Practice Settings:

U.S. urban, suburban, and rural health care sites within primary care, veterans’ services, behavioral health, and palliative care.

Methodology and Sample:

Utilizing the Joanna Briggs Institute and PRISMA guidelines for scoping reviews, a stepwise method was applied to search multiple databases for peer-reviewed published research on transitional care models serving HNHC adult patients in the United States from 2008 to 2018. All eligible studies were included regardless of quality rating. Exclusions were foreign models, studies published prior to 2008, review articles, care reports, and studies with participants younger than 18 years. The search returned 1,088 studies, of which 19 were included.

Results:

Four studies were randomized controlled trials and other designs included case reports and observational, quasi-experimental, cohort, and descriptive studies. Studies focused on Medicaid, Medicare, dual-eligible patients, veterans, and the uninsured or underinsured. High-need, high-cost patients were identified on the basis of prior utilization patterns of inpatient and emergency department visits, high cost, multiple chronic medical diagnoses, or a combination of these factors. Tools used to identify these patients included the hierarchical condition category predictive model, the Elder Risk Assessment, and the 4-year prognostic index score. The majority of studies combined characteristics of multiple case management models with varying levels of impact.

Implications for Case Management Practice:

Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare

Sepsis is a leading cause of death in hospitals. Early prediction and diagnosis of sepsis, which is critical in reducing mortality, is challenging as many of its signs and symptoms are similar to other less critical conditions. We develop an artificial intelligence algorithm, SERA algorithm, which uses both structured data and unstructured clinical notes to predict and diagnose sepsis. We test this algorithm with independent, clinical notes and achieve high predictive accuracy 12 hours before the onset of sepsis (AUC 0.94, sensitivity 0.87 and specificity 0.87). We compare the SERA algorithm against physician predictions and show the algorithm's potential to increase the early detection of sepsis by up to 32% and reduce false positives by up to 17%. Mining unstructured clinical notes is shown to improve the algorithm's accuracy compared to using only clinical measures for early warning 12 to 48 hours before the onset of sepsis.

Use of a modular ontology and a semantic annotation tool to describe the care pathway of patients with amyotrophic lateral sclerosis in a coordination network

The objective of this study was to describe the care pathway of patients with amyotrophic lateral sclerosis (ALS) based on real-life textual data from a regional coordination network, the Ile-de-France ALS network. This coordination network provides care for 92% of patients diagnosed with ALS living in Ile-de-France. We developed a modular ontology (OntoPaRON) for the automatic processing of these unstructured textual data. OntoPaRON has different modules: the core, medical, socio-environmental, coordination, and consolidation modules. Our approach was unique in its creation of fully defined concepts at different levels of the modular ontology to address specific topics relating to healthcare trajectories. We also created a semantic annotation tool specific to the French language and the specificities of our corpus, the Ontology-Based Semantic Annotation Module (OnBaSAM), using the OntoPaRON ontology as a reference. We used these tools to annotate the records of 928 patients automatically. The semantic (qualitative) annotations of the concepts were transformed into quantitative data. By using these pipelines we were able to transform unstructured textual data into structured quantitative data. Based on data processing, semantic annotations, sociodemographic data for the patient and clinical variables, we found that the need and demand for human and technical assistance depend on the initial form of the disease, the motor state, and the patient age. The presence of exhaustion in care management, is related to the patient’s motor and cognitive state.

Coronary Artery Disease Phenotype Detection in an Academic Hospital System Setting

BACKGROUND

The United States, and especially West Virginia, have a tremendous burden of coronary artery disease (CAD). Undiagnosed familial hypercholesterolemia (FH) is an important factor for CAD in the U.S. Identification of a CAD phenotype is an initial step to find families with FH.

OBJECTIVE

We hypothesized that a CAD phenotype detection algorithm that uses discrete data elements from electronic health records (EHRs) can be validated from EHR information housed in a data repository.

METHODS

We developed an algorithm to detect a CAD phenotype which searched through discrete data elements, such as diagnosis, problem lists, medical history, billing, and procedure (International Classification of Diseases [ICD]-9/10 and Current Procedural Terminology [CPT]) codes. The algorithm was applied to two cohorts of 500 patients, each with varying characteristics. The second (younger) cohort consisted of parents from a school child screening program. We then determined which patients had CAD by systematic, blinded review of EHRs. Following this, we revised the algorithm by refining the acceptable diagnoses and procedures. We ran the second algorithm on the same cohorts and determined the accuracy of the modification.

RESULTS

CAD phenotype Algorithm I was 89.6% accurate, 94.6% sensitive, and 85.6% specific for group 1. After revising the algorithm (denoted CAD Algorithm II) and applying it to the same groups 1 and 2, sensitivity 98.2%, specificity 87.8%, and accuracy 92.4; accuracy 93% for group 2. Group 1 F1 score was 92.4%. Specific ICD-10 and CPT codes such as "coronary angiography through a vein graft" were more useful than generic terms.

CONCLUSION

We have created an algorithm, CAD Algorithm II, that detects CAD on a large scale with high accuracy and sensitivity (recall). It has proven useful among varied patient populations. Use of this algorithm can extend to monitor a registry of patients in an EHR and/or to identify a group such as those with likely FH.

Technology-facilitated care coordination in rural areas: What is needed?

BACKGROUND

Health is poorer in rural areas and a major challenge is care coordination for complex chronic conditions. The HITECH and 21^st Century Cure Acts emphasize health information exchange which underpins activities required to improve care coordination.

OBJECTIVE AND METHODS

Using semi-structured interviews and surveys, we examined how providers experience electronic health information exchange during care coordination since these Acts were implemented, with a focus on rural settings where health disparities exist. We used a purposive sample that included primary care, acute care hospitals, and community health services in the United States.

FINDINGS

We identified seven themes related to care coordination and information exchange: 'insufficient trust of data'; 'please respond'; 'just fax it'; 'care plans'; 'needle in the haystack'; 're-documentation'; and 'rural reality'. These gaps were magnified when information exchange was required between unaffiliated electronic health records (EHRs) about shared patients, which was more pronounced in rural settings.

CONCLUSION

Policy and incentive modifications are likely needed to overcome the observed health information technology (HIT) shortcomings. Rural settings in the United States accentuate problems that can be addressed through international medical informatics policy makers and the implementation and evaluation of interoperable HIT systems.

Professional care at home: Patient-centredness, interprofessionality and effectivity? A scoping review

The aim of this scoping review was to describe the state of knowledge on professional care at home with regard to different perspectives on patient-centredness, content of care, interprofessional collaboration, competence framework and effectivity. A scoping review, n = 35 papers, from four databases (EBSCO, CINAHL, Medline, Swemed) were reviewed between May and August 2018 using the terms: hospital-at-home, hospital-in-the-home, advanced home healthcare, hospital-based home care or patient-centered medical home. Criteria for inclusion in this review included full text papers, published between 2001 and 2018, in English, Swedish or Finnish. A descriptive content analysis was conducted. Patient-centredness appears to be one aim of professional care at home, but clarity is lacking regarding patient recruitment and the planning and evaluation of care. Content depends, to a certain degree, on the type of care at home and how it is organised: the more non-acute care needs, the more nurse-coordinated care and family involvement and the less interprofessionality. The competence framework presupposed for care at home was extensive yet not explicit, varying from maturity, clinical experience, collaboration skills, ongoing clinical assessment education to Master's studies or degree. The effectivity of care at home services was discussed in terms of experiential, clinical and economic aspects. Patients and their family caregivers were satisfied with care at home, but there was no consensus on clinical or economic outcomes compared with inpatient care. In the context of professional care at home, there is still a lot to do regarding patient-centredness, patient recruitment, patient and care staff education, the organisation of interprofessional collaboration and the analysis of effectivity.

Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review

Background

Novel approaches that complement and go beyond evidence-based medicine are required in the domain of chronic diseases, given the growing incidence of such conditions on the worldwide population. A promising avenue is the secondary use of electronic health records (EHRs), where patient data are analyzed to conduct clinical and translational research. Methods based on machine learning to process EHRs are resulting in improved understanding of patient clinical trajectories and chronic disease risk prediction, creating a unique opportunity to derive previously unknown clinical insights. However, a wealth of clinical histories remains locked behind clinical narratives in free-form text. Consequently, unlocking the full potential of EHR data is contingent on the development of natural language processing (NLP) methods to automatically transform clinical text into structured clinical data that can guide clinical decisions and potentially delay or prevent disease onset.

Objective

The goal of the research was to provide a comprehensive overview of the development and uptake of NLP methods applied to free-text clinical notes related to chronic diseases, including the investigation of challenges faced by NLP methodologies in understanding clinical narratives.

Methods

Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed and searches were conducted in 5 databases using “clinical notes,” “natural language processing,” and “chronic disease” and their variations as keywords to maximize coverage of the articles.

Results

Of the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using the International Classification of Diseases, 10th Revision. The majority of studies focused on diseases of the circulatory system (n=38) while endocrine and metabolic diseases were fewest (n=14). This was due to the structure of clinical records related to metabolic diseases, which typically contain much more structured data, compared with medical records for diseases of the circulatory system, which focus more on unstructured data and consequently have seen a stronger focus of NLP. The review has shown that there is a significant increase in the use of machine learning methods compared to rule-based approaches; however, deep learning methods remain emergent (n=3). Consequently, the majority of works focus on classification of disease phenotype with only a handful of papers addressing extraction of comorbidities from the free text or integration of clinical notes with structured data. There is a notable use of relatively simple methods, such as shallow classifiers (or combination with rule-based methods), due to the interpretability of predictions, which still represents a significant issue for more complex methods. Finally, scarcity of publicly available data may also have contributed to insufficient development of more advanced methods, such as extraction of word embeddings from clinical notes.

Conclusions

Efforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and (5) availability of large-scale, de-identified clinical corpora.

Starting Up a Hospital at Home Program: Facilitators and Barriers to Implementation

BACKGROUND

Hospital at home (HaH) is a model of care that provides acute-level services in the home. HaH has been shown to improve quality and patient satisfaction, and reduce iatrogenesis and costs. Uptake of HaH in the United States has been limited, and little research exists on how to implement it successfully.

OBJECTIVES

This study examined facilitators and barriers to implementation of an HaH program.

DESIGN

A HaH program that included a 30-day transitional care bundle following the acute stay was implemented through a Centers for Medicare & Medicaid Services Innovations Award. Informants completed a priming table describing initial implementation components, their barriers, and facilitators. These were followed up with semistructured focus groups and individual interviews that were transcribed and independently coded using thematic analysis by two independent investigators.

SETTING

Large urban academic health system.

PARTICIPANTS

Clinical and administrative personnel from Mount Sinai, the Visiting Nurse Service of New York, and executive leaders at partner organizations (laboratory, pharmacy, radiology, and transportation).

RESULTS

To facilitate successful development and implementation of a high-quality HaH program, a number of barriers needed to be overcome through significant teamwork and communication internally with policymakers and external partners. Areas of paramount importance include facilitating work-arounds to regulatory barriers and health system policies; altering an electronic health record that was not designed for HaH; developing the necessary payment and billing mechanisms; and building effective and collaborative partnerships and communication with outside vendors.

CONCLUSION

Development of HaH programs in the United States are feasible but require strategic planning and development of strong, tightly coordinated partnerships. J Am Geriatr Soc 67:588-595, 2019.

Challenges in adapting existing clinical natural language processing systems to multiple, diverse health care settings

Objective

Widespread application of clinical natural language processing (NLP) systems requires taking existing NLP systems and adapting them to diverse and heterogeneous settings. We describe the challenges faced and lessons learned in adapting an existing NLP system for measuring colonoscopy quality.

Materials and Methods

Colonoscopy and pathology reports from 4 settings during 2013-2015, varying by geographic location, practice type, compensation structure, and electronic health record.

Results

Though successful, adaptation required considerably more time and effort than anticipated. Typical NLP challenges in assembling corpora, diverse report structures, and idiosyncratic linguistic content were greatly magnified.

Discussion

Strategies for addressing adaptation challenges include assessing site-specific diversity, setting realistic timelines, leveraging local electronic health record expertise, and undertaking extensive iterative development. More research is needed on how to make it easier to adapt NLP systems to new clinical settings.

Conclusions

A key challenge in widespread application of NLP is adapting existing systems to new clinical settings.

Clinical information extraction applications: A literature review

BACKGROUND

With the rapid adoption of electronic health records (EHRs), it is desirable to harvest information and knowledge from EHRs to support automated systems at the point of care and to enable secondary use of EHRs for clinical and translational research. One critical component used to facilitate the secondary use of EHR data is the information extraction (IE) task, which automatically extracts and encodes clinical information from text.

OBJECTIVES

In this literature review, we present a review of recent published research on clinical information extraction (IE) applications.

METHODS

A literature search was conducted for articles published from January 2009 to September 2016 based on Ovid MEDLINE In-Process & Other Non-Indexed Citations, Ovid MEDLINE, Ovid EMBASE, Scopus, Web of Science, and ACM Digital Library.

RESULTS

A total of 1917 publications were identified for title and abstract screening. Of these publications, 263 articles were selected and discussed in this review in terms of publication venues and data sources, clinical IE tools, methods, and applications in the areas of disease- and drug-related studies, and clinical workflow optimizations.

CONCLUSIONS

Clinical IE has been used for a wide range of applications, however, there is a considerable gap between clinical studies using EHR data and studies using clinical IE. This study enabled us to gain a more concrete understanding of the gap and to provide potential solutions to bridge this gap.

Health Information Technology Coordination to Support Patient-centered Care Coordination

OBJECTIVE

To select papers published in 2014, illustrating how information technology can contribute to and improve patient-centered care coordination.

METHOD

The two section editors performed a literature review from Medline and Web of Science to select a list of candidate best papers on the use of information technology for patient-centered care coordination. These papers were peer-reviewed by external reviewers and three of them were selected as "best papers".

RESULTS

The first selected paper reports a qualitative study exploring the gap between current practices of care coordination in various settings and idealized longitudinal care plans. The second selected paper illustrates several unintended consequences of HIT designed to improve care coordination. The third selected paper shows that advanced analytic techniques in medical informatics can be instrumental in studying patient-centered care coordination.

CONCLUSIONS

The realization of true patient-centered care coordination is dependent upon a number of factors. Standardization of clinical documentation and HIT interoperability across organization and settings is a critical prerequisite for HIT to support patient-centered care coordination. Enabling patient involvement is an efficient means for goal setting and health information sharing. Additionally, unintended consequences of HIT tools (both positive and negative) must be measured and taken into account for quality improvement.

Identifying Care Coordination Interventions Provided to Community-Dwelling Older Adults Using Electronic Health Records

Although care coordination is a popular intervention, there is no standard method of delivery. Also little is known about who benefits most, or characteristics that predict the amount of care coordination needed, especially with chronically ill older adults. The purpose of this study was to identify types and amount of nurse care coordination interventions provided to 231 chronically ill older adults who participated in a 12-month home care medication management program in the Midwest. For each participant, the nurse care coordinator spent an average of 134 min/mo providing in-person home care, 48 min/mo of travel, and 18 min/mo of indirect care occurring outside the home visit. This accounted for 67.2%, 23.8%, and 9.0% of nursing time, respectively, for home visits, travel, and indirect care. Four of 11 nursing interventions focused on medication management were provided to all participants. Seven of the 11 main interventions were individualized according to each person's special needs. Wide variations were observed in time provided with in-person home care and communications with multiple stakeholders. Study findings indicate the importance of individualizing interventions and the variability in the amount of nursing time needed to provide care coordination to chronically ill older adults.

Home Health Care: Nurse-Physician Communication, Patient Severity, and Hospital Readmission

OBJECTIVE

To evaluate whether communication failures between home health care nurses and physicians during an episode of home care after hospital discharge are associated with hospital readmission, stratified by patients at high and low risk of readmission.

DATA SOURCE/STUDY SETTING

We linked Visiting Nurse Services of New York electronic medical records for patients with congestive heart failure in 2008 and 2009 to hospitalization claims data for Medicare fee-for-service beneficiaries.

STUDY DESIGN

Linear regression models and a propensity score matching approach were used to assess the relationship between communication failure and 30-day readmission, separately for patients with high-risk and low-risk readmission probabilities.

DATA COLLECTION/EXTRACTION METHODS

Natural language processing was applied to free-text data in electronic medical records to identify failures in communication between home health nurses and physicians.

PRINCIPAL FINDINGS

Communication failure was associated with a statistically significant 9.7 percentage point increase in the probability of a patient readmission (32.6 percent of the mean) among high-risk patients.

CONCLUSIONS

Poor communication between home health nurses and physicians is associated with an increased risk of hospital readmission among high-risk patients. Efforts to reduce readmissions among this population should consider focusing attention on this factor.

Big data science: A literature review of nursing research exemplars

BACKGROUND

Big data and cutting-edge analytic methods in nursing research challenge nurse scientists to extend the data sources and analytic methods used for discovering and translating knowledge.

PURPOSE

The purpose of this study was to identify, analyze, and synthesize exemplars of big data nursing research applied to practice and disseminated in key nursing informatics, general biomedical informatics, and nursing research journals.

METHODS

A literature review of studies published between 2009 and 2015. There were 650 journal articles identified in 17 key nursing informatics, general biomedical informatics, and nursing research journals in the Web of Science database. After screening for inclusion and exclusion criteria, 17 studies published in 18 articles were identified as big data nursing research applied to practice.

DISCUSSION

Nurses clearly are beginning to conduct big data research applied to practice. These studies represent multiple data sources and settings. Although numerous analytic methods were used, the fundamental issue remains to define the types of analyses consistent with big data analytic methods.

CONCLUSION

There are needs to increase the visibility of big data and data science research conducted by nurse scientists, further examine the use of state of the science in data analytics, and continue to expand the availability and use of a variety of scientific, governmental, and industry data resources. A major implication of this literature review is whether nursing faculty and preparation of future scientists (PhD programs) are prepared for big data and data science.

TrhOnt: building an ontology to assist rehabilitation processes

Background

One of the current research efforts in the area of biomedicine is the representation of knowledge in a structured way so that reasoning can be performed on it. More precisely, in the field of physiotherapy, information such as the physiotherapy record of a patient or treatment protocols for specific disorders must be adequately modeled, because they play a relevant role in the management of the evolutionary recovery process of a patient. In this scenario, we introduce TrhOnt, an application ontology that can assist physiotherapists in the management of the patients’ evolution via reasoning supported by semantic technology.

Methods

The ontology was developed following the NeOn Methodology. It integrates knowledge from ontological (e.g. FMA ontology) and non-ontological resources (e.g. a database of movements, exercises and treatment protocols) as well as additional physiotherapy-related knowledge.

Results

We demonstrate how the ontology fulfills the purpose of providing a reference model for the representation of the physiotherapy-related information that is needed for the whole physiotherapy treatment of patients, since they step for the first time into the physiotherapist’s office, until they are discharged. More specifically, we present the results for each of the intended uses of the ontology listed in the document that specifies its requirements, and show how TrhOnt can answer the competency questions defined within that document. Moreover, we detail the main steps of the process followed to build the TrhOnt ontology in order to facilitate its reproducibility in a similar context. Finally, we show an evaluation of the ontology from different perspectives.

Conclusions

TrhOnt has achieved the purpose of allowing for a reasoning process that changes over time according to the patient’s state and performance.

An ontology-driven, case-based clinical decision support model for removable partial denture design

We present the initial work toward developing a clinical decision support model for specific design of removable partial dentures (RPDs) in dentistry. We developed an ontological paradigm to represent knowledge of a patient’s oral conditions and denture component parts. During the case-based reasoning process, a cosine similarity algorithm was applied to calculate similarity values between input patients and standard ontology cases. A group of designs from the most similar cases were output as the final results. To evaluate this model, the output designs of RPDs for 104 randomly selected patients were compared with those selected by professionals. An area under the curve of the receiver operating characteristic (AUC-ROC) was created by plotting true-positive rates against the false-positive rate at various threshold settings. The precision at position 5 of the retrieved cases was 0.67 and at the top of the curve it was 0.96, both of which are very high. The mean average of precision (MAP) was 0.61 and the normalized discounted cumulative gain (NDCG) was 0.74 both of which confirmed the efficient performance of our model. All the metrics demonstrated the efficiency of our model. This methodology merits further research development to match clinical applications for designing RPDs. This paper is organized as follows. After the introduction and description of the basis for the paper, the evaluation and results are presented in Section 2. Section 3 provides a discussion of the methodology and results. Section 4 describes the details of the ontology, similarity algorithm, and application.