Fuzzy Matching for Symptom Detection in Tweets: Application to Covid-19 During the First Wave of the Pandemic in France

The exhaustive automatic detection of symptoms in social media posts is made difficult by the presence of colloquial expressions, misspellings and inflected forms of words. The detection of self-reported symptoms is of major importance for emergent diseases like the Covid-19. In this study, we aimed to (1) develop an algorithm based on fuzzy matching to detect symptoms in tweets, (2) establish a comprehensive list of Covid-19-related symptoms and (3) evaluate the fuzzy matching for Covid-19-related symptom detection in French tweets. The Covid-19-related symptom list was built based on the aggregation of different data sources. French Covid-19-related tweets were automatically extracted using a dedicated data broker during the first wave of the pandemic in France. The fuzzy matching parameters were finetuned using all symptoms from MedDRA and then evaluated on a subset of 5000 Covid-19-related tweets in French for the detection of symptoms from our Covid-19-related list. The fuzzy matching improved the detection by the addition of 42% more correct matches with an 81% precision.

Calibrating a chief complaint list for low resource settings: a methodologic case study

Background The chief or presenting complaint is the reason for seeking health care, often in the patient’s own words. In limited resource settings, a diagnosis-based approach to quantifying burden of disease is not possible, partly due to limited availability of an established lexicon or coding system. Our group worked with colleagues from the African Federation of Emergency Medicine building on the existing literature to create a pilot symptom list representing an attempt to standardize undifferentiated chief complaints in emergency and acute care settings. An ideal list for any setting is one that strikes a balance between ease of use and length, while covering the vast majority of diseases with enough detail to permit epidemiologic surveillance and make informed decisions about resource needs. Methods This study was incorporated as a part of a larger prospective observational study on human immunodeficiency virus testing in Emergency Departments in South Africa. The pilot symptom list was used for chief complaint coding in three Emergency Departments. Data was collected on 3357 patients using paper case report forms. Chief complaint terms were reviewed by two study team members to determine the frequency of concordance between the coded chief complaint term and the selected symptom(s) from the pilot symptom list. Results Overall, 3537 patients’ chief complaints were reviewed, of which 640 were identified as ‘potential mismatches.’ When considering the 191 confirmed mismatches (29.8%), the Delphi process identified 6 (3.1%) false mismatches and 185 (96.9%) true mismatches. Significant chief-complaint clustering was identified with 9 sets of complaints frequently selected together for the same patient. “Pain” was used 2076 times for 58.7% of all patients. A combination of user feedback and expert-panel modified Delphi analysis of mismatched complaints and clustered complaints resulted in several substantial changes to the pilot symptom list. Conclusions This study presented a systematic methodology for calibrating a chief complaint list for the local context. Our revised list removed/reworded symptoms that frequently clustered together or were misinterpreted by health professionals. Recommendations for additions, modifications, and/or deletions from the pilot chief complaint list we believe will improve the functionality of the list in low resource environments.

Latent profiles of patients with borderline pathology based on the alternative DSM-5 model for personality disorders

Background There have been multiple attempts to try to parse out heterogeneity within borderline pathology by identifying patient subtypes; thus far, these works have yielded few consistent results. Recent developments in the operationalization of borderline pathology may provide new opportunities to identify clinically and conceptually meaningful subgroups of patients. The Alternative DSM-5 Model for Personality Disorders (AMPD) offers a categorical-dimensional operationalization of Borderline personality disorder (BPD) that has yet to be tested for identification of patient subgroups. The purpose of the present study is to test whether the combination of the Criterion A elements (pertaining to level of severity) and the seven pathological facets from Criterion B that define BPD in the AMPD can yield meaningful patient profiles. Methods A total of 211 outpatients from a specialized PD treatment program (133 women, Mage = 33.66, SD = 10.97) were selected based on the presence of at least moderate borderline pathology according to cutoffs recently proposed for the Borderline Symptom List-23. Valid Criterion A (Self and Interpersonal Functioning Scale) and B (Personality Inventory for DSM-5 Faceted Brief Form) self-reports were administered to measure elements and facets that define BPD in the AMPD model; these variables were used as indicators in a latent profile analysis (LPA). Results The optimal solution generated by LPA yielded four distinct profiles: (a) Borderline traits; (b) Moderate pathology with Impulsivity; (c) Moderate pathology with Identity problems and Depressivity; and (d) Severe pathology. Clinically meaningful distinctions emerged among profiles on AMPD indicators and external variables relevant to PD, especially aggression and impulsivity. Conclusions Profiles reflected both the “severity” and “style” components imbedded within Criterion A and B of the AMPD, as they were mainly distinguished by a continuum of severity but also by some meaningful qualitative differences that may have important clinical implications for treatment planning and contracting. Results also suggest that the four Criterion A elements have independent value to identify important differences in patients with borderline pathology. They also highlight that some Criterion B facets that define BPD in the AMPD may be especially important to identify subgroups of patients, mainly Impulsivity and Depressivity.

Validating a Chief Compliant List for Low Resource Settings: A Methodologic Case Study

Background:The chief or presenting complaint is the reason for seeking health care, often in the patient’s own words. In limited resource settings, a diagnosis-based approach to quantifying burden of disease is not possible, partly due to limited availability of an established lexicon or coding system. Collaboration with World Health Organization colleagues resulted in the creation of a pilot symptom list representing an attempt to standardize undifferentiated chief complaints in emergency and acute care settings. A validated universal chief complaint list would profoundly benefit clinicians, researchers, and policymakers world-wide by allowing the communication and development of system-level priorities based around the signs and symptoms most often experienced by the patients being served.Methods: This study was incorporated as a part of a larger prospective observational study on human immunodeficiency virus testing in Emergency Departments in South Africa. The pilot symptom list was used for chief complaint coding in three Emergency Departments. Data was collected on 3,357 patients using paper case report forms. Chief complaint terms were reviewed by two study team members to determine the frequency of concordance between the coded chief complaint term and the selected symptom(s) from the pilot symptom list.Results:Overall, 3,537 patients’ chief complaints were reviewed, of which 640 were identified as ‘potential mis-matches’. When considering the 191 confirmed mis-matches (29.8%), the Delphi process identified 6 (3.1%) false mismatches and 185 (96.9%) true mismatches. Significant chief-complaint clustering was identified with 9 sets of complaints frequently selected together for the same patient. “Pain” was used 2,076 times for 58.7% of all patients. Testing for validity and functionality of the initial draft dataset via user feedback and expert-panel modified Delphi analysis resulted in several substantial changes to the pilot symptom list.Conclusions:This study found that the pilot symptom list with aforementioned modifications could be applied to a low resource emergency system. Recommendations for additions, modifications, and/or deletions from the draft chief complaint list will improve validity and functionality of the list in low resource environments. Selecting a patient’s chief complaint from a validated list offers a vital tool to help triage patients, streamline emergency care delivery, and improve patient outcomes.

Latent Profiles of Patients with Borderline Pathology Based on the Alternative DSM-5 Model for Personality Disorders

Background There have been multiple attempts to try to parse out heterogeneity within borderline pathology by identifying patient subtypes; thus far, these works have yielded few consistent results. Recent developments in the operationalization of borderline pathology may provide new opportunities to identify clinically and conceptually meaningful subgroups of patients. The Alternative DSM-5 Model for Personality Disorders (AMPD) offers a categorical-dimensional operationalization of Borderline personality disorder (BPD) that has yet to be tested for identification of patient subgroups. The purpose of the present study is to test whether the combination of the Criterion A elements (pertaining to level of severity) and the seven pathological traits from Criterion B that define BPD in the AMPD can yield meaningful patient profiles. Methods A total of 211 outpatients from a specialized PD treatment program (133 women, Mage = 33.66, SD = 10.97) were selected based on the presence of at least moderate borderline pathology according to cutoffs recently proposed for the Borderline Symptom List-23. Valid Criterion A (Self and Interpersonal Functioning Scale) and B (Personality Inventory for DSM-5-Short Form) self-reports were administered to measure elements and traits that define BPD in the AMPD model; these variables were used as indicators in a Latent profile analysis (LPA). Results The optimal solution generated by LPA yielded four distinct profiles: (a) Borderline traits; (b) Low borderline pathology with Impulsivity; (c) Moderate borderline pathology with Identity problems and Depressivity; and (d) Severe borderline pathology. Clinically meaningful distinctions emerged between profiles on AMPD indicators and external variables relevant to PD, especially aggression and impulsivity. Conclusions Profiles reflected both the “severity” and “style” components imbedded within Criterion A and B of the AMPD, as they were mainly distinguished by a continuum of severity but also by some meaningful qualitative differences that may have important clinical implications for treatment planning and contracting. Results also suggest that the four Criterion A elements have independent value to identify important differences in patients with borderline pathology. They also highlight that some Criterion B traits that define BPD in the AMPD may be especially important to identify subgroups of patients, mainly Impulsivity and Depressivity.

B·RIGHT: usability and satisfaction with a mobile app for self-managing emotional crises in patients with borderline personality disorder

Objective: Borderline personality disorder (BPD) is a severe mental disorder characterized by emotional crises. To date, crisis interventions for BPD have been conducted via telephone calls and emergency units, which are associated with an extra amount of resources. The aim of this research was to test the usability and satisfaction with a psychotherapeutic mobile app for self-managing crises in BPD. Method: The B·RIGHT app was designed based on Artificial Intelligence psychotherapeutic algorithms. Usability and satisfaction with the app were assessed in 25 outpatients diagnosed with BPD (84% female, mean age = 35.80 years) using the System Usability Scale (SUS) and other questionnaires. Clinical features were assessed using the Borderline Symptom List, the Difficulties in Emotion Regulation Scale and Beck’s Depression Inventory. Results: Patients with BPD considered the app user-friendly (mean total score = 4.03) and highly satisfactory (mean total score = 4.02), resulting in a positive user experience (mean total score = 4.09). Total usability was negatively associated with age ( r = −.44), positively associated with educational level ( rho = .47) and with overall emotion dysregulation ( r = .51), and negatively associated with depression severity ( r = −.47). Conclusions: The usability and satisfaction testing of the B·RIGHT app showed promising findings, which warrant further research in order to validate its effectiveness.

A Proposed Severity Classification of Borderline Symptoms Using the Borderline Symptom List (BSL-23)

Background The Borderline Symptom List (BSL-23) is a well-established self-rating instrument to assess the severity of borderline typical psychopathology. However, a classification of severity levels for the BSL-23 is missing. Methods Data from 1.090 adults were used to develop a severity classification for the Borderline Symptom List (BSL-23). The severity grading was based on the distribution of the BSL-23 in 241 individuals with a diagnosis of BPD. Data from three independent samples were used to validate the previously defined severity grades. These validation samples included a group of treatment seeking patients with a diagnosis of BPD (n=317), a sample of individuals with mental illnesses other than BPD (n=176), and a healthy control sample (n=356). The severity grades were validated from comparisons with established assessment instruments such as the International Personality Disorders Examination, the Structured Clinical Interview for DSM-IV, the global severity index of the Symptom Checklist (GSI, SCL-90), the Global Assessment of Functioning (GAF), and the Beck Depression Inventory (BDI-II).Results Six grades of symptom severity were defined for the BSL-23 mean score: none or low: 0-0.3; mild: 0.3-0.7; moderate: 0.7-1.7; high: 1.7-2.7; very high: 2.7-3.5; and extremely high: 3.5-4. These grades received consistent empirical support from the independent instruments and samples. For instance, individuals with a severity grade of none or low were virtually free from diagnostic BPD-criteria, had a GSI below the normative population, and a high level of global functioning corresponding to few or no symptoms. Severity grades indicating high to extremely high levels of BPD symptoms were observed at a much higher rate in treatment-seeking patients (70.0%) than in clinical controls (17.6%) and healthy controls (0.0%). The BSL-23 score that best separated treatment-seeking BPD patients and clinical controls was 1.50, whereas the clearest discrimination of BPD patients and healthy controls was found at a score of 0.64.Conclusions The grades of BPD-specific symptom severity derived from the distribution of the BSL-23 scores received consistent empirical validation from established assessments for psychopathology. Future studies should expand this validation by including additional instruments e.g., to assess self-esteem, loneliness, connectedness, and quality of life.