An artificial intelligence-based approach for identifying rare disease patients using retrospective electronic health records applied for Pompe disease.

Objective: We retrospectively screened 350,116 electronic health records (EHRs) to identify suspected patients for Pompe disease. Using these suspected patients, we then describe their phenotypical characteristics and estimate the prevalence in the respective population covered by the EHRs. Methods: We applied Symptoma's Artificial Intelligence-based approach for identifying rare disease patients to retrospective anonymized EHRs provided by the "University Hospital Salzburg" clinic group. Within 1 month, the AI screened 350,116 EHRs reaching back 15 years from five hospitals, and 104 patients were flagged as probable for Pompe disease. Flagged patients were manually reviewed and assessed by generalist and specialist physicians for their likelihood for Pompe disease, from which the performance of the algorithms was evaluated. Results: Of the 104 patients flagged by the algorithms, generalist physicians found five "diagnosed," 10 "suspected," and seven patients with "reduced suspicion." After feedback from Pompe disease specialist physicians, 19 patients remained clinically plausible for Pompe disease, resulting in a specificity of 18.27% for the AI. Estimating from the remaining plausible patients, the prevalence of Pompe disease for the greater Salzburg region [incl. Bavaria (Germany), Styria (Austria), and Upper Austria (Austria)] was one in every 18,427 people. Phenotypes for patient cohorts with an approximated onset of symptoms above or below 1 year of age were established, which correspond to infantile-onset Pompe disease (IOPD) and late-onset Pompe disease (LOPD), respectively. Conclusion: Our study shows the feasibility of Symptoma's AI-based approach for identifying rare disease patients using retrospective EHRs. Via the algorithm's screening of an entire EHR population, a physician had only to manually review 5.47 patients on average to find one suspected candidate. This efficiency is crucial as Pompe disease, while rare, is a progressively debilitating but treatable neuromuscular disease. As such, we demonstrated both the efficiency of the approach and the potential of a scalable solution to the systematic identification of rare disease patients. Thus, similar implementation of this methodology should be encouraged to improve care for all rare disease patients.

Establishing an Expert Consensus on Key Indicators of the Quality of Life among Breast Cancer Survivors: A Modified Delphi Study.

(1) Background: The needs of cancer survivors are often not reflected in practice. One of the main barriers of the use of patient-reported outcomes is associated with data collection and the interpretation of patient-reported outcomes (PROs) due to a multitude of instruments and measuring approaches. The aim of the study was to establish an expert consensus on the relevance and key indicators of quality of life in the clinical practice of breast cancer survivors. (2) Methods: Potential indicators of the quality of life of breast cancer survivors were extracted from the established quality of life models, depicting survivors' perspectives. The specific domains and subdomains of quality of life were evaluated in a two-stage online Delphi process, including an international and multidisciplinary panel of experts. (3) Results: The first round of the Delphi process was completed by 57 and the second by 37 participants. A consensus was reached for the Physical and Psychological domains, and on eleven subdomains of quality of life. The results were further supported by the additional ranking of importance of the subdomains in the second round. (4) Conclusions: The current findings can serve to optimize the use of instruments and address the challenges related to data collection and interpretation as the facilitators of the adaption in routine practice.

Symptoms associated with a COVID-19 infection among a non-hospitalized cohort in Vienna.

BACKGROUND: Most clinical studies report the symptoms experienced by those infected with coronavirus disease 2019 (COVID-19) via patients already hospitalized. Here we analyzed the symptoms experienced outside of a hospital setting. METHODS: The Vienna Social Fund (FSW; Vienna, Austria), the Public Health Services of the City of Vienna (MA15) and the private company Symptoma collaborated to implement Vienna's official online COVID-19 symptom checker. Users answered 12 yes/no questions about symptoms to assess their risk for COVID-19. They could also specify their age and sex, and whether they had contact with someone who tested positive for COVID-19. Depending on the assessed risk of COVID-19 positivity, a SARS-CoV­2 nucleic acid amplification test (NAAT) was performed. In this publication, we analyzed which factors (symptoms, sex or age) are associated with COVID-19 positivity. We also trained a classifier to correctly predict COVID-19 positivity from the collected data. RESULTS: Between 2 November 2020 and 18 November 2021, 9133 people experiencing COVID-19-like symptoms were assessed as high risk by the chatbot and were subsequently tested by a NAAT. Symptoms significantly associated with a positive COVID-19 test were malaise, fatigue, headache, cough, fever, dysgeusia and hyposmia. Our classifier could successfully predict COVID-19 positivity with an area under the curve (AUC) of 0.74. CONCLUSION: This study provides reliable COVID-19 symptom statistics based on the general population verified by NAATs.

An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot.

To combat the pandemic of the coronavirus disease 2019 (COVID-19), numerous governments have established phone hotlines to prescreen potential cases. These hotlines have struggled with the volume of callers, leading to wait times of hours or, even, an inability to contact health authorities. Symptoma is a symptom-to-disease digital health assistant that can differentiate more than 20,000 diseases with an accuracy of more than 90%. We tested the accuracy of Symptoma to identify COVID-19 using a set of diverse clinical cases combined with case reports of COVID-19. We showed that Symptoma can accurately distinguish COVID-19 in 96.32% of clinical cases. When considering only COVID-19 symptoms and risk factors, Symptoma identified 100% of those infected when presented with only three signs. Lastly, we showed that Symptoma's accuracy far exceeds that of simple "yes-no" questionnaires widely available online. In summary, Symptoma provides unparalleled accuracy in systematically identifying cases of COVID-19 while also considering over 20,000 other diseases. Furthermore, Symptoma allows free text input, furthered with disease-specific follow up questions, in 36 languages. Combined, these results and accessibility give Symptoma the potential to be a key tool in the global fight against COVID-19. The Symptoma predictor is freely available online at https://www.symptoma.com .

Diagnostic Accuracy of Web-Based COVID-19 Symptom Checkers: Comparison Study.

BACKGROUND: A large number of web-based COVID-19 symptom checkers and chatbots have been developed; however, anecdotal evidence suggests that their conclusions are highly variable. To our knowledge, no study has evaluated the accuracy of COVID-19 symptom checkers in a statistically rigorous manner. OBJECTIVE: The aim of this study is to evaluate and compare the diagnostic accuracies of web-based COVID-19 symptom checkers. METHODS: We identified 10 web-based COVID-19 symptom checkers, all of which were included in the study. We evaluated the COVID-19 symptom checkers by assessing 50 COVID-19 case reports alongside 410 non-COVID-19 control cases. A bootstrapping method was used to counter the unbalanced sample sizes and obtain confidence intervals (CIs). Results are reported as sensitivity, specificity, F1 score, and Matthews correlation coefficient (MCC). RESULTS: The classification task between COVID-19-positive and COVID-19-negative for "high risk" cases among the 460 test cases yielded (sorted by F1 score): Symptoma (F1=0.92, MCC=0.85), Infermedica (F1=0.80, MCC=0.61), US Centers for Disease Control and Prevention (CDC) (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Cleveland Clinic (F1=0.40, MCC=0.07), Providence (F1=0.40, MCC=0.05), Apple (F1=0.29, MCC=-0.10), Docyet (F1=0.27, MCC=0.29), Ada (F1=0.24, MCC=0.27) and Your.MD (F1=0.24, MCC=0.27). For "high risk" and "medium risk" combined the performance was: Symptoma (F1=0.91, MCC=0.83) Infermedica (F1=0.80, MCC=0.61), Cleveland Clinic (F1=0.76, MCC=0.47), Providence (F1=0.75, MCC=0.45), Your.MD (F1=0.72, MCC=0.33), CDC (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Apple (F1=0.70, MCC=0.25), Ada (F1=0.42, MCC=0.03), and Docyet (F1=0.27, MCC=0.29). CONCLUSIONS: We found that the number of correctly assessed COVID-19 and control cases varies considerably between symptom checkers, with different symptom checkers showing different strengths with respect to sensitivity and specificity. A good balance between sensitivity and specificity was only achieved by two symptom checkers.