MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis.

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar-Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89-0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7-58.7%) and the consensus of all five radiologists (59.3%, P < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.

Contextualising adverse events of special interest to characterise the baseline incidence rates in 24 million patients with COVID-19 across 26 databases: a multinational retrospective cohort study.

Background: Adverse events of special interest (AESIs) were pre-specified to be monitored for the COVID-19 vaccines. Some AESIs are not only associated with the vaccines, but with COVID-19. Our aim was to characterise the incidence rates of AESIs following SARS-CoV-2 infection in patients and compare these to historical rates in the general population. Methods: A multi-national cohort study with data from primary care, electronic health records, and insurance claims mapped to a common data model. This study's evidence was collected between Jan 1, 2017 and the conclusion of each database (which ranged from Jul 2020 to May 2022). The 16 pre-specified prevalent AESIs were: acute myocardial infarction, anaphylaxis, appendicitis, Bell's palsy, deep vein thrombosis, disseminated intravascular coagulation, encephalomyelitis, Guillain- Barré syndrome, haemorrhagic stroke, non-haemorrhagic stroke, immune thrombocytopenia, myocarditis/pericarditis, narcolepsy, pulmonary embolism, transverse myelitis, and thrombosis with thrombocytopenia. Age-sex standardised incidence rate ratios (SIR) were estimated to compare post-COVID-19 to pre-pandemic rates in each of the databases. Findings: Substantial heterogeneity by age was seen for AESI rates, with some clearly increasing with age but others following the opposite trend. Similarly, differences were also observed across databases for same health outcome and age-sex strata. All studied AESIs appeared consistently more common in the post-COVID-19 compared to the historical cohorts, with related meta-analytic SIRs ranging from 1.32 (1.05 to 1.66) for narcolepsy to 11.70 (10.10 to 13.70) for pulmonary embolism. Interpretation: Our findings suggest all AESIs are more common after COVID-19 than in the general population. Thromboembolic events were particularly common, and over 10-fold more so. More research is needed to contextualise post-COVID-19 complications in the longer term. Funding: None.

La era del big data: análisis del lenguaje natural mediante la aplicación de folksonomía / The big data era: The usefulness of folksonomy for natural language processing

Antecedentes y objetivo: Gran parte de la información médica que se deriva de la práctica clínica habitual queda recogida en forma de lenguaje natural en los informes médicos. Clásicamente, la extracción de información clínica para su posterior análisis a partir de los informes médicos requiere de la lectura y revisión manual de cada uno de ellos con la consiguiente inversión de tiempo. El objetivo de este proyecto piloto ha sido evaluar la utilidad de la folksonomía para la extracción y análisis rápido de los datos que contienen los informes médicos. Material y métodos: En este proyecto piloto hemos utilizado la folksonomía para el análisis y la rápida extracción de datos de 1.631 informes médicos de alta de hospitalización del Servicio de Nefrología del Hospital del Mar sin necesidad de crear una base de datos estructurada previamente. Resultados: A partir de determinadas preguntas sobre la práctica médica habitual (tratamiento hipoglicemiante de los pacientes diabéticos, tratamiento antihipertensivo y manejo de los inhibidores del sistema renina angiotensina durante el ingreso en nefrología y análisis de datos relacionados con la esfera emocional de los pacientes renales) la herramienta ha permitido estructurar y analizar la información contenida en texto libre en los informes de alta. Conclusiones: La aplicación de folksonomía a los informes médicos nos permite transformar la información contenida en lenguaje natural en una serie de datos estructurados y analizables de manera automática sin necesidad de proceder a la revisión manual de los mismos. (AU)

Background: A huge amount of clinical data is daily generated and it is usually filed in clinical reports as natural language. Data extraction and further analysis requires reading and manual review of each report, which is a time consuming process. With the aim to test folksonomy to quickly obtain and analyze the information contained in medial reports we set up this study. Methods and objectives:We have used folksonomy to quickly obtain and analyse data from 1631 discharge clinical reports from Nephrology Department of Hospital del Mar, without the need to create an structured database. Results: After posing some questions related to daily clinical practice (hypoglycaemic drugs used in diabetic patients, antihypertensive drugs and the use of renin angiotensin blockers during hospitalisation in the nephrology department and data related to emotional environment of patients with chronic kidney disease) this tool has allowed the conversion of unstructured information in natural language into a structured pool of data for its further analysis. Conclusions: Folksonomy allows the conversion of the information contained in clinical reports as natural language into a pool of structured data which can be further easily analysed without the need of the classical manual review of the reports. (AU)

Exploring the Association of Cancer and Depression in Electronic Health Records: Combining Encoded Diagnosis and Mining Free-Text Clinical Notes.

BACKGROUND: A cancer diagnosis is a source of psychological and emotional stress, which are often maintained for sustained periods of time that may lead to depressive disorders. Depression is one of the most common psychological conditions in patients with cancer. According to the Global Cancer Observatory, breast and colorectal cancers are the most prevalent cancers in both sexes and across all age groups in Spain. OBJECTIVE: This study aimed to compare the prevalence of depression in patients before and after the diagnosis of breast or colorectal cancer, as well as to assess the usefulness of the analysis of free-text clinical notes in 2 languages (Spanish or Catalan) for detecting depression in combination with encoded diagnoses. METHODS: We carried out an analysis of the electronic health records from a general hospital by considering the different sources of clinical information related to depression in patients with breast and colorectal cancer. This analysis included ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification) diagnosis codes and unstructured information extracted by mining free-text clinical notes via natural language processing tools based on Systematized Nomenclature of Medicine Clinical Terms that mentions symptoms and drugs used for the treatment of depression. RESULTS: We observed that the percentage of patients diagnosed with depressive disorders significantly increased after cancer diagnosis in the 2 types of cancer considered-breast and colorectal cancers. We managed to identify a higher number of patients with depression by mining free-text clinical notes than the group selected exclusively on ICD-9-CM codes, increasing the number of patients diagnosed with depression by 34.8% (441/1269). In addition, the number of patients with depression who received chemotherapy was higher than those who did not receive this treatment, with significant differences (P<.001). CONCLUSIONS: This study provides new clinical evidence of the depression-cancer comorbidity and supports the use of natural language processing for extracting and analyzing free-text clinical notes from electronic health records, contributing to the identification of additional clinical data that complements those provided by coded data to improve the management of these patients.

Unraveling COVID-19: A Large-Scale Characterization of 4.5 Million COVID-19 Cases Using CHARYBDIS.

Purpose: Routinely collected real world data (RWD) have great utility in aiding the novel coronavirus disease (COVID-19) pandemic response. Here we present the international Observational Health Data Sciences and Informatics (OHDSI) Characterizing Health Associated Risks and Your Baseline Disease In SARS-COV-2 (CHARYBDIS) framework for standardisation and analysis of COVID-19 RWD. Patients and Methods: We conducted a descriptive retrospective database study using a federated network of data partners in the United States, Europe (the Netherlands, Spain, the UK, Germany, France and Italy) and Asia (South Korea and China). The study protocol and analytical package were released on 11th June 2020 and are iteratively updated via GitHub. We identified three non-mutually exclusive cohorts of 4,537,153 individuals with a clinical COVID-19 diagnosis or positive test, 886,193 hospitalized with COVID-19, and 113,627 hospitalized with COVID-19 requiring intensive services. Results: We aggregated over 22,000 unique characteristics describing patients with COVID-19. All comorbidities, symptoms, medications, and outcomes are described by cohort in aggregate counts and are readily available online. Globally, we observed similarities in the USA and Europe: more women diagnosed than men but more men hospitalized than women, most diagnosed cases between 25 and 60 years of age versus most hospitalized cases between 60 and 80 years of age. South Korea differed with more women than men hospitalized. Common comorbidities included type 2 diabetes, hypertension, chronic kidney disease and heart disease. Common presenting symptoms were dyspnea, cough and fever. Symptom data availability was more common in hospitalized cohorts than diagnosed. Conclusion: We constructed a global, multi-centre view to describe trends in COVID-19 progression, management and evolution over time. By characterising baseline variability in patients and geography, our work provides critical context that may otherwise be misconstrued as data quality issues. This is important as we perform studies on adverse events of special interest in COVID-19 vaccine surveillance.

The big data era: The usefulness of folksonomy for natural language processing.

BACKGROUND: A huge amount of clinical data is generated daily and it is usually filed in clinical reports as natural language. Data extraction and further analysis requires reading and manual review of each report, which is a time consuming process. With the aim to test folksonomy to quickly obtain and analyze the information contained in media reports we set up this study. METHODS AND OBJECTIVES: We have used folksonomy to quickly obtain and analyze data from 1631 discharge clinical reports from the Nephrology Department of Hospital del Mar, without the need to create a structured database. RESULTS: After posing some questions related to daily clinical practice (hypoglycaemic drugs used in diabetic patients, antihypertensive drugs and the use of renin angiotensin blockers during hospitalization in the nephrology department and data related to emotional environment of patients with chronic kidney disease) this tool has allowed the conversion of unstructured information in natural language into a structured pool of data for its further analysis. CONCLUSIONS: Folksonomy allows the conversion of the information contained in clinical reports as natural language into a pool of structured data which can be further easily analyzed without the need for the classical manual review of the reports.

Characteristics and outcomes of patients with COVID-19 with and without prevalent hypertension: a multinational cohort study.

OBJECTIVE: To characterise patients with and without prevalent hypertension and COVID-19 and to assess adverse outcomes in both inpatients and outpatients. DESIGN AND SETTING: This is a retrospective cohort study using 15 healthcare databases (primary and secondary electronic healthcare records, insurance and national claims data) from the USA, Europe and South Korea, standardised to the Observational Medical Outcomes Partnership common data model. Data were gathered from 1 March to 31 October 2020. PARTICIPANTS: Two non-mutually exclusive cohorts were defined: (1) individuals diagnosed with COVID-19 (diagnosed cohort) and (2) individuals hospitalised with COVID-19 (hospitalised cohort), and stratified by hypertension status. Follow-up was from COVID-19 diagnosis/hospitalisation to death, end of the study period or 30 days. OUTCOMES: Demographics, comorbidities and 30-day outcomes (hospitalisation and death for the 'diagnosed' cohort and adverse events and death for the 'hospitalised' cohort) were reported. RESULTS: We identified 2 851 035 diagnosed and 563 708 hospitalised patients with COVID-19. Hypertension was more prevalent in the latter (ranging across databases from 17.4% (95% CI 17.2 to 17.6) to 61.4% (95% CI 61.0 to 61.8) and from 25.6% (95% CI 24.6 to 26.6) to 85.9% (95% CI 85.2 to 86.6)). Patients in both cohorts with hypertension were predominantly >50 years old and female. Patients with hypertension were frequently diagnosed with obesity, heart disease, dyslipidaemia and diabetes. Compared with patients without hypertension, patients with hypertension in the COVID-19 diagnosed cohort had more hospitalisations (ranging from 1.3% (95% CI 0.4 to 2.2) to 41.1% (95% CI 39.5 to 42.7) vs from 1.4% (95% CI 0.9 to 1.9) to 15.9% (95% CI 14.9 to 16.9)) and increased mortality (ranging from 0.3% (95% CI 0.1 to 0.5) to 18.5% (95% CI 15.7 to 21.3) vs from 0.2% (95% CI 0.2 to 0.2) to 11.8% (95% CI 10.8 to 12.8)). Patients in the COVID-19 hospitalised cohort with hypertension were more likely to have acute respiratory distress syndrome (ranging from 0.1% (95% CI 0.0 to 0.2) to 65.6% (95% CI 62.5 to 68.7) vs from 0.1% (95% CI 0.0 to 0.2) to 54.7% (95% CI 50.5 to 58.9)), arrhythmia (ranging from 0.5% (95% CI 0.3 to 0.7) to 45.8% (95% CI 42.6 to 49.0) vs from 0.4% (95% CI 0.3 to 0.5) to 36.8% (95% CI 32.7 to 40.9)) and increased mortality (ranging from 1.8% (95% CI 0.4 to 3.2) to 25.1% (95% CI 23.0 to 27.2) vs from 0.7% (95% CI 0.5 to 0.9) to 10.9% (95% CI 10.4 to 11.4)) than patients without hypertension. CONCLUSIONS: COVID-19 patients with hypertension were more likely to suffer severe outcomes, hospitalisations and deaths compared with those without hypertension.

Prescription and Integration of Accredited Mobile Apps in Catalan Health and Social Care: Protocol for the AppSalut Site Design.

BACKGROUND: The use of new mobile technologies in the health and social welfare sectors is already a reality. The ICT Social Health Foundation, in accordance with the technology strategy of the Catalan government's Ministry of Health and its Ministry of Labour, Social Affairs and Families, is leading an initiative to create a public library of apps for its AppSalut Site. OBJECTIVE: The objective of this paper is to present an account of the design of the project, with a global perspective, applied to the Catalan ecosystem, which can be divided into 3 areas: the framework governing the recommendation and prescription of apps, the subset of interoperability for mobile environments, and the data storage infrastructure. METHODS: The security and credibility of the apps included in the catalog is ensured by submitting them to an accreditation process in the public domain that provides users with the guarantee that they are fit for purpose and trustworthy for the management and care of their health, while providing health care professionals with the possibility of recommending the apps in the doctor's surgery, as well as adding the information generated by the users' mobile devices to the information systems of the various organizations concerned. RESULTS: An examination of the abovementioned areas suggests possibilities for improvements in the future. The experience obtained from the development of this element has shown the heterogeneity of the vocabularies used, as expected, due to the lack of awareness on the part of the developers regarding the need to standardize the information generated by the app, requiring the foundation to take on the role of consultant. CONCLUSIONS: The project has evolved in keeping with changes in the technological and social paradigm and responds very satisfactorily to the needs posed to it. It can be seen as a landmark experience in mobile strategies in the fields of health and welfare of any public health system. The experience has shown itself to be feasible in organizational terms, necessary in any attempt to integrate mobile technologies into public health practice, and a global pioneer in the field. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/11414.

The Prescription of Mobile Apps by Primary Care Teams: A Pilot Project in Catalonia.

BACKGROUND: In Catalonia, the Fundació TIC Salut Social's mHealth Office created the AppSalut Site to showcase to mobile apps in the field of health and social services. Its primary objective was to encourage the public to look after their health. The catalogue allows primary health care doctors to prescribe certified, connected apps, which guarantees a safe and reliable environment for their use. The generated data can be consulted by health care professionals and included in the patient's clinical history. This document presents the intervention and the major findings following a five-month pilot project conducted in the Barcelona area. OBJECTIVE: The objective of the pilot study was to test, in a real, controlled environment, the implementation of AppSalut. Specifically, we tested whether (1) the procedures corresponding to the prescription, transmission, and evaluation of the data functions correctly, (2) users interact successfully and accept the tool, and (3) the data travels through existing pathways in accordance with international standards. The evaluation is not based on clinical criteria, but rather on the usability and technological reliability of the intervention and its implementation in the context of primary care. METHODS: The project was presented to the Primary Care Team participants to encourage the involvement of doctors. The study involved at least 5 doctors and 5 patients per professional, chosen at their discretion and in accordance with their own clinical criteria. An initial consultation took place, during which the doctor discussed the pilot project with the patient and recommended the app. The patient was sent a text message (SMS, short message service) containing an access code. When the patient arrived home, they accessed their personal health record (PHR) to view the recommendation, download the app, and enter the access code. The patient was then able to start using the app. The data was collected in a standardized manner and automatically sent to the system. In a second visit, the patient looked at the data with their doctor on their clinical station screen. The latter was able to consult the information generated by the patient and select what to include in their electronic health record. In order to assess the performance of the system, three focus groups were performed and two ad-hoc case-specific questionnaires, one for doctors and one for patients, were sent by email. Response was voluntary. RESULTS: A total of 32 doctors made 79 recommendations of apps to patients. On average, the patients uploaded data 13 times per prescribed app, accounting for a total of 16 different variables. Results show that data traveled through the established channels in an adequate manner and in accordance with international standards. This includes the prescription of an app by a doctor, the patient accessing the recommendation via the PHR, app download by the patient from the official app stores, linking of the patient to the public platform through the app, the generation and visualization of the data on the primary care workstation, and its subsequent validation by the clinician. CONCLUSIONS: First, the choice of apps to be used is fundamental; the user's perception of the utility of the proposed tool being paramount. Second, thorough face-to-face support is vital for a smooth transition towards a more intense model of telemedicine. Last, a powerful limiting factor is the lack of control over people's ability to use the apps.

[Digital health as a motor for change towards new healthcare models and the relationship between patients and healthcare professionals. Disruption of healthcare processes]. / La salud digital como motor de cambio hacia nuevos modelos asistenciales y de relación entre los pacientes y los profesionales de la salud. La disrupción de los procesos asistenciales.

We find ourselves at the end of an era of asymmetry in the domain of health information where the majority of this data is in the hands of the healthcare system. Increasingly, the public are calling for a more central role in the new paradigm that enables them to duly exercise their right of access to their health data while availing of more reliable and safer technologies which contribute to the management of their condition and promote healthy lifestyles. So far, the TIC Salud strategic plan has been developed independently from the Generalitat de Catalunya Health Department's Healthcare Plan, which sets out health policy strategy in Catalonia. However, from its initial design stage the new Healthcare Plan (2016- 2020) envisages incorporating a new strategic Information and communications technology (ICT) line called "Digital Health". Incorporating ICT into the Health Plan will allow these technologies to become integral part of all strategic healthcare processes, acting as a driving force for a shift towards a new healthcare models and an innovative relationship between the public and healthcare professionals. The Digital Health implies a disruption in itself, by way of the convergence of several technologies and their positive impact on health and healthcare procedures, by way of the public's access to information concerning their health, and by creating new opportunities for promoting health and the salutogenic paradigm which empowers people to develop their health, welfare and quality of life.

La salud digital como motor de cambio hacia nuevos modelos asistenciales y de relación entre los pacientes y los profesionales de la salud. La disrupción de los procesos asistenciales / No disponible

Nos encontramos al final de una época de asimetría en el dominio de la información de salud, donde la mayor parte de esta se halla bajo custodia del sistema sanitario. Cada vez más, el ciudadano reclama un papel central dentro del nuevo paradigma, que le posibilite ejercer adecuadamente el derecho de acceso a sus datos de salud y disponer de tecnologías fiables y seguras que contribuyan al manejo de su condición y la promoción de estilos de vida saludables. Hasta ahora, el plan estratégico TIC Salud se desarrollaba de forma independiente al Plan de Salud del Departament de Salut de la Generalitat de Catalunya, que marca la estrategia de las políticas de salud en el territorio catalán. Sin embargo, el nuevo Plan de Salud (2016- 2020) contempla desde su diseño inicial la incorporación de una nueva línea estratégica TIC (tecnologías de la información y la comunicación) denominada “Salud Digital”. Introducir las TIC en el Plan de Salud va a permitir que estas tecnologías sean integradas en todos los procesos asistenciales estratégicos, actuando como motor de cambio hacia nuevos modelos asistenciales y de relación entre los ciudadanos y los profesionales de la salud. La Salud Digital lleva consigo disrupción, por la convergencia de distintas tecnologías y su impacto positivo sobre la salud y los procesos asistenciales, por el acceso de todos los ciudadanos a la información sobre su salud y por la generación de nuevas oportunidades para la promoción de la salud y el paradigma salutogénico, que empodera al ciudadano en el desarrollo de su salud, bienestar y calidad de vida (AU)

We find ourselves at the end of an era of asymmetry in the domain of health information where the majority of this data is in the hands of the healthcare system. Increasingly, the public are calling for a more central role in the new paradigm that enables them to duly exercise their right of access to their health data while availing of more reliable and safer technologies which contribute to the management of their condition and promote healthy lifestyles. So far, the TIC Salud strategic plan has been developed independently from the Generalitat de Catalunya Health Department's Healthcare Plan, which sets out health policy strategy in Catalonia. However, from its initial design stage the new Healthcare Plan (2016- 2020) envisages incorporating a new strategic Information and communications technology (ICT) line called “Digital Health”. Incorporating ICT into the Health Plan will allow these technologies to become integral part of all strategic healthcare processes, acting as a driving force for a shift towards a new healthcare models and an innovative relationship between the public and healthcare professionals. The Digital Health implies a disruption in itself, by way of the convergence of several technologies and their positive impact on health and healthcare procedures, by way of the public's access to information concerning their health, and by creating new opportunities for promoting health and the salutogenic paradigm which empowers people to develop their health, welfare and quality of life (AU)