Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions.

OBJECTIVE: To develop and validate a natural language processing (NLP) pipeline that detects 18 conditions in French clinical notes, including 16 comorbidities of the Charlson index, while exploring a collaborative and privacy-enhancing workflow. MATERIALS AND METHODS: The detection pipeline relied both on rule-based and machine learning algorithms, respectively, for named entity recognition and entity qualification, respectively. We used a large language model pre-trained on millions of clinical notes along with annotated clinical notes in the context of 3 cohort studies related to oncology, cardiology, and rheumatology. The overall workflow was conceived to foster collaboration between studies while respecting the privacy constraints of the data warehouse. We estimated the added values of the advanced technologies and of the collaborative setting. RESULTS: The pipeline reached macro-averaged F1-score positive predictive value, sensitivity, and specificity of 95.7 (95%CI 94.5-96.3), 95.4 (95%CI 94.0-96.3), 96.0 (95%CI 94.0-96.7), and 99.2 (95%CI 99.0-99.4), respectively. F1-scores were superior to those observed using alternative technologies or non-collaborative settings. The models were shared through a secured registry. CONCLUSIONS: We demonstrated that a community of investigators working on a common clinical data warehouse could efficiently and securely collaborate to develop, validate and use sensitive artificial intelligence models. In particular, we provided an efficient and robust NLP pipeline that detects conditions mentioned in clinical notes.

Natural language processing of multi-hospital electronic health records for public health surveillance of suicidality.

There is an urgent need to monitor the mental health of large populations, especially during crises such as the COVID-19 pandemic, to timely identify the most at-risk subgroups and to design targeted prevention campaigns. We therefore developed and validated surveillance indicators related to suicidality: the monthly number of hospitalisations caused by suicide attempts and the prevalence among them of five known risks factors. They were automatically computed analysing the electronic health records of fifteen university hospitals of the Paris area, France, using natural language processing algorithms based on artificial intelligence. We evaluated the relevance of these indicators conducting a retrospective cohort study. Considering 2,911,920 records contained in a common data warehouse, we tested for changes after the pandemic outbreak in the slope of the monthly number of suicide attempts by conducting an interrupted time-series analysis. We segmented the assessment time in two sub-periods: before (August 1, 2017, to February 29, 2020) and during (March 1, 2020, to June 31, 2022) the COVID-19 pandemic. We detected 14,023 hospitalisations caused by suicide attempts. Their monthly number accelerated after the COVID-19 outbreak with an estimated trend variation reaching 3.7 (95%CI 2.1-5.3), mainly driven by an increase among girls aged 8-17 (trend variation 1.8, 95%CI 1.2-2.5). After the pandemic outbreak, acts of domestic, physical and sexual violence were more often reported (prevalence ratios: 1.3, 95%CI 1.16-1.48; 1.3, 95%CI 1.10-1.64 and 1.7, 95%CI 1.48-1.98), fewer patients died (p = 0.007) and stays were shorter (p < 0.001). Our study demonstrates that textual clinical data collected in multiple hospitals can be jointly analysed to compute timely indicators describing mental health conditions of populations. Our findings also highlight the need to better take into account the violence imposed on women, especially at early ages and in the aftermath of the COVID-19 pandemic.

Development and Validation of a Natural Language Processing Algorithm to Pseudonymize Documents in the Context of a Clinical Data Warehouse.

OBJECTIVE: The objective of this study is to address the critical issue of deidentification of clinical reports to allow access to data for research purposes, while ensuring patient privacy. The study highlights the difficulties faced in sharing tools and resources in this domain and presents the experience of the Greater Paris University Hospitals (AP-HP for Assistance Publique-Hôpitaux de Paris) in implementing a systematic pseudonymization of text documents from its Clinical Data Warehouse. METHODS: We annotated a corpus of clinical documents according to 12 types of identifying entities and built a hybrid system, merging the results of a deep learning model as well as manual rules. RESULTS AND DISCUSSION: Our results show an overall performance of 0.99 of F1-score. We discuss implementation choices and present experiments to better understand the effort involved in such a task, including dataset size, document types, language models, or rule addition. We share guidelines and code under a 3-Clause BSD license.

Impact of the COVID-19 pandemic on clinical presentation, treatments, and outcomes of new breast cancer patients: A retrospective multicenter cohort study.

BACKGROUND: The SARS CoV-2 pandemic disrupted healthcare systems. We compared the cancer stage for new breast cancers (BCs) before and during the pandemic. METHODS: We performed a retrospective multicenter cohort study on the data warehouse of Greater Paris University Hospitals (AP-HP). We identified all female patients newly referred with a BC in 2019 and 2020. We assessed the timeline of their care trajectories, initial tumor stage, and treatment received: BC resection, exclusive systemic therapy, exclusive radiation therapy, or exclusive best supportive care (BSC). We calculated patients' 1-year overall survival (OS) and compared indicators in 2019 and 2020. RESULTS: In 2019 and 2020, 2055 and 1988, new BC patients underwent cancer treatment, and during the two lockdowns, the BC diagnoses varied by -18% and by +23% compared to 2019. De novo metastatic tumors (15% and 15%, p = 0.95), pTNM and ypTNM distributions of 1332 cases with upfront resection and of 296 cases with neoadjuvant therapy did not differ (p = 0.37, p = 0.3). The median times from first multidisciplinary meeting and from diagnosis to treatment of 19 days (interquartile 11-39 days) and 35 days (interquartile 22-65 days) did not differ. Access to plastic surgery (15% and 17%, p = 0.08) and to treatment categories did not vary: tumor resection (73% and 72%), exclusive systemic therapy (13% and 14%), exclusive radiation therapy (9% and 9%), exclusive BSC (5% and 5%) (p = 0.8). Among resected patients, the neoadjuvant therapy rate was lower in 2019 (16%) versus 2020 (20%) (p = 0.02). One-year OS rates were 99.3% versus 98.9% (HR = 0.96; 95% CI, 0.77-1.2), 72.6% versus 76.6% (HR = 1.28; 95% CI, 0.95-1.72), 96.6% versus 97.8% (HR = 1.09; 95% CI, 0.61-1.94), and 15.5% versus 15.1% (HR = 0.99; 95% CI, 0.72-1.37), in the treatment groups. CONCLUSIONS: Despite a decrease in the number of new BCs, there was no tumor stage shift, and OS did not vary.

Development of a natural language processing model for deriving breast cancer quality indicators : A cross-sectional, multicenter study.

OBJECTIVES: Medico-administrative data are promising to automate the calculation of Healthcare Quality and Safety Indicators. Nevertheless, not all relevant indicators can be calculated with this data alone. Our feasibility study objective is to analyze 1) the availability of data sources; 2) the availability of each indicator elementary variables, and 3) to apply natural language processing to automatically retrieve such information. METHOD: We performed a multicenter cross-sectional observational feasibility study on the clinical data warehouse of Assistance Publique - Hôpitaux de Paris (AP-HP). We studied the management of breast cancer patients treated at AP-HP between January 2019 and June 2021, and the quality indicators published by the European Society of Breast Cancer Specialist, using claims data from the Programme de Médicalisation du Système d'Information (PMSI) and pathology reports. For each indicator, we calculated the number (%) of patients for whom all necessary data sources were available, and the number (%) of patients for whom all elementary variables were available in the sources, and for whom the related HQSI was computable. To extract useful data from the free text reports, we developed and validated dedicated rule-based algorithms, whose performance metrics were assessed with recall, precision, and f1-score. RESULTS: Out of 5785 female patients diagnosed with a breast cancer (60.9 years, IQR [50.0-71.9]), 5,147 (89.0%) had procedures related to breast cancer recorded in the PMSI, and 3732 (72.5%) had at least one surgery. Out of the 34 key indicators, 9 could be calculated with the PMSI alone, and 6 others became so using the data from pathology reports. Ten elementary variables were needed to calculate the 6 indicators combining the PMSI and pathology reports. The necessary sources were available for 58.8% to 94.6% of patients, depending on the indicators. The extraction algorithms developed had an average accuracy of 76.5% (min-max [32.7%-93.3%]), an average precision of 77.7% [10.0%-97.4%] and an average sensitivity of 71.6% [2.8% to 100.0%]. Once these algorithms applied, the variables needed to calculate the indicators were extracted for 2% to 88% of patients, depending on the indicators. DISCUSSION: The availability of medical reports in the electronic health records, of the elementary variables within the reports, and the performance of the extraction algorithms limit the population for which the indicators can be calculated. CONCLUSIONS: The automated calculation of quality indicators from electronic health records is a prospect that comes up against many practical obstacles.

No changes in clinical presentation, treatment strategies and survival of pancreatic cancer cases during the SARS-COV-2 outbreak: A retrospective multicenter cohort study on real-world data.

The SARS-COV-2 pandemic disrupted healthcare systems. We assessed its impact on the presentation, care trajectories and outcomes of new pancreatic cancers (PCs) in the Paris area. We performed a retrospective multicenter cohort study on the data warehouse of Greater Paris University Hospitals (AP-HP). We identified all patients newly referred with a PC between January 1, 2019, and June 30, 2021, and excluded endocrine tumors. Using claims data and health records, we analyzed the timeline of care trajectories, the initial tumor stage, the treatment categories: pancreatectomy, exclusive systemic therapy or exclusive best supportive care (BSC). We calculated patients' 1-year overall survival (OS) and compared indicators in 2019 and 2020 to 2021. We included 2335 patients. Referral fell by 29% during the first lockdown. The median time from biopsy and from first MDM to treatment were 25 days (16-50) and 21 days (11-40), respectively. Between 2019 and 2020 to 2021, the rate of metastatic tumors (36% vs 33%, P = .39), the pTNM distribution of the 464 cases with upfront tumor resection (P = .80), and the proportion of treatment categories did not vary: tumor resection (32% vs 33%), exclusive systemic therapy (49% vs 49%), exclusive BSC (19% vs 19%). The 1-year OS rates in 2019 vs 2020 to 2021 were 92% vs 89% (aHR = 1.42; 95% CI, 0.82-2.48), 52% vs 56% (aHR = 0.88; 95% CI, 0.73-1.08), 13% vs 10% (aHR = 1.00; 95% CI, 0.78-1.25), in the treatment categories, respectively. Despite an initial decrease in the number of new PCs, we did not observe any stage shift. OS did not vary significantly.

Why Are Data Missing in Clinical Data Warehouses? A Simulation Study of How Data Are Processed (and Can Be Lost).

In recent years, the development of clinical data warehouses (CDW) has put Electronic Health Records (EHR) data in the spotlight. More and more innovative technologies for healthcare are based on these EHR data. However, quality assessments on EHR data are fundamental to gain confidence in the performances of new technologies. The infrastructure developed to access EHR data - CDW - can affect EHR data quality but its impact is difficult to measure. We conducted a simulation on the Assistance Publique - Hôpitaux de Paris (AP-HP) infrastructure to assess how a study on breast cancer care pathways could be affected by the complexity of the data flows between the AP-HP Hospital Information System, the CDW, and the analysis platform. A model of the data flows was developed. We retraced the flows of specific data elements for a simulated cohort of 1,000 patients. We estimated that 756 [743;770] and 423 [367;483] patients had all the data elements necessary to reconstruct the care pathway in the analysis platform in the "best case" scenarios (losses affect the same patients) and in a random distribution scenario (losses affect patients at random), respectively.

Influence of the SARS-CoV-2 outbreak on management and prognosis of new lung cancer cases, a retrospective multicentre real-life cohort study.

INTRODUCTION: The SARS-CoV-2 pandemic has impacted the care of cancer patients. This study sought to assess the pandemic's impact on the clinical presentations and outcomes of newly referred patients with lung cancer from the Greater Paris area. METHODS: We retrospectively retrieved the electronic health records and administrative data of 11.4 million patients pertaining to Greater Paris University Hospital (AP-HP). We compared indicators for the 2018-2019 period to those of 2020 in regard to newly referred lung cancer cases. We assessed the initial tumour stage, the delay between the first multidisciplinary tumour board (MTB) and anticancer treatment initiation, and 6-month overall survival (OS) rates depending on the anticancer treatment, including surgery, palliative systemic treatment, and best supportive care (BSC). RESULT: Among 6240 patients with lung cancer, 2179 (35%) underwent tumour resection, 2069 (33%) systemic anticancer therapy, 775 (12%) BSC, whereas 1217 (20%) did not receive any treatment. During the first lockdown, the rate of new diagnoses decreased by 32% compared with that recorded in 2018-2019. Initial tumour stage, repartition of patients among treatment categories, and MTB-related delays remained unchanged. The 6-month OS rates of patients diagnosed in 2018-2019 who underwent tumour resection were 98% versus 97% (HR = 1.2; 95% CI: 0.7-2.0) for those diagnosed in 2020; the respective rates for patients who underwent systemic anticancer therapy were 78% versus 79% (HR = 1.0; 95% CI: 0.8-1.2); these rates were 20% versus 13% (HR = 1.3; 95% CI: 1.1-1.6) for those who received BSC. COVID-19 was associated with poorer OS rates (HR = 2.1; 95% CI: 1.6-3.0) for patients who received systemic anticancer therapy. CONCLUSIONS: The SARS-CoV-2 pandemic has not exerted any deleterious impact on 6-month OS of new lung cancer patients that underwent active anticancer therapy in Greater Paris University hospitals.

AP-HP Health Data Space (AHDS) to the Test of the Covid-19 Pandemic.

Sharing observational and interventional health data within a common data space enables university hospitals to leverage such data for biomedical discovery and moving towards a learning health system. OBJECTIVE: To describe the AP-HP Health Data Space (AHDS) and the IT services supporting piloting, research, innovation and patient care. METHODS: Built on three pillars - governance and ethics, technology and valorization - the AHDS and its major component, the Clinical Data Warehouse (CDW) have been developed since 2015. RESULTS: The AP-HP CDW has been made available at scale to AP-HP both healthcare professionals and public or private partners in January 2017. Supported by an institutional secured and high-performance cloud and an ecosystem of tools, mostly open source, the AHDS integrates a large amount of massive healthcare data collected during care and research activities. As of December 2021, the AHDS operates the electronic data capture for almost +840 clinical trials sponsored by AP-HP, the CDW is enabling the processing of health data from more than 11 million patients and generated +200 secondary data marts from IRB authorized research projects. During the Covid-19 pandemic, AHDS has had to evolve quickly to support administrative professionals and caregivers heavily involved in the reorganization of both patient care and biomedical research. CONCLUSION: The AP-HP Data Space is a key facilitator for data-driven evidence generation and making the health system more efficient and personalized.

Impact of two waves of Sars-Cov2 outbreak on the number, clinical presentation, care trajectories and survival of patients newly referred for a colorectal cancer: A French multicentric cohort study from a large group of university hospitals.

The SARS-Cov2 may have impaired care trajectories, patient overall survival (OS), tumor stage at initial presentation for new colorectal cancer (CRC) cases. This study aimed at assessing those indicators before and after the beginning of the pandemic in France. In this retrospective cohort study, we collected prospectively the clinical data of the 11.4 million of patients referred to the Greater Paris University Hospitals (AP-HP). We identified new CRC cases between 1 January 2018 and 31 December 2020, and compared indicators for 2018-2019 to 2020. pTNM tumor stage was extracted from postoperative pathology reports for localized colon cancer, and metastatic status was extracted from CT-scan baseline text reports. Between 2018 and 2020, 3602 and 1083 new colon and rectal cancers were referred to the AP-HP, respectively. The 1-year OS rates reached 94%, 93% and 76% for new CRC patients undergoing a resection of the primary tumor, in 2018-2019, in 2020 without any Sars-Cov2 infection and in 2020 with a Sars-Cov2 infection, respectively (HR 3.78, 95% CI 2.1-7.1). For patients undergoing other kind of anticancer treatment, the percentages are 64%, 66% and 27% (HR 2.1, 95% CI 1.4-3.3). Tumor stage at initial presentation, emergency level of primary tumor resection, delays between the first multidisciplinary meeting and the first anticancer treatment did not differ over time. The SARS-Cov2 pandemic has been associated with less newly diagnosed CRC patients and worse 1-year OS rates attributable to the infection itself rather than to its impact on hospital care delivery or tumor stage at initial presentation.

Carbon dioxide as a line active agent: Its impact on line tension and nucleation rate.

By considering a water capillary bridge confined between two flat surfaces, we investigate the thermodynamics of the triple line delimiting this solid-liquid-vapor system when supplemented in carbon dioxide. In more detail, by means of atom-scale simulations, we show that carbon dioxide accumulates at the solid walls and, preferably, at the triple lines where it plays the role of a line active agent. The line tension of the triple line, which is quantitatively assessed using an original mechanical route, is shown to be driven by the line excess concentrations of the solute (carbon dioxide) and solvent (water). Solute accumulation at the lines decreases the negative line tension (i.e., more negative) while solvent depletion from the lines has the opposite effect. Such an unprecedented quantitative assessment of gas-induced line tension modifications shows that the absolute value of the negative line tension increases upon increasing the carbon dioxide partial pressure. As a striking example, for hydrophilic surfaces, the line tension is found to increase by more than an order of magnitude when the carbon dioxide pressure exceeds 3 MPa. By considering the coupling between line and surface effects induced by gaseous adsorption, we hypothesize from the observed gas concentration-dependent line tension a nontrivial impact on heterogeneous nucleation of nanometric critical nuclei.

New cancer cases at the time of SARS-Cov2 pandemic and related public health policies: A persistent and concerning decrease long after the end of the national lockdown.

INTRODUCTION: The dissemination of SARS-Cov2 may have delayed the diagnosis of new cancers. This study aimed at assessing the number of new cancers during and after the lockdown. METHODS: We prospectively collected the clinical data of the 11.4 million patients referred to the Assistance Publique Hôpitaux de Paris Teaching Hospital. We identified new cancer cases between 1st January 2018 and 31st September 2020 and compared indicators for 2018 and 2019 to 2020 with a focus on the French lockdown (17th March to 11th May 2020) across cancer types and patient age classes. RESULTS: Between January and September, 28,348, 27,272 and 23,734 new cancer cases were identified in 2018, 2019 and 2020, respectively. The monthly median number of new cases reached 3168 (interquartile range, IQR, 3027; 3282), 3054 (IQR 2945; 3127) and 2723 (IQR 2085; 2,863) in 2018, 2019 and 2020, respectively. From March 1st to May 31st, new cancer decreased by 30% in 2020 compared to the 2018-19 average; then by 9% from 1st June to 31st September. This evolution was consistent across all tumour types: -30% and -9% for colon, -27% and -6% for lung, -29% and -14% for breast, -33% and -12% for prostate cancers, respectively. For patients aged <70 years, the decrease of colorectal and breast new cancers in April between 2018 and 2019 average and 2020 reached 41% and 39%, respectively. CONCLUSION: The SARS-Cov2 pandemic led to a substantial decrease in new cancer cases. Delays in cancer diagnoses may affect clinical outcomes in the coming years.

Fold-stratified cross-validation for unbiased and privacy-preserving federated learning.

OBJECTIVE: We introduce fold-stratified cross-validation, a validation methodology that is compatible with privacy-preserving federated learning and that prevents data leakage caused by duplicates of electronic health records (EHRs). MATERIALS AND METHODS: Fold-stratified cross-validation complements cross-validation with an initial stratification of EHRs in folds containing patients with similar characteristics, thus ensuring that duplicates of a record are jointly present either in training or in validation folds. Monte Carlo simulations are performed to investigate the properties of fold-stratified cross-validation in the case of a model data analysis using both synthetic data and MIMIC-III (Medical Information Mart for Intensive Care-III) medical records. RESULTS: In situations in which duplicated EHRs could induce overoptimistic estimations of accuracy, applying fold-stratified cross-validation prevented this bias, while not requiring full deduplication. However, a pessimistic bias might appear if the covariate used for the stratification was strongly associated with the outcome. DISCUSSION: Although fold-stratified cross-validation presents low computational overhead, to be efficient it requires the preliminary identification of a covariate that is both shared by duplicated records and weakly associated with the outcome. When available, the hash of a personal identifier or a patient's date of birth provides such a covariate. On the contrary, pseudonymization interferes with fold-stratified cross-validation, as it may break the equality of the stratifying covariate among duplicates. CONCLUSION: Fold-stratified cross-validation is an easy-to-implement methodology that prevents data leakage when a model is trained on distributed EHRs that contain duplicates, while preserving privacy.

Probing the concept of line tension down to the nanoscale.

A novel mechanical approach is developed to explore by means of atom-scale simulation the concept of line tension at a solid-liquid-vapor contact line as well as its dependence on temperature, confinement, and solid/fluid interactions. More precisely, by estimating the stresses exerted along and normal to a straight contact line formed within a partially wet pore, the line tension can be estimated while avoiding the pitfalls inherent to the geometrical scaling methodology based on hemispherical drops. The line tension for Lennard-Jones fluids is found to follow a generic behavior with temperature and chemical potential effects that are all included in a simple contact angle parameterization. Former discrepancies between theoretical modeling and molecular simulation are resolved, and the line tension concept is shown to be robust down to molecular confinements. The same qualitative behavior is observed for water, but the line tension at the wetting transition diverges or converges toward a finite value depending on the range of solid/fluid interactions at play.