Analytical and clinical evaluation of a novel real-time PCR-based detection kit for Mpox virus.

Outbreaks of emerging diseases, like Mpox in 2022, pose unprecedented challenges to global healthcare systems. Although Mpox cases globally decreased since the end of 2022, numbers are still significant in the African Region, European Region, Region of the Americas, and Western Pacific Region. Rapid and efficient detection of infected individuals by precise screening assays is crucial for successful containment. In these assays, analytical and clinical performance must be assessed to ensure high quality. However, clinical studies evaluating Mpox virus (MPXV) detection kits using patient-derived samples are scarce. This study evaluated the analytical and clinical performance of a new diagnostic MPXV real-time PCR detection kit (Sansure Monkeypox Virus Nucleic Acid Diagnostic Kit) using patient-derived samples collected in Germany during the MPXV clade IIb outbreak in 2022. Our experimental approach determined the Limit of Detection (LoD) to less than 200 cp/mL using whole blood samples and samples derived from vesicles or pustules. Furthermore, we tested potentially inhibiting substances and pathogens with homologous nucleic acid sequences or similar clinical presentation and detected no cross-reactivity or interference. Following this, the assay was compared to a CE-marked test in a clinical performance study and achieved a diagnostic sensitivity of 100.00% and diagnostic specificity of 96.97%. In summary, the investigated real-time PCR assay demonstrates high analytical performance and concurs with the competitor device with high specificity and sensitivity.

Incorporating temporal dynamics of mutations to enhance the prediction capability of antiretroviral therapy's outcome for HIV-1.

MOTIVATION: In predicting HIV therapy outcomes, a critical clinical question is whether using historical information can enhance predictive capabilities compared with current or latest available data analysis. This study analyses whether historical knowledge, which includes viral mutations detected in all genotypic tests before therapy, their temporal occurrence, and concomitant viral load measurements, can bring improvements. We introduce a method to weigh mutations, considering the previously enumerated factors and the reference mutation-drug Stanford resistance tables. We compare a model encompassing history (H) with one not using this information (NH). RESULTS: The H-model demonstrates superior discriminative ability, with a higher ROC-AUC score (76.34%) than the NH-model (74.98%). Wilcoxon test results confirm significant improvement of predictive accuracy for treatment outcomes through incorporating historical information. The increased performance of the H-model might be attributed to its consideration of latent HIV reservoirs, probably obtained when leveraging historical information. The findings emphasize the importance of temporal dynamics in acquiring mutations. However, our result also shows that prediction accuracy remains relatively high even when no historical information is available. AVAILABILITY AND IMPLEMENTATION: This analysis was conducted using the Euresist Integrated DataBase (EIDB). For further validation, we encourage reproducing this study with the latest release of the EIDB, which can be accessed upon request through the Euresist Network.

SARS-CoV-2 Test-to-Stay in Daycare.

BACKGROUND AND OBJECTIVES: Test-to-stay concepts apply serial testing of children in daycare after exposure to SARS-CoV-2 without use of quarantine. This study aims to assess the safety of a test-to-stay screening in daycare facilities. METHODS: 714 daycare facilities and approximately 50 000 children ≤6 years in Cologne, Germany participated in a SARS-CoV-2 Pool-polymerase chain reaction (PCR) screening from March 2021 to April 2022. The screening initially comprised post-exposure quarantine and was adapted to a test-to-stay approach during its course. To assess safety of the test-to-stay approach, we explored potential changes in frequencies of infections among children after the adaptation to the test-to-stay approach by applying regression discontinuity in time (RDiT) analyses. To this end, PCR-test data were linked with routinely collected data on reported infections in children and analyzed using ordinary least squares regressions. RESULTS: 219 885 Pool-PCRs and 352 305 Single-PCRs were performed. 6440 (2.93%) Pool-PCRs tested positive, and 17 208 infections in children were reported. We estimated that during a period of 30 weeks, the test-to-stay concept avoided between 7 and 20 days of quarantine per eligible daycare child. RDiT revealed a 26% reduction (Exp. Coef: 0.74, confidence interval 0.52-1.06) in infection frequency among children and indicated no significant increase attributable to the test-to-stay approach. This result was not sensitive to adjustments for 7-day incidence, season, SARS-CoV-2 variant, and socioeconomic status. CONCLUSIONS: Our analyses provide evidence that suggest safety of the test-to-stay approach compared with quarantine measures. This approach offers a promising option to avoid use of quarantine after exposure to respiratory pathogens in daycare settings.

Torque Teno Virus load is associated with CDC stage and CD4+ cell count in people living with HIV but unrelated to AIDS-defining events and Human Pegivirus load.

BACKGROUND: Torque Teno Virus (TTV) is a non-enveloped, circular single-strand DNA virus and part of the human virome. The replication of TTV was related to the immune status in patients treated with immunosuppressive drugs after organ transplantation. We hypothesize that TTV load could be an additional marker for immune function in people living with HIV (PLWH). METHODS: In this analysis serum samples of PLWH from the RESINA multicenter cohort were reanalysed for TTV. Investigated clinical and epidemiological parameters included Pegivirus (HPgV) load, age, sex, HIV load, CD4+ cell count (CDC 1, 2, 3) and CDC clinical stages (1993 CDC classification system, A, B, C) before initiation of antiretroviral treatment. Regression analysis was used to detect possible associations among parameters. RESULTS: Our analysis confirmed TTV as a strong predictor of CD4+ cell count and CDC class 3. This relationship was used to propose a first classification of TTV load in regard to clinical stage. We found no association with clinical CDC stages A, B and C. HPgV load was inversely correlated with HIV load but not TTV load. CONCLUSIONS: TTV load was associated with immunodeficiency in PLWH. Neither TTV- nor HIV load were predictive for the clinical categories of HIV infection.

Five-year single-center analysis of cytomegalovirus viremia in kidney transplant recipients and possible implication for novel prophylactic therapy approaches.

BACKGROUND: Cytomegalovirus (CMV) infections are a common complication after kidney transplantation (KTx) and negatively affecting patient outcome. Valganciclovir (VGC) prophylaxis is often limited by drug-induced side effects and dose reduction due to decline in kidney function. METHOD: In the present study, episodes of CMV viremia in the first year after KTx in a cohort of 316 recipients were analyzed retrospectively to identify risk factors linked to persistent infections. RESULTS: In the studied cohort, 18.7% of patients showed a high-risk (HR) constellation (D+/R-) for CMV infections. CMV viremia affected 22% of our cohort, with HR patients being the most affected cohort (44.1%). Within this group, most viremic events (65.3%) occurred while patients were still on prophylactic therapy, showing significantly higher viral loads and a longer duration compared to seropositive recipients. CONCLUSION: The analysis at hand revealed that detection of viremia under ongoing antiviral prophylaxis bears an increased risk for sustained viral replication and antiviral drug resistance in HR patients. We identified low estimated glomerular filtration rate (eGFR) and lower dose VGC prophylaxis post-KTx as a risk factor for breakthrough infections in HR patients in our single center cohort. These patients might benefit from a closer CMV monitoring or novel prophylactic agents as letermovir.

SARS-CoV-2 trends in Italy, Germany and Portugal and school opening during the period of Omicron variant dominance: A quasi experimental study in the EuCARE project.

OBJECTIVES: We investigated the impact of school reopening on SARS-CoV-2 transmission in Italy, Germany, and Portugal in autumn 2022 when the Omicron variant was prevalent. METHODS: A prospective international study was conducted using the case reproduction number (Rc) calculated with the time parametrization of Omicron. For Germany and Italy, staggered difference-in-differences analysis was employed to explore the causal relationship between school reopening and Rc changes, accounting for varying reopening dates. In Portugal, interrupted time series analysis was used due to simultaneous school reopenings. Multivariable models were adopted to adjust for confounders. RESULTS: In Italy and Germany, post-reopening Rc estimates were significantly lower compared to those from regions/states that had not yet reopened at the same time points, both in the student population (overall average treatment effect for the treated subpopulation [O-ATT]: -0.80 [95% CI: -0.94;-0.66] for Italy; O-ATT-0.30 [95% CI: -0.36;-0.23] for Germany) and the adult population (O-ATT: -0.04 [95% CI: -0.07;-0.01] for Italy; O-ATT: -0.07 [95% CI: -0.11;-0.03] for Germany). In Portugal, there was a significant decreasing trend in Rc following school reopenings compared to the pre-reopening period (sustained effect: -0.03 [95% CI: -0.04; -0.03] in students; -0.02 [95% CI: -0.03; -0.02] in adults). CONCLUSIONS: We found no evidence of a causal relationship between school reopenings in autumn 2022 and Omicron SARS-CoV-2 transmission.

The Role of Late Presenters in HIV-1 Transmission Clusters in Europe.

BACKGROUND: Investigating the role of late presenters (LPs) in HIV-1 transmission is important, as they can contribute to the onward spread of HIV-1 virus before diagnosis, when they are not aware of their HIV status. OBJECTIVE: To characterize individuals living with HIV-1 followed up in Europe infected with subtypes A, B, and G and to compare transmission clusters (TC) in LP vs. non-late presenter (NLP) populations. METHODS: Information from a convenience sample of 2679 individuals living with HIV-1 was collected from the EuResist Integrated Database between 2008 and 2019. Maximum likelihood (ML) phylogenies were constructed using FastTree. Transmission clusters were identified using Cluster Picker. Statistical analyses were performed using R. RESULTS: 2437 (91.0%) sequences were from subtype B, 168 (6.3%) from subtype A, and 74 (2.8%) from subtype G. The median age was 39 y/o (IQR: 31.0-47.0) and 85.2% of individuals were males. The main transmission route was via homosexual (MSM) contact (60.1%) and 85.0% originated from Western Europe. In total, 54.7% of individuals were classified as LPs and 41.7% of individuals were inside TCs. In subtype A, individuals in TCs were more frequently males and natives with a recent infection. For subtype B, individuals in TCs were more frequently individuals with MSM transmission route and with a recent infection. For subtype G, individuals in TCs were those with a recent infection. When analyzing cluster size, we found that LPs more frequently belonged to small clusters (<8 individuals), particularly dual clusters (2 individuals). CONCLUSION: LP individuals are more present either outside or in small clusters, indicating a limited role of late presentation to HIV-1 transmission.

Torque teno virus-DNA load as individual cytomegalovirus risk assessment parameter upon allogeneic hematopoietic stem cell transplantation.

BACKGROUND: Immune recovery following allogeneic hematopoietic stem cell transplantation (allo-HSCT) decisively influences the occurrence of opportunistic infections, one of the leading causes of death among this group of patients. Yet, today, there are no laboratory parameters mirroring immune function sufficiently. Torque teno virus (TTV) has already proven itself as a functional immune marker in other settings. AIMS: In this analysis, we investigated whether monitoring of TTV-DNA load in whole blood is able to provide additional information on the capacity of the immune system to control cytomegalovirus (CMV) replication in allo-HSCT recipients. METHODS: Whole blood samples from 59 patients were collected upon allo-HSCT (between Day -7 and +10), on Day +14, +21, +28, +56, +90, and +365 post-transplant. TTV-DNA loads and other relevant clinical information were correlated with the risk of CMV infections or reactivations, defined by evidence of viral replication in blood. RESULTS: CMV serostatus of the recipient and a TTV load below 1000 copies/mL upon allo-HSCT were significantly associated with an increased incidence of CMV infection or reactivation. CONCLUSIONS: Quantification of TTV load in the early phase of allo-HSCT procedure could provide additional information in order to identify patients at risk for CMV infection or reactivation.

Acute orchitis deciphered: Coxsackievirus B strains are the main etiology and their presence in semen is associated with acute inflammation and risk of persistent oligozoospermia.

Although various viruses are considered to be the clinical cause for acute orchitis, it is completely unclear to what extent and which viruses are etiologically involved in acute orchitis and what the clinic and course of these patients are like. Therefore, a prospective study was set up to decipher acute isolated orchitis. Between July 2007 and February 2023, a total of 26 patients with isolated orchitis were recruited and compared with 530 patients with acute epididymitis. We were able to show for isolated orchitis, that (1) orchitis is usually of viral origin (20/26, 77%) and enteroviruses with coxsackievirus B strains (16/26, 62%) are predominant, (2) virus isolates could be received from semen indicating the presence of replication-competent virus particles, (3) a polymerase chain reaction (PCR) for enteroviruses should be conducted using semen provided at the onset of disease, because the virus is not detectable in serum/urine, (4) there is a circannual occurrence with the maximum in summer, (5) orchitis is associated with a characteristic inflammatory cytokine panel in the semen and systemic inflammation, (6) orchitis is usually rapidly self-limiting, and (7) about 30% of patients (6/20) suffer ongoing oligozoospermia. These seven emerging aspects are likely to fundamentally change thinking and clinical practice regarding acute isolated orchitis.

Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV.

OBJECTIVE: Clinical data's confidential nature often limits the development of machine learning models in healthcare. Generative adversarial networks (GANs) can synthesise realistic datasets, but suffer from mode collapse, resulting in low diversity and bias towards majority demographics and common clinical practices. This work proposes an extension to the classic GAN framework that includes a variational autoencoder (VAE) and an external memory mechanism to overcome these limitations and generate synthetic data accurately describing imbalanced class distributions commonly found in clinical variables. METHODS: The proposed method generated a synthetic dataset related to antiretroviral therapy for human immunodeficiency virus (ART for HIV). We evaluated it based on five metrics: (1) accurately representing imbalanced class distribution; (2) the realism of the individual variables; (3) the realism among variables; (4) patient disclosure risk; and (5) the utility of the generated dataset for developing downstream machine learning models. RESULTS: The proposed method overcomes the issue of mode collapse and generates a synthetic dataset that accurately describes imbalanced class distributions commonly found in clinical variables. The generated data has a patient disclosure risk of 0.095%, lower than the 9% threshold stated by Health Canada and the European Medicines Agency, making it suitable for distribution to the research community with high security. The generated data also has high utility, indicating the potential of the proposed method to enable the development of downstream machine learning algorithms for healthcare applications using synthetic data. CONCLUSION: Our proposed extension to the classic GAN framework, which includes a VAE and an external memory mechanism, represents a promising approach towards generating synthetic data that accurately describe imbalanced class distributions commonly found in clinical variables. This method overcomes the limitations of GANs and creates more realistic datasets with higher patient cohort diversity, facilitating the development of downstream machine learning algorithms for healthcare applications.

Cohort Profile: A European Multidisciplinary Network for the Fight against HIV Drug Resistance (EuResist Network).

The EuResist cohort was established in 2006 with the purpose of developing a clinical decision-support tool predicting the most effective antiretroviral therapy (ART) for persons living with HIV (PLWH), based on their clinical and virological data. Further to continuous extensive data collection from several European countries, the EuResist cohort later widened its activity to the more general area of antiretroviral treatment resistance with a focus on virus evolution. The EuResist cohort has retrospectively enrolled PLWH, both treatment-naïve and treatment-experienced, under clinical follow-up from 1998, in nine national cohorts across Europe and beyond, and this article is an overview of its achievement. A clinically oriented treatment-response prediction system was released and made available online in 2008. Clinical and virological data have been collected from more than one hundred thousand PLWH, allowing for a number of studies on the response to treatment, selection and spread of resistance-associated mutations and the circulation of viral subtypes. Drawing from its interdisciplinary vocation, EuResist will continue to investigate clinical response to antiretroviral treatment against HIV and monitor the development and circulation of HIV drug resistance in clinical settings, along with the development of novel drugs and the introduction of new treatment strategies. The support of artificial intelligence in these activities is essential.

CMV-IgG pre-allogeneic hematopoietic stem cell transplantation and the risk for CMV reactivation and mortality.

Cytomegalovirus (CMV) represents one of the most common infectious complications after allogeneic hematopoietic stem cell transplantation (allo-HSCT). Currently, a common diagnostic test used to stratify the risk for CMV infection in allo-HSCT recipients is the qualitative CMV serology of donor and recipient. A positive serostatus of the recipient is the most important risk factor for CMV reactivation and associated with reduced overall survival post-transplantation (TX). Direct and indirect effects of CMV are involved in the poorer survival outcome. The present study investigated if the quantitative interpretation of anti-CMV IgG before allo-HSCT might serve as a novel parameter for the identification of patients at risk for CMV reactivation and worse outcome post-TX. For this purpose, a cohort of 440 allo-HSCT recipients over a period of 10 years was retrospectively analyzed. Our findings indicated that patients with high CMV IgG pre-allo-HSCT had a higher risk to develop CMV reactivation, including clinically relevant infections, and a worse prognosis 36 months post-allo-HSCT as compared to recipients with low CMV IgG values. In the letermovir (LMV) era, this group of patients might benefit from a closer CMV monitoring, and hence, earlier intervention if needed, especially after discontinuation of prophylaxis.

Anti-angiogenic agents for NSCLC following first-line immunotherapy: Rationale, recent updates, and future perspectives.

The implementation of immune checkpoint inhibitors (ICIs), with or without chemotherapy, as first-line treatment for patients who do not have actionable mutations has proved to be a major paradigm shift in the management of advanced non-small cell lung cancer (NSCLC). However, the transition of ICIs, such as pembrolizumab and nivolumab, to a first-line setting has left an unmet need for effective second-line treatment options, which is an area of intense research. In 2020, we reviewed the biological and mechanistic rationale for anti-angiogenic agents in combination with, or following, immunotherapy with the aim of eliciting a so called 'angio-immunogenic' switch in the tumor microenvironment. Here, we review the latest clinical evidence of the benefits of incorporating anti-angiogenic agents into treatment regimens. While there is a paucity of prospective data, several recent observational studies indicate that the marketed anti-angiogenic drugs, nintedanib or ramucirumab, are effective in combination with docetaxel following immuno-chemotherapy. Addition of anti-angiogenics, like bevacizumab, have also demonstrated clinical benefit when combined with first-line immuno-chemotherapy regimens. Ongoing clinical trials are assessing these agents in combination with ICIs, with encouraging early results (e.g., ramucirumab plus pembrolizumab in LUNG-MAP S1800A). Also, several emerging anti-angiogenic agents combined with ICIs are currently being assessed in phase III trials following immunotherapy, including lenvatinib (LEAP-008), and sitravatinib (SAPPHIRE) It is hoped that these trials will help expand second-line treatment options in patients with NSCLC. Areas of focus in the future will include further molecular dissection of the mechanisms of resistance to immunotherapy and the various response-progression profiles to immunotherapy observed in the clinic and the monitoring of the dynamics of immunomodulation over the course of treatment. Improved understanding of these phenomena may help identify clinical biomarkers and inform the optimal use of anti-angiogenics in the treatment of individual patients.

In-depth virological and immunological characterization of HIV-1 cure after CCR5Δ32/Δ32 allogeneic hematopoietic stem cell transplantation.

Despite scientific evidence originating from two patients published to date that CCR5Δ32/Δ32 hematopoietic stem cell transplantation (HSCT) can cure human immunodeficiency virus type 1 (HIV-1), the knowledge of immunological and virological correlates of cure is limited. Here we characterize a case of long-term HIV-1 remission of a 53-year-old male who was carefully monitored for more than 9 years after allogeneic CCR5Δ32/Δ32 HSCT performed for acute myeloid leukemia. Despite sporadic traces of HIV-1 DNA detected by droplet digital PCR and in situ hybridization assays in peripheral T cell subsets and tissue-derived samples, repeated ex vivo quantitative and in vivo outgrowth assays in humanized mice did not reveal replication-competent virus. Low levels of immune activation and waning HIV-1-specific humoral and cellular immune responses indicated a lack of ongoing antigen production. Four years after analytical treatment interruption, the absence of a viral rebound and the lack of immunological correlates of HIV-1 antigen persistence are strong evidence for HIV-1 cure after CCR5Δ32/Δ32 HSCT.

European Cohorts of patients and schools to Advance Response to Epidemics (EuCARE): a cluster randomised interventional and observational study protocol to investigate the relationship between schools and SARS-CoV-2 infection.

BACKGROUND: Contradictory results were reported on the role of school closure/reopening on the overall SARS-CoV-2 transmission rate, as well as on which kind and level of mitigation measures implemented in schools may be effective in limiting its diffusion. Some recent studies were reassuring, showing that opening did not increase the community spread, although teachers and families are worried about the high class density. On the other hand, distance learning was associated with a negative impact on learning, sociability and psychological health, especially in vulnerable children. As it becomes clear that the SARS-CoV-2 pandemic will last for a long time, there is a high need for studies and solutions to support safe schools opening based on scientific evidence of harms and benefits. The Lolli-Methode (LM) is a strategy for epidemiological surveillance and early intervention aiming at SARS-CoV-2 outbreaks' reduction in schools, relying on polymerase chain reaction analysis of saliva samples. METHODS: In this cluster randomised trial protocol, we aim to determine whether the LM is useful to support schools opening and to reduce clusters and attack rates in schools, compared with the standard of care (SoC) surveillance by public health departments. This multicenter study will enrol 440 classes (around 8800 students, teachers and other personnel) from two countries, cluster randomised to LM or SoC. The samples from the pools will be collected and tested using PCR-based techniques. Test results will be combined with questionnaires filled in by children, parents, schoolteachers, and principals, concerning ongoing mitigation measures, their perceived psychological impact and other health and socio-economic information. An ancillary observational study will be carried out to study the prevalence of SARS-CoV-2 in schools, frequencies and size of clusters and attack rates, to compare the effectiveness of the different preventive measures adopted and to evaluate psychological issues in students and teachers in relation to the pandemic's containment measures. DISCUSSION: By the end of this study, we will have defined and characterised the applicability of the LM for SARS-CoV-2 surveillance, as well as the impact of pandemic preventive measures on children and teachers. Trial registration International Standard Randomised Controlled Trial Number: NCT05396040, 27.05.2022.

Implementing the Lolli-Method and pooled RT-qPCR testing for SARS-CoV-2 surveillance in schools: a pilot project.

PURPOSE: School closures have been used as part of lockdown strategies to contain the spread of SARS-CoV-2, adversely affecting children's health and education. To ensure the accessibility of educational institutions without exposing society to the risk of increased transmissions, it is essential to establish SARS-CoV-2 testing strategies that are child-friendly, scalable and implementable in a daily school routine. Self-sampling using non-invasive saliva swabs combined with pooled RT-qPCR testing (Lolli-Method) has been proven to be a sensitive method for the detection of SARS-CoV-2. METHODS: We conducted a pilot project in Cologne, Germany, designed to determine the feasibility of a large-scale rollout of the Lolli-Method for testing without any additional on-site medical staff in schools. Over a period of three weeks, students from 22 schools were sampled using the Lolli-Method. At the end of the project, teachers were asked to evaluate the overall acceptance of the project. RESULTS: We analyzed a total of 757 pooled RT-qPCRs obtained from 8,287 individual swabs and detected 7 SARS-CoV-2 infected individuals. The Lolli-Method was shown to be a feasible and accepted testing strategy whose application is only slightly disruptive to the daily school routine. CONCLUSION: Our observations suggest that the Lolli-Method in combination with pooled RT-qPCR can be implemented for SARS-CoV-2 surveillance in daily school routine, applicable on a large scale.

Analysis of mutational history of multidrug-resistant genotypes with a mutagenetic tree model.

Human immunodeficiency virus (HIV) can develop resistance to all antiretroviral drugs. Multidrug resistance, however, is a rare event in modern HIV treatment, but can be life-threatening, particular in patients with very long therapy histories and in areas with limited access to novel drugs. To understand the evolution of multidrug resistance, we analyzed the EuResist database to uncover the accumulation of mutations over time. We hypothesize that the accumulation of resistance mutations is not acquired simultaneously and randomly across viral genotypes but rather tends to follow a predetermined order. The knowledge of this order might help to elucidate potential mechanisms of multidrug resistance. Our evolutionary model shows an almost monotonic increase of resistance with each acquired mutation, including less well-known nucleoside reverse transcriptase (RT) inhibitor-related mutations like K223Q, L228H, and Q242H. Mutations within the integrase (IN) (T97A, E138A/K G140S, Q148H, N155H) indicate high probability of multidrug resistance. Hence, these IN mutations also tend to be observed together with mutations in the protease (PR) and RT. We followed up with an analysis of the mutation-specific error rates of our model given the data. We identified several mutations with unusual rates (PR: M41L, L33F, IN: G140S). This could imply the existence of previously unknown virus variants in the viral quasispecies. In conclusion, our bioinformatics model supports the analysis and understanding of multidrug resistance.

The Health Gym: synthetic health-related datasets for the development of reinforcement learning algorithms.

In recent years, the machine learning research community has benefited tremendously from the availability of openly accessible benchmark datasets. Clinical data are usually not openly available due to their confidential nature. This has hampered the development of reproducible and generalisable machine learning applications in health care. Here we introduce the Health Gym - a growing collection of highly realistic synthetic medical datasets that can be freely accessed to prototype, evaluate, and compare machine learning algorithms, with a specific focus on reinforcement learning. The three synthetic datasets described in this paper present patient cohorts with acute hypotension and sepsis in the intensive care unit, and people with human immunodeficiency virus (HIV) receiving antiretroviral therapy. The datasets were created using a novel generative adversarial network (GAN). The distributions of variables, and correlations between variables and trends in variables over time in the synthetic datasets mirror those in the real datasets. Furthermore, the risk of sensitive information disclosure associated with the public distribution of the synthetic datasets is estimated to be very low.