Quantifying the environmental limits to fire spread in grassy ecosystems.

Modeling fire spread as an infection process is intuitive: An ignition lights a patch of fuel, which infects its neighbor, and so on. Infection models produce nonlinear thresholds, whereby fire spreads only when fuel connectivity and infection probability are sufficiently high. These thresholds are fundamental both to managing fire and to theoretical models of fire spread, whereas applied fire models more often apply quasi-empirical approaches. Here, we resolve this tension by quantifying thresholds in fire spread locally, using field data from individual fires (n = 1,131) in grassy ecosystems across a precipitation gradient (496 to 1,442 mm mean annual precipitation) and evaluating how these scaled regionally (across 533 sites) and across time (1989 to 2012 and 2016 to 2018) using data from Kruger National Park in South Africa. An infection model captured observed patterns in individual fire spread better than competing models. The proportion of the landscape that burned was well described by measurements of grass biomass, fuel moisture, and vapor pressure deficit. Regionally, averaging across variability resulted in quasi-linear patterns. Altogether, results suggest that models aiming to capture fire responses to global change should incorporate nonlinear fire spread thresholds but that linear approximations may sufficiently capture medium-term trends under a stationary climate.

IL-13 and IL-13-induced periostin levels are specifically decreased in patients following endoscopic sinus surgery for chronic rhinosinusitis.

BACKGROUND: Type 2 (T2) inflammation plays a pathogenic role in chronic rhinosinusitis (CRS). The effects of endoscopic sinus surgery (ESS) on T2 inflammation are unknown. OBJECTIVE: The aim of this study was to compare T2 inflammatory biomarkers from middle meatal (MM) mucus for distinguishing patients with CRS from CRS-free patients, identifying major phenotypes (CRS without nasal polyps [CRSsNP] and CRS with nasal polyps [CRSwNP]), assessing endotypic change, and establishing cross-sectional and longitudinal outcomes in patients undergoing ESS. METHODS: MM mucus samples were collected from patients with CRSsNP and patients with CRSwNP before and 6 to 12 months after ESS and compared with samples from CRS-free control patients. T2 biomarkers were evaluated both continuously and using threshold-based definitions of T2 endotype to identify relationships with patient-reported (based on the 22-Item Sinonasal Outcomes Test and Chronic Rhinosinusitis Patient-Reported Outcomes Measure) and clinician-reported (radiographic and endoscopic) severity. Linear mixed models were developed to analyze clinical variables associated with T2 biomarker levels. RESULTS: A total of 154 patients with CRS (89 with CRSsNP and 65 with CRSwNP) were enrolled, with a mean interval of 9 months between ESS and follow-up. An analysis of pre-ESS MM mucus samples revealed elevated levels of T2 mediators in patients with CRSwNP versus in patients with CRSsNP and CRS-free controls. Temporally stable correlations between levels of IL-13 and IL-5, levels of periostin and complement 5a, and levels of eosinophil cationic protein (ECP) and eotaxin-3 were observed. On this basis and on the basis of pathologic significance, levels of IL-13, periostin and ECP were further analyzed. After ESS, levels of IL-13 and periostin decreased significantly, whereas ECP levels remained unchanged. Across pre- and post-ESS evaluation, the T2 endotype was associated with radiographic severity but did not predict outcomes. CRSwNP status and African American race were associated with higher levels of IL-13 and periostin, whereas ECP level was higher in patients undergoing extensive surgery. CONCLUSION: ESS decreased levels of IL-13 and periostin in the middle meatus. T2 inflammation after ESS was correlated with patient- and clinician-reported severity across phenotypes. Pre-ESS T2 inflammation did not predict post-ESS outcomes.

The inter-laboratory validation study of EpiSensA for predicting skin sensitization potential.

The Epidermal Sensitization Assay (EpiSensA) is a reconstructed human epidermis (RhE)-based gene expression assay for predicting the skin sensitization potential of chemicals. Since the RhE model is covered by a stratified stratum corneum, various kinds of test chemicals, including lipophilic ones and pre-/pro-haptens, can be tested with a route of exposure akin to an in vivo assay and human exposure. This article presents the results of a formally managed validation study of the EpiSensA that was carried out by three participating laboratories. The purpose of this validation study was to assess transferability of the EpiSensA to new laboratories along with its within- (WLR) and between-laboratory reproducibility (BLR). The validation study was organized into two independent stages. As demonstrated during the first stage, where three sensitizers and one non-sensitizer were correctly predicted by all participating laboratories, the EpiSensA was successfully transferred to all three participating laboratories. For Phase I of the second stage, each participating laboratory performed three experiments with an identical set of 15 coded test chemicals resulting in WLR of 93.3%, 93.3%, and 86.7%, respectively. Furthermore, when the results from the 15 test chemicals were combined with those of the additional 12 chemicals tested in Phase II of the second stage, the BLR for 27 test chemicals was 88.9%. Moreover, the predictive capacity among the three laboratories showed 92.6% sensitivity, 63.0% specificity, 82.7% accuracy, and 77.8% balanced accuracy based on murine local lymph node assay (LLNA) results. Overall, this validation study concluded that EpiSensA is easily transferable and sufficiently robust for assessing the skin sensitization potential of chemicals.

microRNA neural networks improve diagnosis of acute coronary syndrome (ACS).

BACKGROUND: Cardiac troponins are the preferred biomarkers of acute myocardial infarction. Despite superior sensitivity, serial testing of Troponins to identify patients suffering acute coronary syndromes is still required in many cases to overcome limited specificity. Moreover, unstable angina pectoris relies on reported symptoms in the troponin-negative group. In this study, we investigated genome-wide miRNA levels in a prospective cohort of patients with clinically suspected ACS and determined their diagnostic value by applying an in silico neural network. METHODS: PAXgene blood and serum samples were drawn and hsTnT was measured in patients at initial presentation to our Chest-Pain Unit. After clinical and diagnostic workup, patients were adjudicated by senior cardiologists in duty to their final diagnosis: STEMI, NSTEMI, unstable angina pectoris and non-ACS patients. ACS patients and a cohort of healthy controls underwent deep transcriptome sequencing. Machine learning was implemented to construct diagnostic miRNA classifiers. RESULTS: We developed a neural network model which incorporates 34 validated ACS miRNAs, showing excellent classification results. By further developing additional machine learning models and selecting the best miRNAs, we achieved an accuracy of 0.96 (95% CI 0.96-0.97), sensitivity of 0.95, specificity of 0.96 and AUC of 0.99. The one-point hsTnT value reached an accuracy of 0.89, sensitivity of 0.82, specificity of 0.96, and AUC of 0.96. CONCLUSIONS: Here we show the concept of neural network based biomarkers for ACS. This approach also opens the possibility to include multi-modal data points to further increase precision and perform classification of other ACS differential diagnoses.

Physiological responses to cisplatin using a mouse hypersensitivity model.

Background: The physiological mechanisms underlying the development of respiratory hypersensitivity to cisplatin (CDDP) are not well-understood. It has been suggested that these reactions are likely the result of type I hypersensitivity, but other explanations are plausible and the potential for CDDP to induce type I hypersensitivity responses has not been directly evaluated in an animal model. Objectives and Methods: To investigate CDDP hypersensitivity, mice were topically sensitized through application of CDDP before being challenged by oropharyngeal aspiration (OPA) with CDDP. Before and immediately after OPA challenge, pulmonary responses were assessed using whole body plethysmography (WBP). Results: CDDP did not induce an immediate response or alter the respiratory rate in sensitized mice. Two days later, baseline enhanced pause (Penh) values were significantly elevated (p < 0.05) in mice challenged with CDDP. When challenged with methacholine (Mch) aerosol, Penh values were significantly elevated (p < 0.05) in sensitized mice and respiratory rate was reduced (p < 0.05). Lymph node cell counts and immunoglobulin E levels also indicated successful sensitization to CDDP. Irrespective of the sensitization state of the mice, the number of neutrophils increased significantly in bronchoalveolar lavage fluid (BALF) following CDDP challenge. BALF from sensitized mice also contained 2.46 (±0.8) × 104 eosinophils compared to less than 0.48 (±0.2) × 104 cells in non-sensitized mice (p < 0.05). Conclusions: The results from this study indicate that dermal exposure to CDDP induces immunological changes consistent with type I hypersensitivity and that a single respiratory challenge is enough to trigger pulmonary responses in dermally sensitized mice. These data provide previously unknown insights into the mechanisms of CDDP hypersensitivity.

Skin sensitization testing needs and data uses by US regulatory and research agencies.

United States regulatory and research agencies may rely upon skin sensitization test data to assess the sensitization hazards associated with dermal exposure to chemicals and products. These data are evaluated to ensure that such substances will not cause unreasonable adverse effects to human health when used appropriately. The US Consumer Product Safety Commission, the US Environmental Protection Agency, the US Food and Drug Administration, the Occupational Safety and Health Administration, the National Institute for Occupational Safety and Health, and the US Department of Defense are member agencies of the Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM). ICCVAM seeks to identify opportunities for the use of non-animal replacements to satisfy these testing needs and requirements. This review identifies the standards, test guidelines, or guidance documents that are applicable to satisfy each of these agency's needs; the current use of animal testing and flexibility for using alternative methodologies; information needed from alternative tests to fulfill the needs for skin sensitization data; and whether data from non-animal alternative approaches are accepted by these US federal agencies.

Cross-reactivity between halogenated platinum salts in an immediate-type respiratory hypersensitivity model.

Halogenated platinum salts can trigger the development of occupational asthma. Until recently, laboratory research into the development and manifestation of platinum hypersensitivity responses were hindered by the lack of an animal model suitable for assessing the functional consequences of allergic sensitization. We employed a newly developed mouse model to assess the potential allergenicity of ammonium tetrachloroplatinate (ATCP), compare the relative potency of ATCP and another platinum salt, ammonium hexachloroplatinate (AHCP) and assess potential cross-reactivity. Mice were topically sensitized with ATCP before being challenged by intratracheal aspiration (IA) with ATCP. Ventilatory responses were assessed using whole-body plethysmography (WBP). An immediate response (IR) was observed in ATCP-sensitized and challenged mice. Two days later, responsiveness to the nonspecific stimuli methacholine (Mch) was detected in ATCP-sensitized mice using WBP. Bronchoalveolar lavage fluid collected from sensitized mice contained an average of 3.3% eosinophils compared to less than 0.5% in non-sensitized mice (p<.05). Serum harvested from sensitized mice also contained increased total serum immunoglobulin E (p<.05). These data are the first to demonstrate that topical exposure to ATCP is sufficient to develop immediate type hypersensitivity and that a single intra-airway challenge is capable of triggering pulmonary responses. To investigate potential cross-reactivity, mice were sensitized to AHCP and, challenged by a single IA with a second platinum compound, ATCP. Compared to non-sensitized mice challenged with ATCP, these mice exhibited an IR, responsiveness to Mch, and eosinophilic infiltration in the lungs similar to that achieved with AHCP challenge, thus demonstrating cross-reactivity.

Prediction of skin sensitization potency using machine learning approaches.

The replacement of animal use in testing for regulatory classification of skin sensitizers is a priority for US federal agencies that use data from such testing. Machine learning models that classify substances as sensitizers or non-sensitizers without using animal data have been developed and evaluated. Because some regulatory agencies require that sensitizers be further classified into potency categories, we developed statistical models to predict skin sensitization potency for murine local lymph node assay (LLNA) and human outcomes. Input variables for our models included six physicochemical properties and data from three non-animal test methods: direct peptide reactivity assay; human cell line activation test; and KeratinoSens™ assay. Models were built to predict three potency categories using four machine learning approaches and were validated using external test sets and leave-one-out cross-validation. A one-tiered strategy modeled all three categories of response together while a two-tiered strategy modeled sensitizer/non-sensitizer responses and then classified the sensitizers as strong or weak sensitizers. The two-tiered model using the support vector machine with all assay and physicochemical data inputs provided the best performance, yielding accuracy of 88% for prediction of LLNA outcomes (120 substances) and 81% for prediction of human test outcomes (87 substances). The best one-tiered model predicted LLNA outcomes with 78% accuracy and human outcomes with 75% accuracy. By comparison, the LLNA predicts human potency categories with 69% accuracy (60 of 87 substances correctly categorized). These results suggest that computational models using non-animal methods may provide valuable information for assessing skin sensitization potency. Copyright © 2017 John Wiley & Sons, Ltd.

Multivariate models for prediction of human skin sensitization hazard.

One of the Interagency Coordinating Committee on the Validation of Alternative Method's (ICCVAM) top priorities is the development and evaluation of non-animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays - the direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens™ assay - six physicochemical properties and an in silico read-across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches, logistic regression and support vector machine, to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three logistic regression and three support vector machine) with the highest accuracy (92%) used: (1) DPRA, h-CLAT and read-across; (2) DPRA, h-CLAT, read-across and KeratinoSens; or (3) DPRA, h-CLAT, read-across, KeratinoSens and log P. The models performed better at predicting human skin sensitization hazard than the murine local lymph node assay (accuracy 88%), any of the alternative methods alone (accuracy 63-79%) or test batteries combining data from the individual methods (accuracy 75%). These results suggest that computational methods are promising tools to identify effectively the potential human skin sensitizers without animal testing. Published 2016. This article has been contributed to by US Government employees and their work is in the public domain in the USA.

Habitat use of migratory bats killed during autumn at wind turbines.

The killing of large numbers of migratory bats at wind turbines is a pressing conservation problem. Even though avoidance and mitigation measures could benefit from a better knowledge of the species' migratory habits, we lack basic information about what habitats and corridors bats use during migration. We studied the isotopic niche dimensions of three bat species that are frequently killed at wind turbines in Germany: non-migratory Pipistrellus pipistrellus, mid-distance migratory Nyctalus noctula, and long- distance migratory Pipistrellus nathusii. We measured stable carbon and nitrogen isotope ratios (δ¹³C, δ¹5N) in five tissues that differed in isotopic retention time (fur, wing membrane tissue, muscle, liver, blood) to shed light on the species-specific habitat use during the autumn migration period using standard ellipse areas (SEAc). Further, we used stable isotope ratios of non-exchangeable hydrogen (δ²H(K)) in fur keratin to assess the breeding origin of bats. We inferred from isotopic composition (δ¹³C, δ¹5N) of fur keratin that isotopic niche dimensions of P. nathusii was distinct from that of N. noctula and P. pipistrellus, probably because P. nathusii was using more aquatic habitats than the other two species. Isoscape origin models supported that traveled distances before dying at wind turbines was largest for P. nathusii, intermediate for N. noctula, and shortest for P. pipistrellus. Isotopic niche dimensions calculated for each sample type separately reflected the species' migratory behavior. Pipistrellus pipistrellus and N. noctula showed similar isotopic niche breadth across all tissue types, whereas SEAc values of P. nathusii increased in tissues with slow turnaround time. Isotopic data suggested that P. nathusii consistently used aquatic habitats throughout the autumn period, whereas N. noctula showed a stronger association with terrestrial habitats during autumn compared to the pre-migration period.

Integrated decision strategies for skin sensitization hazard.

One of the top priorities of the Interagency Coordinating Committee for the Validation of Alternative Methods (ICCVAM) is the identification and evaluation of non-animal alternatives for skin sensitization testing. Although skin sensitization is a complex process, the key biological events of the process have been well characterized in an adverse outcome pathway (AOP) proposed by the Organisation for Economic Co-operation and Development (OECD). Accordingly, ICCVAM is working to develop integrated decision strategies based on the AOP using in vitro, in chemico and in silico information. Data were compiled for 120 substances tested in the murine local lymph node assay (LLNA), direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens assay. Data for six physicochemical properties, which may affect skin penetration, were also collected, and skin sensitization read-across predictions were performed using OECD QSAR Toolbox. All data were combined into a variety of potential integrated decision strategies to predict LLNA outcomes using a training set of 94 substances and an external test set of 26 substances. Fifty-four models were built using multiple combinations of machine learning approaches and predictor variables. The seven models with the highest accuracy (89-96% for the test set and 96-99% for the training set) for predicting LLNA outcomes used a support vector machine (SVM) approach with different combinations of predictor variables. The performance statistics of the SVM models were higher than any of the non-animal tests alone and higher than simple test battery approaches using these methods. These data suggest that computational approaches are promising tools to effectively integrate data sources to identify potential skin sensitizers without animal testing. Published 2016. This article has been contributed to by US Government employees and their work is in the public domain in the USA.

A chemical biology approach demonstrates G protein ßγ subunits are sufficient to mediate directional neutrophil chemotaxis.

Our laboratory has identified a number of small molecules that bind to G protein ßγ subunits (Gßγ) by competing for peptide binding to the Gßγ "hot spot." M119/Gallein were identified as inhibitors of Gßγ subunit signaling. Here we examine the activity of another molecule identified in this screen, 12155, which we show that in contrast to M119/Gallein had no effect on Gßγ-mediated phospholipase C or phosphoinositide 3-kinase (PI3K) γ activation in vitro. Also in direct contrast to M119/Gallein, 12155 caused receptor-independent Ca(2+) release, and activated other downstream targets of Gßγ including extracellular signal regulated kinase (ERK), protein kinase B (Akt) in HL60 cells differentiated to neutrophils. We show that 12155 releases Gßγ in vitro from Gαi1ß1γ2 heterotrimers by causing its dissociation from GαGDP without inducing nucleotide exchange in the Gα subunit. We used this novel probe to examine the hypothesis that Gßγ release is sufficient to direct chemotaxis of neutrophils in the absence of receptor or G protein α subunit activation. 12155 directed chemotaxis of HL60 cells and primary neutrophils in a transwell migration assay with responses similar to those seen for the natural chemotactic peptide n-formyl-Met-Leu-Phe. These data indicate that release of free Gßγ is sufficient to drive directional chemotaxis in a G protein-coupled receptor signaling-independent manner.

Genome-wide association study of virologic response with efavirenz-containing or abacavir-containing regimens in AIDS clinical trials group protocols.

BACKGROUND: Efavirenz and abacavir are components of recommended first-line regimens for HIV-1 infection. We used genome-wide genotyping and clinical data to explore genetic associations with virologic failure among patients randomized to efavirenz-containing or abacavir-containing regimens in AIDS Clinical Trials Group (ACTG) protocols. PARTICIPANTS AND METHODS: Virologic response and genome-wide genotype data were available from treatment-naive patients randomized to efavirenz-containing (n=1596) or abacavir-containing (n = 786) regimens in ACTG protocols 384, A5142, A5095, and A5202. RESULTS: Meta-analysis of association results across race/ethnic groups showed no genome-wide significant associations (P < 5 × 10) with virologic response for either efavirenz or abacavir. Our sample size provided 80% power to detect a genotype relative risk of 1.8 for efavirenz and 2.4 for abacavir. Analyses focused on CYP2B genotypes that define the lowest plasma efavirenz exposure stratum did not show associations nor did analysis limited to gene sets predicted to be relevant to efavirenz and abacavir disposition. CONCLUSION: No single polymorphism is associated strongly with virologic failure with efavirenz-containing or abacavir-containing regimens. Analyses to better consider context, and that minimize confounding by nongenetic factors, may show associations not apparent here.

A proposed role for efflux transporters in the pathogenesis of hydrocephalus.

Hydrocephalus is a common brain disorder that is treated only with surgery. The basis for surgical treatment rests on the circulation theory. However, clinical and experimental data to substantiate circulation theory have remained inconclusive. In brain tissue and in the ventricles, we see that osmotic gradients drive water diffusion in water-permeable tissue. As the osmolarity of ventricular CSF increases within the cerebral ventricles, water movement into the ventricles increases and causes hydrocephalus. Macromolecular clearance from the ventricles is a mechanism to establish the normal CSF osmolarity, and therefore ventricular volume. Efflux transporters, (p-glycoprotein), are located along the blood brain barrier and play an important role in the clearance of macromolecules (endobiotics and xenobiotics) from the brain to the blood. There is clinical and experimental data to show that macromolecules are cleared out of the brain in normal and hydrocephalic brains. This article summarizes the existing evidence to support the role of efflux transporters in the pathogenesis of hydrocephalus. The location of p-gp along the pathways of macromolecular clearance and the broad substrate specificity of this abundant transporter to a variety of different macromolecules are reviewed. Involvement of p-gp in the transport of amyloid beta in Alzheimer disease and its relation to normal pressure hydrocephalus is reviewed. Finally, individual variability of p-gp expression might explain the variability in the development of hydrocephalus following intraventricular hemorrhage.

Do P-glycoprotein Medications Alter the Risk of Ventriculoperitoneal Shunt in Adults with Hydrocephalus?

Hydrocephalus is a disorder caused by excess fluid accumulation in the brain and results in brain damage with consequent cognitive and physical problems. This condition has no cure; the only treatment is brain surgery. Experimental data indicate that P-glycoprotein (P-gp) plays a crucial role in the pathogenesis of hydrocephalus due to its function in clearing macromolecules from the brain. Numerous medications frequently used are classified as P-gp inducers or inhibitors, and comprehending their effects may aid in attaining improved patient outcomes. Therefore, in this single-center retrospective study, we examined the risk of the need for ventriculoperitoneal shunt placement over 10 years among 4588 adult patients with hydrocephalus not exposed to any P-gp inhibitors/inducers or exclusively exposed to either P-gp inhibitors or inducers. Our analysis shows that patients exposed to P-gp inhibitors had a 3.2 times higher risk of requiring ventriculoperitoneal shunt surgery (P < .0001). In contrast, the relative risk was not significantly affected (P = .07) among those exposed to P-gp inducers. Our findings indicate the need for caution when prescribing P-gp inhibitors to patients with hydrocephalus. Additional studies using larger cohorts are required to confirm whether P-gp inducers in patients with hydrocephalus can mitigate the risk of ventriculoperitoneal shunt.

Improving sudden cardiac death risk stratification in hypertrophic cardiomyopathy using established clinical variables and genetic information.

BACKGROUND AND AIMS: The cardiac societies of Europe and the United States have established different risk models for preventing sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM). The aim of this study is to validate current SCD risk prediction methods in a German HCM cohort and to improve them by the addition of genotype information. METHODS: HCM patients without prior SCD or equivalent arrhythmic events ≥ 18 years of age were enrolled in an expert cardiomyopathy center in Germany. The primary endpoint was defined as SCD/-equivalent within 5 years of baseline evaluation. 5-year SCD-risk estimates and recommendations for ICD implantations, as defined by the ESC and AHA/ACC guidelines, were analyzed. Multivariate cox proportional hazards analyses were integrated with genetic findings as additive SCD risk. RESULTS: 283 patients were included and followed for in median 5.77 years (2.92; 8.85). A disease-causing variant was found in 138 (49%) patients. 14 (5%) patients reached the SCD endpoint (5-year incidence 4.9%). Kaplan-Meier survival analysis shows significantly lower overall SCD event-free survival for patients with an identified disease-causing variant (p < 0.05). The ESC HCM Risk-SCD model showed an area-under-the-curve (AUC) of 0.74 (95% CI 0.68-0.79; p < 0.0001) with a sensitivity of 0.29 (95% CI 0.08-0.58) and specificity of 0.83 (95% CI 0.78-0.88) for a risk estimate ≥ 6%/5-years. By comparison, the AHA/ACC HCM SCD risk stratification model showed an AUC of 0.70 (95% CI 0.65-0.76; p = 0.003) with a sensitivity of 0.93 (95% CI, 0.66-0.998) and specificity of 0.28 (95% CI 0.23-0.34) at the respective cut-off. The modified SCD Risk Score with genetic information yielded an AUC of 0.76 (95% CI 0.71-0.81; p < 0.0001) with a sensitivity of 0.86 (95% CI 0.57-0.98) and specificity of 0.69 (95% CI 0.63-0.74). The number-needed-to-treat (NNT) to prevent 1 SCD event by prophylactic ICD-implantation is 13 for the ESC model, 28 for AHA/ACC and 9 for the modified Genotype-model. CONCLUSION: This study confirms the performance of current risk models in clinical decision making. The integration of genetic findings into current SCD risk stratification methods seem feasible and can add in decision making, especially in borderline risk-groups. A subgroup of patients with high SCD risk remains unidentified by current risk scores.

Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data.

BACKGROUND: With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP). METHODS: For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done. FINDINGS: 66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77-0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77-7·95), with a Pearson correlation of 0·57 (95% CI 0·56-0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79-0·84) for ischaemic cardiomyopathy and 0·92 (0·91-0·94) for hypertrophic cardiomyopathy. INTERPRETATION: Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function. FUNDING: Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.