Global metabolomics revealed deviations from the metabolic aging clock in colorectal cancer patients

Background: Markers of aging hold promise in the context of colorectal cancer (CRC) care. Utilizing high-resolution metabolomic profiling, we can unveil distinctive age-related patterns that have the potential to predict early CRC development. Our study aims to unearth a panel of aging markers and delve into the metabolomic alterations associated with aging and CRC. Methods: We assembled a serum cohort comprising 5,649 individuals, consisting of 3,002 healthy volunteers, 715 patients diagnosed with colorectal advanced precancerous lesions (APL), and 1,932 CRC patients, to perform a comprehensive metabolomic analysis. Results: We successfully identified unique age-associated patterns across 42 metabolic pathways. Moreover, we established a metabolic aging clock, comprising 9 key metabolites, using an elastic net regularized regression model that accurately estimates chronological age. Notably, we observed significant chronological disparities among the healthy population, APL patients, and CRC patients. By combining the analysis of circulative carcinoembryonic antigen levels with the categorization of individuals into the "hypo" metabolic aging subgroup, our blood test demonstrates the ability to detect APL and CRC with positive predictive values of 68.4% (64.3%, 72.2%) and 21.4% (17.8%, 25.9%), respectively. Conclusions: This innovative approach utilizing our metabolic aging clock holds significant promise for accurately assessing biological age and enhancing our capacity to detect APL and CRC.

Utility of smart watches for identifying arrhythmias in children

BACKGROUND

Arrhythmia symptoms are frequent complaints in children and often require a pediatric cardiology evaluation. Data regarding the clinical utility of wearable technologies are limited in children. We hypothesize that an Apple Watch can capture arrhythmias in children.

METHODS

We present an analysis of patients ≤18 years-of-age who had signs of an arrhythmia documented by an Apple Watch. We include patients evaluated at our center over a 4-year-period and highlight those receiving a formal arrhythmia diagnosis. We evaluate the role of the Apple Watch in arrhythmia diagnosis, the results of other ambulatory cardiac monitoring studies, and findings of any EP studies.

RESULTS

We identify 145 electronic-medical-record identifications of Apple Watch, and find arrhythmias confirmed in 41 patients (28%) [mean age 13.8 ± 3.2 years]. The arrythmias include: 36 SVT (88%), 3 VT (7%), 1 heart block (2.5%) and wide 1 complex tachycardia (2.5%). We show that invasive EP study confirmed diagnosis in 34 of the 36 patients (94%) with SVT (2 non-inducible). We find that the Apple Watch helped prompt a workup resulting in a new arrhythmia diagnosis for 29 patients (71%). We note traditional ambulatory cardiac monitors were worn by 35 patients (85%), which did not detect arrhythmias in 10 patients (29%). In 73 patients who used an Apple Watch for recreational or self-directed heart rate monitoring, 18 (25%) sought care due to device findings without any arrhythmias identified.

CONCLUSION

We demonstrate that the Apple Watch can record arrhythmia events in children, including events not identified on traditionally used ambulatory monitors.

Exploring the feasibility of using long-term stored newborn dried blood spots to identify metabolic features for congenital heart disease screening

Congenital heart disease (CHD) represents a significant contributor to both morbidity and mortality in neonates and children. There's currently no analogous dried blood spot (DBS) screening for CHD immediately after birth. This study was set to assess the feasibility of using DBS to identify reliable metabolite biomarkers with clinical relevance, with the aim to screen and classify CHD utilizing the DBS. We assembled a cohort of DBS datasets from the California Department of Public Health (CDPH) Biobank, encompassing both normal controls and three pre-defined CHD categories. A DBS-based quantitative metabolomics method was developed using liquid chromatography with tandem mass spectrometry (LC-MS/MS). We conducted a correlation analysis comparing the absolute quantitated metabolite concentration in DBS against the CDPH NBS records to verify the reliability of metabolic profiling. For hydrophilic and hydrophobic metabolites, we executed significant pathway and metabolite analyses respectively. Logistic and LightGBM models were established to aid in CHD discrimination and classification. Consistent and reliable quantification of metabolites were demonstrated in DBS samples stored for up to 15 years. We discerned dysregulated metabolic pathways in CHD patients, including deviations in lipid and energy metabolism, as well as oxidative stress pathways. Furthermore, we identified three metabolites and twelve metabolites as potential biomarkers for CHD assessment and subtypes classifying. This study is the first to confirm the feasibility of validating metabolite profiling results using long-term stored DBS samples. Our findings highlight the potential clinical applications of our DBS-based methods for CHD screening and subtype classification.

High-throughput quantitation of amino acids and acylcarnitine in cerebrospinal fluid: identification of PCNSL biomarkers and potential metabolic messengers

Background: Due to the poor prognosis and rising occurrence, there is a crucial need to improve the diagnosis of Primary Central Nervous System Lymphoma (PCNSL), which is a rare type of non-Hodgkin's lymphoma. This study utilized targeted metabolomics of cerebrospinal fluid (CSF) to identify biomarker panels for the improved diagnosis or differential diagnosis of primary central nervous system lymphoma (PCNSL). Methods: In this study, a cohort of 68 individuals, including patients with primary central nervous system lymphoma (PCNSL), non-malignant disease controls, and patients with other brain tumors, was recruited. Their cerebrospinal fluid samples were analyzed using the Ultra-high performance liquid chromatography - tandem mass spectrometer (UHPLC-MS/MS) technique for targeted metabolomics analysis. Multivariate statistical analysis and logistic regression modeling were employed to identify biomarkers for both diagnosis (Dx) and differential diagnosis (Diff) purposes. The Dx and Diff models were further validated using a separate cohort of 34 subjects through logistic regression modeling. Results: A targeted analysis of 45 metabolites was conducted using UHPLC-MS/MS on cerebrospinal fluid (CSF) samples from a cohort of 68 individuals, including PCNSL patients, non-malignant disease controls, and patients with other brain tumors. Five metabolic features were identified as biomarkers for PCNSL diagnosis, while nine metabolic features were found to be biomarkers for differential diagnosis. Logistic regression modeling was employed to validate the Dx and Diff models using an independent cohort of 34 subjects. The logistic model demonstrated excellent performance, with an AUC of 0.83 for PCNSL vs. non-malignant disease controls and 0.86 for PCNSL vs. other brain tumor patients. Conclusion: Our study has successfully developed two logistic regression models utilizing metabolic markers in cerebrospinal fluid (CSF) for the diagnosis and differential diagnosis of PCNSL. These models provide valuable insights and hold promise for the future development of a non-invasive and reliable diagnostic tool for PCNSL.

Altered expression of the L-arginine/nitric oxide pathway in ovarian cancer: metabolic biomarkers and biological implications

MOTIVATION

Ovarian cancer (OC) is a highly lethal gynecological malignancy. Extensive research has shown that OC cells undergo significant metabolic alterations during tumorigenesis. In this study, we aim to leverage these metabolic changes as potential biomarkers for assessing ovarian cancer.

METHODS

A functional module-based approach was utilized to identify key gene expression pathways that distinguish different stages of ovarian cancer (OC) within a tissue biopsy cohort. This cohort consisted of control samples (n = 79), stage I/II samples (n = 280), and stage III/IV samples (n = 1016). To further explore these altered molecular pathways, minimal spanning tree (MST) analysis was applied, leading to the formulation of metabolic biomarker hypotheses for OC liquid biopsy. To validate, a multiple reaction monitoring (MRM) based quantitative LCMS/MS method was developed. This method allowed for the precise quantification of targeted metabolite biomarkers using an OC blood cohort comprising control samples (n = 464), benign samples (n = 3), and OC samples (n = 13).

RESULTS

Eleven functional modules were identified as significant differentiators (false discovery rate, FDR < 0.05) between normal and early-stage, or early-stage and late-stage ovarian cancer (OC) tumor tissues. MST analysis revealed that the metabolic L-arginine/nitric oxide (L-ARG/NO) pathway was reprogrammed, and the modules related to "DNA replication" and "DNA repair and recombination" served as anchor modules connecting the other nine modules. Based on this analysis, symmetric dimethylarginine (SDMA) and arginine were proposed as potential liquid biopsy biomarkers for OC assessment. Our quantitative LCMS/MS analysis on our OC blood cohort provided direct evidence supporting the use of the SDMA-to-arginine ratio as a liquid biopsy panel to distinguish between normal and OC samples, with an area under the ROC curve (AUC) of 98.3%.

CONCLUSION

Our comprehensive analysis of tissue genomics and blood quantitative LC/MSMS metabolic data shed light on the metabolic reprogramming underlying OC pathophysiology. These findings offer new insights into the potential diagnostic utility of the SDMA-to-arginine ratio for OC assessment. Further validation studies using adequately powered OC cohorts are warranted to fully establish the clinical effectiveness of this diagnostic test.

Development of a Urine Metabolomics Biomarker-Based Prediction Model for Preeclampsia during Early Pregnancy

Preeclampsia (PE) is a condition that poses a significant risk of maternal mortality and multiple organ failure during pregnancy. Early prediction of PE can enable timely surveillance and interventions, such as low-dose aspirin administration. In this study, conducted at Stanford Health Care, we examined a cohort of 60 pregnant women and collected 478 urine samples between gestational weeks 8 and 20 for comprehensive metabolomic profiling. By employing liquid chromatography mass spectrometry (LCMS/MS), we identified the structures of seven out of 26 metabolomics biomarkers detected. Utilizing the XGBoost algorithm, we developed a predictive model based on these seven metabolomics biomarkers to identify individuals at risk of developing PE. The performance of the model was evaluated using 10-fold cross-validation, yielding an area under the receiver operating characteristic curve of 0.856. Our findings suggest that measuring urinary metabolomics biomarkers offers a noninvasive approach to assess the risk of PE prior to its onset.

An Engineered Living Intestinal Muscle Patch Produces Macroscopic Contractions that can Mix and Break Down Artificial Intestinal Contents

The intestinal muscle layers execute various gut wall movements to achieve controlled propulsion and mixing of intestinal content. Engineering intestinal muscle layers with complex contractile function is critical for developing bioartificial intestinal tissue to treat patients with short bowel syndrome. Here, the first demonstration of a living intestinal muscle patch capable of generating three distinct motility patterns and displaying multiple digesta manipulations is reported. Assessment of contractility, cellular morphology, and transcriptome profile reveals that successful generation of the contracting muscle patch relies on both biological factors in a serum-free medium and environmental cues from an elastic electrospun gelatin scaffold. By comparing gene-expression patterns among samples, it is shown that biological factors from the medium strongly affect ion-transport activities, while the scaffold unexpectedly regulates cell-cell communication. Analysis of ligandreceptor interactome identifies scaffold-driven changes in intercellular communication, and 78% of the upregulated ligand-receptor interactions are involved in the development and function of enteric neurons. The discoveries highlight the importance of combining biomolecular and biomaterial approaches for tissue engineering. The living intestinal muscle patch represents a pivotal advancement for building functional replacement intestinal tissue. It offers a more physiological model for studying GI motility and for preclinical drug discovery.

Early prediction and longitudinal modeling of preeclampsia from multiomics

Preeclampsia is a complex disease of pregnancy whose physiopathology remains unclear. We developed machine-learning models for early prediction of preeclampsia (first 16 weeks of pregnancy) and over gestation by analyzing six omics datasets from a longitudinal cohort of pregnant women. For early pregnancy, a prediction model using nine urine metabolites had the highest accuracy and was validated on an independent cohort (area under the receiver-operating characteristic curve [AUC] = 0.88, 95% confidence interval [CI] [0.76, 0.99] cross-validated; AUC = 0.83, 95% CI [0.62,1] validated). Univariate analysis demonstrated statistical significance of identified metabolites. An integrated multiomics model further improved accuracy (AUC = 0.94). Several biological pathways were identified including tryptophan, caffeine, and arachidonic acid metabolisms. Integration with immune cytometry data suggested novel associations between immune and proteomic dynamics. While further validation in a larger population is necessary, these encouraging results can serve as a basis for a simple, early diagnostic test for preeclampsia.

Single center blind testing of a US multi-center validated diagnostic algorithm for Kawasaki disease in Taiwan

Background

Kawasaki disease (KD) is the leading cause of acquired heart disease in children. The major challenge in KD diagnosis is that it shares clinical signs with other childhood febrile control (FC) subjects. We sought to determine if our algorithmic approach applied to a Taiwan cohort.

Methods

A single center (Chang Gung Memorial Hospital in Taiwan) cohort of patients suspected with acute KD were prospectively enrolled by local KD specialists for KD analysis. Our previously single-center developed computer-based two-step algorithm was further tested by a five-center validation in US. This first blinded multi-center trial validated our approach, with sufficient sensitivity and positive predictive value, to identify most patients with KD diagnosed at centers across the US. This study involved 418 KDs and 259 FCs from the Chang Gung Memorial Hospital in Taiwan.

Findings

Our diagnostic algorithm retained sensitivity (379 of 418; 90.7%), specificity (223 of 259; 86.1%), PPV (379 of 409; 92.7%), and NPV (223 of 247; 90.3%) comparable to previous US 2016 single center and US 2020 fiver center results. Only 4.7% (15 of 418) of KD and 2.3% (6 of 259) of FC patients were identified as indeterminate. The algorithm identified 18 of 50 (36%) KD patients who presented 2 or 3 principal criteria. Of 418 KD patients, 157 were infants younger than one year and 89.2% (140 of 157) were classified correctly. Of the 44 patients with KD who had coronary artery abnormalities, our diagnostic algorithm correctly identified 43 (97.7%) including all patients with dilated coronary artery but one who found to resolve in 8 weeks.

Interpretation

This work demonstrates the applicability of our algorithmic approach and diagnostic portability in Taiwan.

A machine-learning algorithm for diagnosis of multisystem inflammatory syndrome in children and Kawasaki disease in the USA: a retrospective model development and validation study

BACKGROUND

Multisystem inflammatory syndrome in children (MIS-C) is a novel disease that was identified during the COVID-19 pandemic and is characterised by systemic inflammation following SARS-CoV-2 infection. Early detection of MIS-C is a challenge given its clinical similarities to Kawasaki disease and other acute febrile childhood illnesses. We aimed to develop and validate an artificial intelligence algorithm that can distinguish among MIS-C, Kawasaki disease, and other similar febrile illnesses and aid in the diagnosis of patients in the emergency department and acute care setting.

METHODS

In this retrospective model development and validation study, we developed a deep-learning algorithm called KIDMATCH (Kawasaki Disease vs Multisystem Inflammatory Syndrome in Children) using patient age, the five classic clinical Kawasaki disease signs, and 17 laboratory measurements. All features were prospectively collected at the time of initial evaluation from patients diagnosed with Kawasaki disease or other febrile illness between Jan 1, 2009, and Dec 31, 2019, at Rady Children's Hospital in San Diego (CA, USA). For patients with MIS-C, the same data were collected from patients between May 7, 2020, and July 20, 2021, at Rady Children's Hospital, Connecticut Children's Medical Center in Hartford (CT, USA), and Children's Hospital Los Angeles (CA, USA). We trained a two-stage model consisting of feedforward neural networks to distinguish between patients with MIS-C and those without and then those with Kawasaki disease and other febrile illnesses. After internally validating the algorithm using stratified tenfold cross-validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts. We finally externally validated KIDMATCH on patients with MIS-C enrolled between April 22, 2020, and July 21, 2021, from Boston Children's Hospital (MA, USA), Children's National Hospital (Washington, DC, USA), and the CHARMS Study Group consortium of 14 US hospitals.

FINDINGS

1517 patients diagnosed at Rady Children's Hospital between Jan 1, 2009, and June 7, 2021, with MIS-C (n=69), Kawasaki disease (n=775), or other febrile illnesses (n=673) were identified for internal validation, with an additional 16 patients with MIS-C included from Connecticut Children's Medical Center and 50 from Children's Hospital Los Angeles between May 7, 2020, and July 20, 2021. KIDMATCH achieved a median area under the receiver operating characteristic curve during internal validation of 98·8% (IQR 98·0-99·3) in the first stage and 96·0% (95·6-97·2) in the second stage. We externally validated KIDMATCH on 175 patients with MIS-C from Boston Children's Hospital (n=50), Children's National Hospital (n=42), and the CHARMS Study Group consortium of 14 US hospitals (n=83). External validation of KIDMATCH on patients with MIS-C correctly classified 76 of 81 patients (94% accuracy, two rejected by conformal prediction) from 14 hospitals in the CHARMS Study Group consortium, 47 of 49 patients (96% accuracy, one rejected by conformal prediction) from Boston Children's Hospital, and 36 of 40 patients (90% accuracy, two rejected by conformal prediction) from Children's National Hospital.

INTERPRETATION

KIDMATCH has the potential to aid front-line clinicians to distinguish between MIS-C, Kawasaki disease, and other similar febrile illnesses to allow prompt treatment and prevent severe complications.

FUNDING

US Eunice Kennedy Shriver National Institute of Child Health and Human Development, US National Heart, Lung, and Blood Institute, US Patient-Centered Outcomes Research Institute, US National Library of Medicine, the McCance Foundation, and the Gordon and Marilyn Macklin Foundation.

Abstract 4099: Clinical survey of Trop2 antibody drug conjugate target and payload biomarkers in multiple cancer indications using multiplex mass spectrometry

Introduction: Trop2 is overexpressed in many cancers and currently Trop2 ADC is approved in TNBC. In ADC drug design, it is imperative to assess not only the levels of the receptor but also the payload biomarkers. We have developed a multiplex mass spectrometry method to quantitate 72 actionable proteins from FFPE samples that requires minimal tissue (2-3 sections). This panel includes chemotherapy, targeted therapy and immunotherapy agents. The test is run in our CAP, CLIA, and NYSDOH approved laboratory. For this study, we examined a subset of samples run in the clinical lab for the levels of Trop2 (target biomarker) and payload biomarkers (Topo1, TUBB3). Topo1 is a chemosensitive marker for irinotecan, while TUBB3 is a chemoresistance marker for tubulin inhibitors.

Methods: FFPE tissue sections from 1140 clinical samples from a variety of cancers were examined. These include breast (n=318), colorectal (n=228), ovarian (n=199), GBM (n=69), NSCLC (n=169), HNSCC (n=91), and Gastric cancer (n=66). Two sections (10 µ) of FFPE tissue were cut on DIRECTOR slides and only the tumor areas were laser microdissected for downstream analysis which resulted in tryptic peptides. 1µg of peptides (~4000 cells) along with heavy peptides was injected into a triple quad mass spec and 72 biomarkers were quantitated concurrently.

Results: Trop2 showed a wide range of expression in various cancers. Almost all (95%)breast cancer samples expressed Trop2 which exhibited a wide range (93x; 157 - 14650 amol/µg). Topo1 and TUBB3 were expressed in 93% and 60% of samples respectively. 1/4th of NSCLC does not express Trop2 and there is a 106x difference in expression of Trop2 in NSCLC. Topo1 was expressed in almost all samples while TUBB3 was expressed in 80% of NSCLC. Majority of ovarian cancer samples (85%), HNSCC (89%), Gastric cancer (88%) samples expressed Trop2 with a 113x, 134x, 47x difference in expression. Chemosensitive biomarker Topo1 was expressed in almost all ovarian (96%), HNSCC (91%) and Gastric (99%) cancer samples. Chemoresistant marker TUBB3 was expressed in 66% of ovarian cancer, 44% of HNSCC and 45% of gastric cancer samples. In contrast to above cancers, only 10% of Glioblastoma samples express Trop2 and only 3/4th of GBMs express Topo1.

Discussion: In a randomly selected group of cancers, we have found Trop2 is expressed in majority of Breast, Ovarian, Lung, HNSCC and gastric cancers and minimal expression in GBM. Given the range of expression of anti-tubulin resistance marker in many solid tumors, a payload biomarker guided clinical trial is highly recommended in ADCs that employ anti-tubulin inhibitors. In contrast, wide expression of chemosensitive biomarker for Topo1 payload makes it a promising candidate for many solid tumors. Further studies are warranted to determine the level of target and payload biomarkers that will be required for a clinical response.

Citation Format: Sheeno P. Thyparambil, Wei-Li Liao, Robert Heaton, Guolin Zhang, Amanda Strasbaugh, Marya Melkie, Xuefeng B. Ling. Clinical survey of Trop2 antibody drug conjugate target and payload biomarkers in multiple cancer indications using multiplex mass spectrometry [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4099.

Multi-Omics Signatures Link to Ticagrelor Effects on Vascular Function in Patients With Acute Coronary Syndrome

BACKGROUND

Long-term antiplatelet agents including the potent P2Y12 antagonist ticagrelor are indicated in patients with a previous history of acute coronary syndrome. We sought to compare the effect of ticagrelor with that of aspirin monotherapy on vascular endothelial function in patients with prior acute coronary syndrome.

METHODS

This was a prospective, single center, parallel group, investigator-blinded randomized controlled trial. We randomized 200 patients on long-term aspirin monotherapy with prior acute coronary syndrome in a 1:1 fashion to receive ticagrelor 60 mg BD (n=100) or aspirin 100 mg OD (n=100). The primary end point was change from baseline in brachial artery flow-mediated dilation at 12 weeks. Secondary end points were changes to platelet activation marker (CD41_62p) and endothelial progenitor cell (CD34/133) count measured by flow cytometry, plasma level of adenosine, IL-6 (interleukin-6) and EGF (epidermal growth factor), and multi-omics profiling at 12 weeks.

RESULTS

After 12 weeks, brachial flow-mediated dilation was significantly increased in the ticagrelor group compared with the aspirin group (ticagrelor: 3.48±3.48% versus aspirin: -1.26±2.85%, treatment effect 4.73 [95% CI, 3.85-5.62], P<0.001). Nevertheless ticagrelor treatment for 12 weeks had no significant effect on platelet activation markers, circulating endothelial progenitor cell count or plasma level of adenosine, IL-6, and EGF (all P>0.05). Multi-omics pathway assessment revealed that changes in the metabolism and biosynthesis of amino acids (cysteine and methionine metabolism; phenylalanine, tyrosine, and tryptophan biosynthesis) and phospholipids (glycerophosphoethanolamines and glycerophosphoserines) were associated with improved brachial artery flow-mediated dilation in the ticagrelor group.

CONCLUSIONS

In patients with prior acute coronary syndrome, ticagrelor 60 mg BD monotherapy significantly improved brachial flow-mediated dilation compared with aspirin monotherapy and was associated with significant changes in metabolomic and lipidomic signatures.

REGISTRATION

URL: https://www.

CLINICALTRIALS

gov; Unique identifier: NCT03881943.

Serological Phenotyping Analysis Uncovers a Unique Metabolomic Pattern Associated With Early Onset of Type 2 Diabetes Mellitus

Background: Type 2 diabetes mellitus (T2DM) is a multifaceted disorder affecting epidemic proportion at global scope. Defective insulin secretion by pancreatic β-cells and the inability of insulin-sensitive tissues to respond effectively to insulin are the underlying biology of T2DM. However, circulating biomarkers indicative of early diabetic onset at the asymptomatic stage have not been well described. We hypothesized that global and targeted mass spectrometry (MS) based metabolomic discovery can identify novel serological metabolic biomarkers specifically associated with T2DM. We further hypothesized that these markers can have a unique pattern associated with latent or early asymptomatic stage, promising an effective liquid biopsy approach for population T2DM risk stratification and screening.

Methods: Four independent cohorts were assembled for the study. The T2DM cohort included sera from 25 patients with T2DM and 25 healthy individuals for the biomarker discovery and sera from 15 patients with T2DM and 15 healthy controls for the testing. The Pre-T2DM cohort included sera from 76 with prediabetes and 62 healthy controls for the model training and sera from 35 patients with prediabetes and 27 healthy controls for the model testing. Both global and targeted (amino acid, acylcarnitine, and fatty acid) approaches were used to deep phenotype the serological metabolome by high performance liquid chromatography-high resolution mass spectrometry. Different machine learning approaches (Random Forest, XGBoost, and ElasticNet) were applied to model the unique T2DM/Pre-T2DM metabolic patterns and contrasted with their effectiness to differentiate T2DM/Pre-T2DM from controls.

Results: The univariate analysis identified unique panel of metabolites (n = 22) significantly associated with T2DM. Global metabolomics and subsequent structure determination led to the identification of 8 T2DM biomarkers while targeted LCMS profiling discovered 14 T2DM biomarkers. Our panel can effectively differentiate T2DM (ROC AUC = 1.00) or Pre-T2DM (ROC AUC = 0.84) from the controls in the respective testing cohort.

Conclusion: Our serological metabolite panel can be utilized to identifiy asymptomatic population at risk of T2DM, which may provide utility in identifying population at risk at an early stage of diabetic development to allow for clinical intervention. This early detection would guide ehanced levels of care and accelerate development of clinical strategies to prevent T2DM.

Multicenter Validation of a Machine Learning Algorithm for Diagnosing Pediatric Patients with Multisystem Inflammatory Syndrome and Kawasaki Disease

BACKGROUND

Multisystem inflammatory syndrome in children (MIS-C) is a novel disease identified during the COVID-19 pandemic characterized by systemic inflammation following SARS-CoV-2 infection. Delays in diagnosing MIS-C may lead to more severe disease with cardiac dysfunction or death. Most pediatric patients recover fully with anti-inflammatory treatments, but early detection of MIS-C remains a challenge given its clinical similarities to Kawasaki disease (KD) and other acute childhood illnesses.

METHODS

We developed KIDMATCH ( K awasak I D isease vs M ultisystem Infl A mma T ory syndrome in CH ildren), a deep learning algorithm for screening patients for MIS-C, KD, or other febrile illness, using age, the five classical clinical KD signs, and 17 laboratory measurements prospectively collected within 24 hours of admission to the emergency department from 1448 patients diagnosed with KD or other febrile illness between January 1, 2009 and December 31, 2019 at Rady Children's Hospital. For MIS-C patients, the same data was collected from 131 patients between May 14, 2020 to June 18, 2021 at Rady Children's Hospital, Connecticut Children's Hospital, and Children's Hospital Los Angeles. We trained a two-stage model consisting of feedforward neural networks to distinguish between MIS-C and non MIS-C patients and then KD and other febrile illness. After internally validating the algorithm using 10-fold cross validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts, enhancing the model generalizability and confidence by flagging unfamiliar cases as indeterminate instead of making spurious predictions. We externally validated KIDMATCH on 175 MIS-C patients from 16 hospitals across the United States.

FINDINGS

KIDMATCH achieved a high median area under the curve in the 10-fold cross validation of 0.988 [IQR: 0.98-0.993] in the first stage and 0.96 [IQR: 0.956-0.972] in the second stage using thresholds set at 95% sensitivity to detect positive MIS-C and KD cases respectively during training. External validation of KIDMATCH on MIS-C patients correctly classified 76/83 (2 rejected) patients from the CHARMS consortium, 47/50 (1 rejected) patients from Boston Children's Hospital, and 36/42 (2 rejected) patients from Children's National Hospital.

INTERPRETATION

KIDMATCH has the potential to aid frontline clinicians with distinguishing between MIS-C, KD, and similar febrile illnesses in a timely manner to allow prompt treatment and prevent severe complications.

FUNDING

Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Heart, Lung, and Blood Institute, Patient-Centered Outcomes Research Institute, National Library of Medicine.

Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model

BACKGROUND

New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span the entire spectrum of clinical care, but there are no HIE-based clinical decision support tools for diagnosis of incident-HF. We applied machine-learning methods to model the one-year risk of incident-HF from the Maine statewide-HIE.

METHODS AND RESULTS

We included subjects aged ≥ 40 years without prior HF ICD9/10 codes during a three-year period from 2015 to 2018, and incident-HF defined as assignment of two outpatient or one inpatient code in a year. A tree-boosting algorithm was used to model the probability of incident-HF in year two from data collected in year one, and then validated in year three. 5,668 of 521,347 patients (1.09%) developed incident-HF in the validation cohort. In the validation cohort, the model c-statistic was 0.824 and at a clinically predetermined risk threshold, 10% of patients identified by the model developed incident-HF and 29% of all incident-HF cases in the state of Maine were identified.

CONCLUSIONS

Utilizing machine learning modeling techniques on passively collected clinical HIE data, we developed and validated an incident-HF prediction tool that performs on par with other models that require proactively collected clinical data. Our algorithm could be integrated into other HIEs to leverage the EMR resources to provide individuals, systems, and payors with a risk stratification tool to allow for targeted resource allocation to reduce incident-HF disease burden on individuals and health care systems.

Early-pregnancy prediction of risk for pre-eclampsia using maternal blood leptin/ceramide ratio: discovery and confirmation

OBJECTIVE

This study aimed to develop a blood test for the prediction of pre-eclampsia (PE) early in gestation. We hypothesised that the longitudinal measurements of circulating adipokines and sphingolipids in maternal serum over the course of pregnancy could identify novel prognostic biomarkers that are predictive of impending event of PE early in gestation.

STUDY DESIGN

Retrospective discovery and longitudinal confirmation.

SETTING

Maternity units from two US hospitals.

PARTICIPANTS

Six previously published studies of placental tissue (78 PE and 95 non-PE) were compiled for genomic discovery, maternal sera from 15 women (7 non-PE and 8 PE) enrolled at ProMedDx were used for sphingolipidomic discovery, and maternal sera from 40 women (20 non-PE and 20 PE) enrolled at Stanford University were used for longitudinal observation.

OUTCOME MEASURES

Biomarker candidates from discovery were longitudinally confirmed and compared in parallel to the ratio of placental growth factor (PlGF) and soluble fms-like tyrosine kinase (sFlt-1) using the same cohort. The datasets were generated by enzyme-linked immunosorbent and liquid chromatography-tandem mass spectrometric assays.

RESULTS

Our discovery integrating genomic and sphingolipidomic analysis identified leptin (Lep) and ceramide (Cer) (d18:1/25:0) as novel biomarkers for early gestational assessment of PE. Our longitudinal observation revealed a marked elevation of Lep/Cer (d18:1/25:0) ratio in maternal serum at a median of 23 weeks' gestation among women with impending PE as compared with women with uncomplicated pregnancy. The Lep/Cer (d18:1/25:0) ratio significantly outperformed the established sFlt-1/PlGF ratio in predicting impending event of PE with superior sensitivity (85% vs 20%) and area under curve (0.92 vs 0.52) from 5 to 25 weeks of gestation.

CONCLUSIONS

Our study demonstrated the longitudinal measurement of maternal Lep/Cer (d18:1/25:0) ratio allows the non-invasive assessment of PE to identify pregnancy at high risk in early gestation, outperforming the established sFlt-1/PlGF ratio test.

Integrated trajectories of the maternal metabolome, proteome, and immunome predict labor onset

Estimating the time of delivery is of high clinical importance because pre- and postterm deviations are associated with complications for the mother and her offspring. However, current estimations are inaccurate. As pregnancy progresses toward labor, major transitions occur in fetomaternal immune, metabolic, and endocrine systems that culminate in birth. The comprehensive characterization of maternal biology that precedes labor is key to understanding these physiological transitions and identifying predictive biomarkers of delivery. Here, a longitudinal study was conducted in 63 women who went into labor spontaneously. More than 7000 plasma analytes and peripheral immune cell responses were analyzed using untargeted mass spectrometry, aptamer-based proteomic technology, and single-cell mass cytometry in serial blood samples collected during the last 100 days of pregnancy. The high-dimensional dataset was integrated into a multiomic model that predicted the time to spontaneous labor [R = 0.85, 95% confidence interval (CI) [0.79 to 0.89], P = 1.2 × 10^-40, N = 53, training set; R = 0.81, 95% CI [0.61 to 0.91], P = 3.9 × 10^-7, N = 10, independent test set]. Coordinated alterations in maternal metabolome, proteome, and immunome marked a molecular shift from pregnancy maintenance to prelabor biology 2 to 4 weeks before delivery. A surge in steroid hormone metabolites and interleukin-1 receptor type 4 that preceded labor coincided with a switch from immune activation to regulation of inflammatory responses. Our study lays the groundwork for developing blood-based methods for predicting the day of labor, anchored in mechanisms shared in preterm and term pregnancies.

Understanding how biologic and social determinants affect disparities in preterm birth and outcomes of preterm infants in the NICU

To understand the disparities in spontaneous preterm birth (sPTB) and/or its outcomes, biologic and social determinants as well as healthcare practice (such as those in neonatal intensive care units) should be considered. Disparities in sPTB have been largely intractable and remain obscure in most cases, despite a myriad of identified risk factors for and causes of sPTB. We still do not know how they lead to the different outcomes at different gestational ages and if they are independent of NICU practices. Here we describe an integrated approach to study the interplay between the genome and exposome, which may drive biochemistry and physiology and lead to health disparities.

Proteomic signatures predict preeclampsia in individual cohorts but not across cohorts - implications for clinical biomarker studies

Background:

Early identification of pregnant women at risk for preeclampsia (PE) is important, as it will enable targeted interventions ahead of clinical manifestations. The quantitative analyses of plasma proteins feature prominently among molecular approaches used for risk prediction. However, derivation of protein signatures of sufficient predictive power has been challenging. The recent availability of platforms simultaneously assessing over 1000 plasma proteins offers broad examinations of the plasma proteome, which may enable the extraction of proteomic signatures with improved prognostic performance in prenatal care.

Objective:

The primary aim of this study was to examine the generalizability of proteomic signatures predictive of PE in two cohorts of pregnant women whose plasma proteome was interrogated with the same highly multiplexed platform. Establishing generalizability, or lack thereof, is critical to devise strategies facilitating the development of clinically useful predictive tests. A second aim was to examine the generalizability of protein signatures predictive of gestational age (GA) in uncomplicated pregnancies in the same cohorts to contrast physiological and pathological pregnancy outcomes.

Study design:

Serial blood samples were collected during the first, second, and third trimesters in 18 women who developed PE and 18 women with uncomplicated pregnancies (Stanford cohort). The second cohort (Detroit), used for comparative analysis, consisted of 76 women with PE and 90 women with uncomplicated pregnancies. Multivariate analyses were applied to infer predictive and cohort-specific proteomic models, which were then tested in the alternate cohort. Gene ontology (GO) analysis was performed to identify biological processes that were over-represented among top-ranked proteins associated with PE.

Results:

The model derived in the Stanford cohort was highly significant (p = 3.9E–15) and predictive (AUC = 0.96), but failed validation in the Detroit cohort (p = 9.7E–01, AUC = 0.50). Similarly, the model derived in the Detroit cohort was highly significant (p = 1.0E–21, AUC = 0.73), but failed validation in the Stanford cohort (p = 7.3E–02, AUC = 0.60). By contrast, proteomic models predicting GA were readily validated across the Stanford (p = 1.1E–454, R = 0.92) and Detroit cohorts (p = 1.1.E–92, R = 0.92) indicating that the proteomic assay performed well enough to infer a generalizable model across studied cohorts, which makes it less likely that technical aspects of the assay, including batch effects, accounted for observed differences.

Conclusions:

Results point to a broader issue relevant for proteomic and other omic discovery studies in patient cohorts suffering from a clinical syndrome, such as PE, driven by heterogeneous pathophysiologies. While novel technologies including highly multiplex proteomic arrays and adapted computational algorithms allow for novel discoveries for a particular study cohort, they may not readily generalize across cohorts. A likely reason is that the prevalence of pathophysiologic processes leading up to the “same” clinical syndrome can be distributed differently in different and smaller-sized cohorts. Signatures derived in individual cohorts may simply capture different facets of the spectrum of pathophysiologic processes driving a syndrome. Our findings have important implications for the design of omic studies of a syndrome like PE. They highlight the need for performing such studies in diverse and well-phenotyped patient populations that are large enough to characterize subsets of patients with shared pathophysiologies to then derive subset-specific signatures of sufficient predictive power.

Targeted multiplex proteomics (TMP) and genomics of early-onset colorectal cancer (EO-CRC)

97

Background: The incidence and mortality of early-onset colorectal cancer (EO-CRC) is on the rise. Consequently, there is an urgent unmet need to better understand their unique tumor biology to expand therapeutic options and improve clinical outcomes. Methods: Exploratory Targeted multiplex proteomics (TMP) and targeted 648 gene panel was performed on specimens from 35 patients with resected colon cancer diagnosed at age < = 40 years. TMP panel consisted of 72 proteins involved in differentiation, tumorigenesis, and response to chemotherapy, targeted therapy, and immunotherapy. Clinicopathologic and genomic data were also collected. Results: The median age of diagnosis was 33 years. The cohort included 15 male and 20 female patients. 20 (57%) had left-sided tumors and 6 (17%) had stage IV disease. Notable genomic alterations included mutations in: BRAF V600E (2/35); RAS (15/35); PIK3CA exon 9 or 20 (5/35); and ERBB2 (2/35). One patient exhibited ERBB2 amplification. 9/35 tumors were MSI-H. TMP analysis revealed overexpression of chemotherapy resistance proteins in several patients: ALDH1A1:16/35; ERCC1:1/35; GART:26/35; MDR1:9/35; MGMT:5/35; RRM1:6/35; TUBB3:1/35; TYMS:2/35; XRCC1:11/35. In contrast, some tumors exhibited elevated biomarkers of chemosensitivity: hENT1:8/35; DHFR:12/35; TYMP:15/35; OPRT:8/35; SLFN11:1/35; TLE:11/35; TOPO1:12/35; TOPO2A:1/35. Protein targets of cell signaling pathways were overexpressed in a number of tumors: CAT:16/35; CAV-1: 6/35; CBL:2/35; E-Cadherin: 19/35; HSP90A:16/35; HSP90B:18/35; MET:5/35; NQO1:18/35; paxillin:4/35; SRC:21/35; STAT3:11/35. Regarding EGFR and KRAS, none of the tumors exhibited elevated protein expression level. Furthermore, RAS mutational status did not correlate with the level of EGFR or KRAS protein expression. Antibody drug conjugate biomarkers were observed. HER2 overexpression was noted in one patient who had a confirmed ERBB2 amplification. Regarding immunotherapy targets, PDL-1 protein was not overexpressed in any tumor, whereas MSLN and TROP2 were elevated in 1/35 and 2/35 patients, respectively. Conclusions: TMP analysis of EO-CRC patients revealed marked heterogeneity in the expression of proteins involved in differentiation, tumorigenesis, and response to chemotherapy, targeted therapy, and immunotherapy. Differential protein expression may provide insight into therapeutic vulnerabilities for EO-CRC. Furthermore, the discordance between detected genomic alterations and protein expression levels highlights the complementary nature of genomic sequencing and TMP analysis.

Maternal metabolic profiling to assess fetal gestational age and predict preterm delivery: a two-centre retrospective cohort study in the US

OBJECTIVES

The aim of this study was to develop a single blood test that could determine gestational age and estimate the risk of preterm birth by measuring serum metabolites. We hypothesised that serial metabolic modelling of serum analytes throughout pregnancy could be used to describe fetal gestational age and project preterm birth with a high degree of precision.

STUDY DESIGN

A retrospective cohort study.

SETTING

Two medical centres from the USA.

PARTICIPANTS

Thirty-six patients (20 full-term, 16 preterm) enrolled at Stanford University were used to develop gestational age and preterm birth risk algorithms, 22 patients (9 full-term, 13 preterm) enrolled at the University of Alabama were used to validate the algorithms.

OUTCOME MEASURES

Maternal blood was collected serially throughout pregnancy. Metabolic datasets were generated using mass spectrometry.

RESULTS

A model to determine gestational age was developed (R²=0.98) and validated (R²=0.81). 66.7% of the estimates fell within ±1 week of ultrasound results during model validation. Significant disruptions from full-term pregnancy metabolic patterns were observed in preterm pregnancies (R²=-0.68). A separate algorithm to predict preterm birth was developed using a set of 10 metabolic pathways that resulted in an area under the curve of 0.96 and 0.92, a sensitivity of 0.88 and 0.86, and a specificity of 0.96 and 0.92 during development and validation testing, respectively.

CONCLUSIONS

In this study, metabolic profiling was used to develop and test a model for determining gestational age during full-term pregnancy progression, and to determine risk of preterm birth. With additional patient validation studies, these algorithms may be used to identify at-risk pregnancies prompting alterations in clinical care, and to gain biological insights into the pathophysiology of preterm birth. Metabolic pathway-based pregnancy modelling is a novel modality for investigation and clinical application development.

Kinetics of SARS-CoV-2 positivity of infected and recovered patients from a single center

Recurrence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) positive detection in infected but recovered individuals has been reported. Patients who have recovered from coronavirus disease 2019 (COVID-19) could profoundly impact the health care system. We sought to define the kinetics and relevance of PCR-positive recurrence during recovery from acute COVID-19 to better understand risks for prolonged infectivity and reinfection. A series of 414 patients with confirmed SARS-Cov-2 infection, at The Second Affiliated Hospital of Southern University of Science and Technology in Shenzhen, China from January 11 to April 23, 2020. Statistical analyses were performed of the clinical, laboratory, radiologic image, medical treatment, and clinical course of admission/quarantine/readmission data, and a recurrence predictive algorithm was developed. 16.7% recovered patients with PCR positive recurring one to three times, despite being in strict quarantine. Younger patients with mild pulmonary respiratory syndrome had higher risk of PCR positivity recurrence. The recurrence prediction model had an area under the ROC curve of 0.786. This case series provides characteristics of patients with recurrent SARS-CoV-2 positivity. Use of a prediction algorithm may identify patients at high risk of recurrent SARS-CoV-2 positivity and help to establish protocols for health policy.

High-throughput quantitation of serological ceramides/dihydroceramides by LC/MS/MS: Pregnancy baseline biomarkers and potential metabolic messengers

Ceramides and dihydroceramides are sphingolipids that present in abundance at the cellular membrane of eukaryotes. Although their metabolic dysregulation has been implicated in many diseases, our knowledge about circulating ceramide changes during the pregnancy remains limited. In this study, we present the development and validation of a high-throughput liquid chromatography-tandem mass spectrometric method for simultaneous quantification of 16 ceramides and 10 dihydroceramides in human serum within 5 min. by using stable isotope-labeled ceramides as internal standards. This method employs a protein precipitation method for high throughput sample preparation, reverse phase isocratic elusion for chromatographic separation, and Multiple Reaction Monitoring for mass spectrometric detection. To qualify for clinical applications, our assay has been validated against the FDA guidelines for Lower Limit of Quantitation (1 nM), linearity (R²>0.99), precision (imprecision<15 %), accuracy (inaccuracy<15 %), extraction recovery (>90 %), stability (>85 %), and carryover (<0.01 %). With enhanced sensitivity and specificity from this method, we have, for the first time, determined the serological levels of ceramides and dihydroceramides to reveal unique temporal gestational patterns. Our approach could have value in providing insights into disorders of pregnancy.

Multicentre validation of a computer-based tool for differentiation of acute Kawasaki disease from clinically similar febrile illnesses

BACKGROUND

The clinical features of Kawasaki disease (KD) overlap with those of other paediatric febrile illnesses. A missed or delayed diagnosis increases the risk of coronary artery damage. Our computer algorithm for KD and febrile illness differentiation had a sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 94.8%, 70.8%, 93.7% and 98.3%, respectively, in a single-centre validation study. We sought to determine the performance of this algorithm with febrile children from multiple institutions across the USA.

METHODS

We used our previously published 18-variable panel that includes illness day, the five KD clinical criteria and readily available laboratory values. We applied this two-step algorithm using a linear discriminant analysis-based clinical model followed by a random forest-based algorithm to a cohort of 1059 acute KD and 282 febrile control patients from five children's hospitals across the USA.

RESULTS

The algorithm correctly classified 970 of 1059 patients with KD and 163 of 282 febrile controls resulting in a sensitivity of 91.6%, specificity of 57.8% and PPV and NPV of 95.4% and 93.1%, respectively. The algorithm also correctly identified 218 of the 232 KD patients (94.0%) with abnormal echocardiograms.

INTERPRETATION

The expectation is that the predictive accuracy of the algorithm will be reduced in a real-world setting in which patients with KD are rare and febrile controls are common. However, the results of the current analysis suggest that this algorithm warrants a prospective, multicentre study to evaluate its potential utility as a physician support tool.

Proteomic profiling to identify therapeutics targets in glioblastoma (GBM)

2555

Background: Glioblastoma (GBM) is an aggressive primary brain tumor with poor prognosis. Treatment at diagnosis is largely confined to surgery, radiation and temozolomide (TMZ) with median progression-free survival (PFS) of 7 months and median overall survival (mOS) of 15 months. GBM tumors recur in most cases and in patients with recurrent GBM, the mOS is 6.2 months. The lack of effective therapies underscores the importance of exploring other agents. We propose that quantitating therapy-associated protein biomarkers can improve treatment personalization for GBM. Methods: 97 FFPE GBM tissues were microdissected and solubilized for mass spectrometry-based proteomic analysis of therapy-associated protein biomarkers in our CLIA certified lab. We quantified protein levels of MGMT, hENT1, RRM1, TOPO1 and EGFR/TUBB3 (antibody target and payload resistance markers, respectively, for anti-EGFR ADCs) simultaneously. The multiplexed assay also quantified additional 24 clinically relevant proteins. Results: 43/57 patients were predicted to respond to TMZ based on undetectable levels of MGMT, confirming wide utility of this agent. 42/97(43%) patients were predicted to have gemcitabine sensitivity based on high expression of the response marker (hENT1 > 100 amol/ug) and low expression of the resistance marker (RRM1 < 700 amol/ug). 11/97(11%) patients expressed TOPO1 > 1350 amol/ug (75th percentile of all indications tested by author’s laboratory), suggesting likely response to irinotecan and topotecan. EGFR expression ranged from < 100 amol/ug to > 25000 amol/ug, including overexpression (> 1500 amol/ug) in 22%(21/97) of cases. While expression of EGFR(81/97, 84%) suggested likely response to anti-EGFR ADC, concurrent expression of TUBB3(78/81) may indicate resistance to several known payloads, such as taxanes and MMAE. Conjugation with another payload that targets sensitivity marker TOPO1 (68% expression) is a likely option. Proteomic analysis also revealed detectable levels of multiple RTKs (FGFR(4), AXL(20), IGF1R(10), MET overexpression(1), and HER2 overexpression(2)), indicating potential response to RTK inhibitors. Exploratory investigation in tumor vs TME using proteomics and metabolomics is ongoing. Conclusions: In this population of GBM patients, proteomic analysis identified protein targets of multiple approved and investigational therapies. Gemcitabine, which crosses the blood-brain barrier, may be considered as a salvage option after TMZ failure. Proteomic quantitation of EGFR and TUBB3 may improve patient selection for EGFR-targeting ADCs.

Deviation from the precisely timed phenomic ageotypes can assist in early CRC screening and reveal underlying pathophysiology

e16098

Background: Human serum proteome and metabolome profiles have been analyzed to explore the molecular changes that occur with aging. We hypothesized that deep phenomic profiling of longitudinal sera would allow the identification of distinct phenomic chronologic patterns as a normal biological clock baseline to study personal aging. We further hypothesized that molecular assessment of this chronologic deviation, due to advance adenoma and early CRC, from the normal reference ageotypes would be instrumental as potential early diagnostics and reveal underlying pathophysiology. Methods: A cohort of 7673 normal, 746 advanced adenoma, 1177 stage I, 103 stage II and 119 stage III blood samples were assembled. Innovative multi-omics approaches, with global and targeted LCMS data production (metabolomics, lipidomics, and 2D proteomics), were applied to deep profile these subjects. Identification of the age-associated molecular patterns in normal subjects, modeled with an elastic net algorithm, established the reference baseline to mirror a biological clock. CRC associated deviation from this chronologically paced multi-omics clock was quantified to screen for early CRCs and explore the underlying pathophysiology. Results: Multiple mProbe aging indices of proteins and metabolites were identified, strongly predicting chronologic age ( P < 0.001, R > 0.90). Significant disruptions from normal molecular patterns were observed in advanced adenoma and early CRCs patients (R < 0.7). Pathway analysis of the proteins/metabolites with deviating patterns revealed both known and new pathways underlying CRC. Unsupervised cluster analysis identified unique aging subgroups among advanced adenoma and different stage CRC patients, indicating unique underlying biology relating to aging with different severities of cancer burdens. Conclusions: Deviations from the meticulously timed phenomic aging patterns may provide utility to allow future early CRC screening. Close examination of the underlying pathophysiology associated with early CRC, relating to ageotypes, not only may improve the sensitivity and specificity of prognostic and diagnostic tests of early CRCs, but also shed new insights into CRC therapeutics.

Changes in pregnancy-related serum biomarkers early in gestation are associated with later development of preeclampsia

Background

Placental protein expression plays a crucial role during pregnancy. We hypothesized that: (1) circulating levels of pregnancy-associated, placenta-related proteins throughout gestation reflect the temporal progression of the uncomplicated, full-term pregnancy, and can effectively estimate gestational ages (GAs); and (2) preeclampsia (PE) is associated with disruptions in these protein levels early in gestation; and can identify impending PE. We also compared gestational profiles of proteins in the human and mouse, using pregnant heme oxygenase-1 (HO-1) heterozygote (Het) mice, a mouse model reflecting PE-like symptoms.

Methods

Serum levels of placenta-related proteins–leptin (LEP), chorionic somatomammotropin hormone like 1 (CSHL1), elabela (ELA), activin A, soluble fms-like tyrosine kinase 1 (sFlt-1), and placental growth factor (PlGF)–were quantified by ELISA in blood serially collected throughout human pregnancies (20 normal subjects with 66 samples, and 20 subjects who developed PE with 61 samples). Multivariate analysis was performed to estimate the GA in normal pregnancy. Mean-squared errors of GA estimations were used to identify impending PE. The human protein profiles were then compared with those in the pregnant HO-1 Het mice.

Results

An elastic net-based gestational dating model was developed (R² = 0.76) and validated (R² = 0.61) using serum levels of the 6 proteins measured at various GAs from women with normal uncomplicated pregnancies. In women who developed PE, the model was not (R² = -0.17) associated with GA. Deviations from the model estimations were observed in women who developed PE (P = 0.01). The model developed with 5 proteins (ELA excluded) performed similarly from sera from normal human (R² = 0.68) and WT mouse (R² = 0.85) pregnancies. Disruptions of this model were observed in both human PE-associated (R² = 0.27) and mouse HO-1 Het (R² = 0.30) pregnancies. LEP outperformed sFlt-1 and PlGF in differentiating impending PE at early human and late mouse GAs.

Conclusions

Serum placenta-related protein profiles are temporally regulated throughout normal pregnancies and significantly disrupted in women who develop PE. LEP changes earlier than the well-established biomarkers (sFlt-1 and PlGF). There may be evidence of a causative action of HO-1 deficiency in LEP upregulation in a PE-like murine model.

Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records

Suicide is the tenth leading cause of death in the United States (US). An early-warning system (EWS) for suicide attempt could prove valuable for identifying those at risk of suicide attempts, and analyzing the contribution of repeated attempts to the risk of eventual death by suicide. In this study we sought to develop an EWS for high-risk suicide attempt patients through the development of a population-based risk stratification surveillance system. Advanced machine-learning algorithms and deep neural networks were utilized to build models with the data from electronic health records (EHRs). A final risk score was calculated for each individual and calibrated to indicate the probability of a suicide attempt in the following 1-year time period. Risk scores were subjected to individual-level analysis in order to aid in the interpretation of the results for health-care providers managing the at-risk cohorts. The 1-year suicide attempt risk model attained an area under the curve (AUC ROC) of 0.792 and 0.769 in the retrospective and prospective cohorts, respectively. The suicide attempt rate in the "very high risk" category was 60 times greater than the population baseline when tested in the prospective cohorts. Mental health disorders including depression, bipolar disorders and anxiety, along with substance abuse, impulse control disorders, clinical utilization indicators, and socioeconomic determinants were recognized as significant features associated with incident suicide attempt.

Expression of antibody-drug conjugates (ADC) biomarkers in colorectal cancer

17

Background: Multiple ADCs are in clinical trials for CRC and the optimal strategy for selecting patients who may benefit from the treatment is evolving. Due to the unique mechanism of ADCs, patient selection should involve screening not only for the presence of the antibody target, but also for markers of resistance or response to the payload. We have built a multiplexed ADC biomarker panel in FFPE tumor tissue that simultaneously quantifies the protein levels of the antibody targets and also the payload markers. Methods: FFPE tumor tissues from 363 CRC patients were microdissected and solubilized for mass spectrometry-based targeted proteomic analysis in our CLIA certified laboratory. We quantified protein levels of EGFR, HER2, HER3, Axl, Mesothelin, FRalpha, Trop2 (antibody targets), tubulin-beta3 and TOPO1 (payload resistance and response markers, respectively) simultaneously. The multiplexed assay also quantified additional 22 clinically relevant proteins. Results: Expression of EGFR(83%), HER2(52%), HER3(21.5%), Axl(3.7%), Mesothelin(26.5%), FRalpha(3.7%), and Trop2(59.8%) may indicate likely response to ADCs. Expression of TUBB3(+) and TOPO1 (>1350amol/µg) in antibody target-positive subset may suggest resistance or response to payloads, such as taxanes and irinotecan, respectively (Table). Previously we identified that HER2 expression >750amol/µg correlated with HER2 positivity. Accordingly, 1.4% (5/355) of CRC patients were HER2 positive, of which 40% (2/5) had TOPO1 expression >1350amol/µg (75th percentile) suggesting that these 2 patients may receive benefit from a HER2/TOPO1 ADC. (+) indicates expression ≥LOQ; (-) indicates expression <LOQ. Conclusions: In patients with CRC, quantitative proteomics identified both antibody targets and markers of resistance or response to the payloads for multiple approved and investigational ADC therapies.

[Table: see text]

Integrating multiple “omics” analyses, on a triage concept, for effective case selection followed by diagnostic colonoscopy

244

Background: Implementation of population screening for colorectal cancer (CRC) before colonoscopy can reduce the challenge of the overall capacity of bowel examination and improve survival. Blood based CRC assessment biomarkers, on a triage concept, can lead to improved selection to colonoscopy and cost-effective CRC care. Methods: Innovative multi-omics approaches, with global and targeted LCMS data production (metabolomics, lipidomics, and 2D proteomics) and integrative data analytics, were applied to discover serological biomarkers to assess nonadvanced adenoma and identify stage I/II colorectal bowel lesions. A cohort of 2396 normal, 660 adenoma, 953 stage I, and 101 stage II blood samples, was constructed to discover screening biomarkers to support case finding of patients at high risk for nonadvanced adenoma and stage I/II cancer for subsequent diagnostic colonoscopy. Results: A three-analyte mProbe panel was constructed which outperformed the commercial assays of plasma methylated septin 9 and fecal Cologuard tests. Sensitivity: (1) nonadvanced adenoma–Cologuard 17.2%, mProbe 76.0%; (2) stage I-III-Cologuard 93.3%, stage I-II Septin 9 (ARUP laboratories) 77%, stage I-II mProbe: 92.3%. Specificity–Cologuard 89.8%, Septin 9 (ARUP laboratories) 88%, mProbe 90.7%. Conclusions: mProbe triage concept of a blood-based protein biomarker panel promises the precision to allow future CRC screening, and reduce the low-risk utilization of unnecessary, unpleasant and risk-associated bowel examinations.

A proteomic clock for malignant gliomas: The role of the environment in tumorigenesis at the presymptomatic stage

Malignant gliomas remain incurable with a poor prognosis despite of aggressive treatment. We have been studying the development of brain tumors in a glioma rat model, where rats develop brain tumors after prenatal exposure to ethylnitrosourea (ENU), and there is a sizable interval between when the first pathological changes are noted and tumors become detectable with MRI. Our aim to define a molecular timeline through proteomic profiling of the cerebrospinal fluid (CSF) such that brain tumor commitment can be revealed earlier than at the presymptomatic stage. A comparative proteomic approach was applied to profile CSF collected serially either before, at and after the time MRI becomes positive. Elastic net (EN) based models were developed to infer the timeline of normal or tumor development respectively, mirroring a chronology of precisely timed, “clocked”, adaptations. These CSF changes were later quantified by longitudinal entropy analyses of the EN predictive metric. False discovery rates (FDR) were computed to control the expected proportion of the EN models that are due to multiple hypothesis testing. Our ENU rat brain tumor dating EN model indicated that protein content in CSF is programmed even before tumor MRI detection. The findings of the precisely timed CSF tumor microenvironment changes at presymptomatic stages, deviation from the normal development timeline, may provide the groundwork for the understanding of adaptation of the brain environment in tumorigenesis to devise effective brain tumor management strategies.

Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine

BACKGROUND

Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate.

OBJECTIVE

The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of new incident lung cancer within the next 1 year in the general population.

METHODS

Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients with at least one EHR between April 1, 2016, and March 31, 2018, who had no history of lung cancer. A retrospective cohort (N=873,598) and a prospective cohort (N=836,659) were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual to quantify the probability of a new incident lung cancer diagnosis from October 1, 2016, to September 31, 2017. The model was trained with the clinical profile in the retrospective cohort from the preceding 6 months and validated with the prospective cohort to predict the risk of incident lung cancer from April 1, 2017, to March 31, 2018.

RESULTS

The model had an area under the curve (AUC) of 0.881 (95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium-, and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than that in the overall cohort (1167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with new incident lung cancer.

CONCLUSIONS

We retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify statewide high-risk patients, which will benefit the population health through establishment of preventive interventions or more intensive surveillance.

Estimating One-Year Risk of Incident Chronic Kidney Disease: Retrospective Development and Validation Study Using Electronic Medical Record Data From the State of Maine

Background

Chronic kidney disease (CKD) is a major public health concern in the United States with high prevalence, growing incidence, and serious adverse outcomes.

Objective

We aimed to develop and validate a model to identify patients at risk of receiving a new diagnosis of CKD (incident CKD) during the next 1 year in a general population.

Methods

The study population consisted of patients who had visited any care facility in the Maine Health Information Exchange network any time between January 1, 2013, and December 31, 2015, and had no history of CKD diagnosis. Two retrospective cohorts of electronic medical records (EMRs) were constructed for model derivation (N=1,310,363) and validation (N=1,430,772). The model was derived using a gradient tree-based boost algorithm to assign a score to each individual that measured the probability of receiving a new diagnosis of CKD from January 1, 2014, to December 31, 2014, based on the preceding 1-year clinical profile. A feature selection process was conducted to reduce the dimension of the data from 14,680 EMR features to 146 as predictors in the final model. Relative risk was calculated by the model to gauge the risk ratio of the individual to population mean of receiving a CKD diagnosis in next 1 year. The model was tested on the validation cohort to predict risk of CKD diagnosis in the period from January 1, 2015, to December 31, 2015, using the preceding 1-year clinical profile.

Results

The final model had a c-statistic of 0.871 in the validation cohort. It stratified patients into low-risk (score 0-0.005), intermediate-risk (score 0.005-0.05), and high-risk (score ≥ 0.05) levels. The incidence of CKD in the high-risk patient group was 7.94%, 13.7 times higher than the incidence in the overall cohort (0.58%). Survival analysis showed that patients in the 3 risk categories had significantly different CKD outcomes as a function of time (P<.001), indicating an effective classification of patients by the model.

Conclusions

We developed and validated a model that is able to identify patients at high risk of having CKD in the next 1 year by statistically learning from the EMR-based clinical history in the preceding 1 year. Identification of these patients indicates care opportunities such as monitoring and adopting intervention plans that may benefit the quality of care and outcomes in the long term.

A Classification Tool for Differentiation of Kawasaki Disease from Other Febrile Illnesses

OBJECTIVE

To develop and validate a novel decision tree-based clinical algorithm to differentiate Kawasaki disease (KD) from other pediatric febrile illnesses that share common clinical characteristics.

STUDY DESIGN

Using clinical and laboratory data from 801 subjects with acute KD (533 for development, and 268 for validation) and 479 febrile control subjects (318 for development, and 161 for validation), we developed a stepwise KD diagnostic algorithm combining our previously developed linear discriminant analysis (LDA)-based model with a newly developed tree-based algorithm.

RESULTS

The primary model (LDA) stratified the 1280 subjects into febrile controls (n = 276), indeterminate (n = 247), and KD (n = 757) subgroups. The subsequent model (decision trees) further classified the indeterminate group into febrile controls (n = 103) and KD (n = 58) subgroups, leaving only 29 of 801 KD (3.6%) and 57 of 479 febrile control (11.9%) subjects indeterminate. The 2-step algorithm had a sensitivity of 96.0% and a specificity of 78.5%, and correctly classified all subjects with KD who later developed coronary artery aneurysms.

CONCLUSION

The addition of a decision tree step increased sensitivity and specificity in the classification of subject with KD and febrile controls over our previously described LDA model. A multicenter trial is needed to prospectively determine its utility as a point of care diagnostic test for KD.

Prehypertension During Normotensive Pregnancy and Postpartum Clustering of Cardiometabolic Risk Factors: A Prospective Cohort Study

The nonstratification of blood pressure (BP) levels may underestimate future cardiovascular risk in pregnant women who present with BP levels in the range of prehypertension (120-139/80-89 mm Hg). We prospectively evaluated the relationship between multiple antepartum BP measurements (from 11(+0) to 13(+6) weeks' gestation to term) and the occurrence of postpartum metabolic syndrome in 507 normotensive pregnant women after a live birth. By using latent class growth modeling, we identified the following 3 distinctive diastolic BP (DBP) trajectory groups: the low-J-shaped group (34.2%; DBP from 62.5±5.8 to 65.0±6.8 mm Hg), the moderate-U-shaped group (52.6%; DBP from 71.0±5.9 to 69.8±6.2 mm Hg), and the elevated-J-shaped group (13.2%; DBP from 76.2±6.7 to 81.8±4.8 mm Hg). Notably, the elevated-J-shaped trajectory group had mean DBP and systolic BP levels within the range of prehypertension from 37(+0) and 26(+0) weeks of pregnancy, respectively. Among the 309 women who completed the ≈1.6 years of postpartum follow-up, the women in the elevated-J-shaped group had greater odds of developing postpartum metabolic syndrome (adjusted odds ratio, 6.55; 95% confidence interval, 1.79-23.92; P=0.004) than the low-J-shaped group. Moreover, a parsimonious model incorporating DBP (membership in the elevated-J-shaped group but not in the DBP prehypertension group as identified by a single measurement) and elevated levels of fasting glucose (>4.99 mmol/L) and triglycerides (>3.14 mmol/L) at term was developed, with good discrimination and calibration for postpartum metabolic syndrome (c-statistic, 0.764; 95% confidence interval, 0.674-0.855; P<0.001). Therefore, prehypertension identified by DBP trajectories throughout pregnancy is an independent risk factor for predicting postpartum metabolic syndrome in normotensive pregnant women.

Urinary Colorimetric Sensor Array and Algorithm to Distinguish Kawasaki Disease from Other Febrile Illnesses

Objectives

Kawasaki disease (KD) is an acute pediatric vasculitis of infants and young children with unknown etiology and no specific laboratory-based test to identify. A specific molecular diagnostic test is urgently needed to support the clinical decision of proper medical intervention, preventing subsequent complications of coronary artery aneurysms. We used a simple and low-cost colorimetric sensor array to address the lack of a specific diagnostic test to differentiate KD from febrile control (FC) patients with similar rash/fever illnesses.

Study Design

Demographic and clinical data were prospectively collected for subjects with KD and FCs under standard protocol. After screening using a genetic algorithm, eleven compounds including metalloporphyrins, pH indicators, redox indicators and solvatochromic dye categories, were selected from our chromatic compound library (n = 190) to construct a colorimetric sensor array for diagnosing KD. Quantitative color difference analysis led to a decision-tree-based KD diagnostic algorithm.

Results

This KD sensing array allowed the identification of 94% of KD subjects (receiver operating characteristic [ROC] area under the curve [AUC] 0.981) in the training set (33 KD, 33 FC) and 94% of KD subjects (ROC AUC: 0.873) in the testing set (16 KD, 17 FC). Color difference maps reconstructed from the digital images of the sensing compounds demonstrated distinctive patterns differentiating KD from FC patients.

Conclusions

The colorimetric sensor array, composed of common used chemical compounds, is an easily accessible, low-cost method to realize the discrimination of subjects with KD from other febrile illness.

Prospective stratification of patients at risk for emergency department revisit: resource utilization and population management strategy implications

Background

Estimating patient risk of future emergency department (ED) revisits can guide the allocation of resources, e.g. local primary care and/or specialty, to better manage ED high utilization patient populations and thereby improve patient life qualities.

Methods

We set to develop and validate a method to estimate patient ED revisit risk in the subsequent 6 months from an ED discharge date. An ensemble decision-tree-based model with Electronic Medical Record (EMR) encounter data from HealthInfoNet (HIN), Maine’s Health Information Exchange (HIE), was developed and validated, assessing patient risk for a subsequent 6 month return ED visit based on the ED encounter-associated demographic and EMR clinical history data. A retrospective cohort of 293,461 ED encounters that occurred between January 1, 2012 and December 31, 2012, was assembled with the associated patients’ 1-year clinical histories before the ED discharge date, for model training and calibration purposes. To validate, a prospective cohort of 193,886 ED encounters that occurred between January 1, 2013 and June 30, 2013 was constructed.

Results

Statistical learning that was utilized to construct the prediction model identified 152 variables that included the following data domains: demographics groups (12), different encounter history (104), care facilities (12), primary and secondary diagnoses (10), primary and secondary procedures (2), chronic disease condition (1), laboratory test results (2), and outpatient prescription medications (9). The c-statistics for the retrospective and prospective cohorts were 0.742 and 0.730 respectively. Total medical expense and ED utilization by risk score 6 months after the discharge were analyzed. Cluster analysis identified discrete subpopulations of high-risk patients with distinctive resource utilization patterns, suggesting the need for diversified care management strategies.

Conclusions

Integration of our method into the HIN secure statewide data system in real time prospectively validated its performance. It promises to provide increased opportunity for high ED utilization identification, and optimized resource and population management.

Electronic supplementary material

The online version of this article (doi:10.1186/s12873-016-0074-5) contains supplementary material, which is available to authorized users.

Novel data-mining approach identifies biomarkers for diagnosis of Kawasaki disease

BACKGROUND

As Kawasaki disease (KD) shares many clinical features with other more common febrile illnesses and misdiagnosis, leading to a delay in treatment, increases the risk of coronary artery damage, a diagnostic test for KD is urgently needed. We sought to develop a panel of biomarkers that could distinguish between acute KD patients and febrile controls (FC) with sufficient accuracy to be clinically useful.

METHODS

Plasma samples were collected from three independent cohorts of FC and acute KD patients who met the American Heart Association definition for KD and presented within the first 10 d of fever. The levels of 88 biomarkers associated with inflammation were assessed by Luminex bead technology. Unsupervised clustering followed by supervised clustering using a Random Forest model was used to find a panel of candidate biomarkers.

RESULTS

A panel of biomarkers commonly available in the hospital laboratory (absolute neutrophil count, erythrocyte sedimentation rate, alanine aminotransferase, γ-glutamyl transferase, concentrations of α-1-antitrypsin, C-reactive protein, and fibrinogen, and platelet count) accurately diagnosed 81-96% of KD patients in a series of three independent cohorts.

CONCLUSION

After prospective validation, this eight-biomarker panel may improve the recognition of KD.

Virtual Pharmacist: A Platform for Pharmacogenomics

We present Virtual Pharmacist, a web-based platform that takes common types of high-throughput data, namely microarray SNP genotyping data, FASTQ and Variant Call Format (VCF) files as inputs, and reports potential drug responses in terms of efficacy, dosage and toxicity at one glance. Batch submission facilitates multivariate analysis or data mining of targeted groups. Individual analysis consists of a report that is readily comprehensible to patients and practioners who have basic knowledge in pharmacology, a table that summarizes variants and potential affected drug response according to the US Food and Drug Administration pharmacogenomic biomarker labeled drug list and PharmGKB, and visualization of a gene-drug-target network. Group analysis provides the distribution of the variants and potential affected drug response of a target group, a sample-gene variant count table, and a sample-drug count table. Our analysis of genomes from the 1000 Genome Project underlines the potentially differential drug responses among different human populations. Even within the same population, the findings from Watson's genome highlight the importance of personalized medicine. Virtual Pharmacist can be accessed freely at http://www.sustc-genome.org.cn/vp or installed as a local web server. The codes and documentation are available at the GitHub repository (https://github.com/VirtualPharmacist/vp). Administrators can download the source codes to customize access settings for further development.

Development, Validation and Deployment of a Real Time 30 Day Hospital Readmission Risk Assessment Tool in the Maine Healthcare Information Exchange

Objectives

Identifying patients at risk of a 30-day readmission can help providers design interventions, and provide targeted care to improve clinical effectiveness. This study developed a risk model to predict a 30-day inpatient hospital readmission for patients in Maine, across all payers, all diseases and all demographic groups.

Methods

Our objective was to develop a model to determine the risk for inpatient hospital readmission within 30 days post discharge. All patients within the Maine Health Information Exchange (HIE) system were included. The model was retrospectively developed on inpatient encounters between January 1, 2012 to December 31, 2012 from 24 randomly chosen hospitals, and then prospectively validated on inpatient encounters from January 1, 2013 to December 31, 2013 using all HIE patients.

Results

A risk assessment tool partitioned the entire HIE population into subgroups that corresponded to probability of hospital readmission as determined by a corresponding positive predictive value (PPV). An overall model c-statistic of 0.72 was achieved. The total 30-day readmission rates in low (score of 0–30), intermediate (score of 30–70) and high (score of 70–100) risk groupings were 8.67%, 24.10% and 74.10%, respectively. A time to event analysis revealed the higher risk groups readmitted to a hospital earlier than the lower risk groups. Six high-risk patient subgroup patterns were revealed through unsupervised clustering. Our model was successfully integrated into the statewide HIE to identify patient readmission risk upon admission and daily during hospitalization or for 30 days subsequently, providing daily risk score updates.

Conclusions

The risk model was validated as an effective tool for predicting 30-day readmissions for patients across all payer, disease and demographic groups within the Maine HIE. Exposing the key clinical, demographic and utilization profiles driving each patient’s risk of readmission score may be useful to providers in developing individualized post discharge care plans.

Exploring Value in Congenital Heart Disease: An Evaluation of Inpatient Admissions

OBJECTIVES

Understanding value provides an important context for improvement. However, most health care models fail to measure value. Our objective was to categorize inpatient encounters within an academic congenital heart program based on clinical outcome and the cost to achieve the outcome (value). We aimed to describe clinical and nonclinical features associated with value.

DESIGN

We defined hospital encounters based on outcome per resource utilized. We performed principal component and cluster analysis to classify encounters based on mortality, length of stay, hospital cost and revenue into six classes. We used nearest shrunken centroid to identify discriminant features associated with the cluster-derived classes. These features underwent hierarchical clustering and multivariate analysis to identify features associated with each class.

STUDY SETTING/PATIENTS

We analyzed all patients admitted to an academic congenital heart program between September 1, 2009, and December 31, 2012.

OUTCOME MEASURES/RESULTS

A total of 2658 encounters occurred during the study period. Six classes were categorized by value. Low-performing value classes were associated with greater institutional reward; however, encounters with higher-performing value were associated with a loss in profitability. Encounters that included insertion of a pediatric ventricular assist device (log OR 2.5 [95% CI, 1.78 to 3.43]) and acquisition of a hospital-acquired infection (log OR 1.42 [95% CI, 0.99 to 1.87]) were risk factors for inferior health care value.

CONCLUSIONS

Among the patients in our study, institutional reward was not associated with value. We describe a framework to target quality improvement and resource management efforts that can benefit patients, institutions, and payers alike.

NLP based congestive heart failure case finding: A prospective analysis on statewide electronic medical records

BACKGROUND

In order to proactively manage congestive heart failure (CHF) patients, an effective CHF case finding algorithm is required to process both structured and unstructured electronic medical records (EMR) to allow complementary and cost-efficient identification of CHF patients.

METHODS AND RESULTS

We set to identify CHF cases from both EMR codified and natural language processing (NLP) found cases. Using narrative clinical notes from all Maine Health Information Exchange (HIE) patients, the NLP case finding algorithm was retrospectively (July 1, 2012-June 30, 2013) developed with a random subset of HIE associated facilities, and blind-tested with the remaining facilities. The NLP based method was integrated into a live HIE population exploration system and validated prospectively (July 1, 2013-June 30, 2014). Total of 18,295 codified CHF patients were included in Maine HIE. Among the 253,803 subjects without CHF codings, our case finding algorithm prospectively identified 2411 uncodified CHF cases. The positive predictive value (PPV) is 0.914, and 70.1% of these 2411 cases were found to be with CHF histories in the clinical notes.

CONCLUSIONS

A CHF case finding algorithm was developed, tested and prospectively validated. The successful integration of the CHF case findings algorithm into the Maine HIE live system is expected to improve the Maine CHF care.

Cerebrospinal fluid protein dynamic driver network: At the crossroads of brain tumorigenesis

To get a better understanding of the ongoing in situ environmental changes preceding the brain tumorigenesis, we assessed cerebrospinal fluid (CSF) proteome profile changes in a glioma rat model in which brain tumor invariably developed after a single in utero exposure to the neurocarcinogen ethylnitrosourea (ENU). Computationally, the CSF proteome profile dynamics during the tumorigenesis can be modeled as non-smooth or even abrupt state changes. Such brain tumor environment transition analysis, correlating the CSF composition changes with the development of early cellular hyperplasia, can reveal the pathogenesis process at network level during a time before the image detection of the tumors. In our controlled rat model study, matched ENU- and saline-exposed rats' CSF proteomics changes were quantified at approximately 30, 60, 90, 120, 150 days of age (P30, P60, P90, P120, P150). We applied our transition-based network entropy (TNE) method to compute the CSF proteome changes in the ENU rat model and test the hypothesis of the critical transition state prior to impending hyperplasia. Our analysis identified a dynamic driver network (DDN) of CSF proteins related with the emerging tumorigenesis progressing from the non-hyperplasia state. The DDN associated leading network CSF proteins can allow the early detection of such dynamics before the catastrophic shift to the clear clinical landmarks in gliomas. Future characterization of the critical transition state (P60) during the brain tumor progression may reveal the underlying pathophysiology to device novel therapeutics preventing tumor formation. More detailed method and information are accessible through our website at http://translationalmedicine.stanford.edu.

Real-time web-based assessment of total population risk of future emergency department utilization: statewide prospective active case finding study

Background

An easily accessible real-time Web-based utility to assess patient risks of future emergency department (ED) visits can help the health care provider guide the allocation of resources to better manage higher-risk patient populations and thereby reduce unnecessary use of EDs.

Objective

Our main objective was to develop a Health Information Exchange-based, next 6-month ED risk surveillance system in the state of Maine.

Methods

Data on electronic medical record (EMR) encounters integrated by HealthInfoNet (HIN), Maine’s Health Information Exchange, were used to develop the Web-based surveillance system for a population ED future 6-month risk prediction. To model, a retrospective cohort of 829,641 patients with comprehensive clinical histories from January 1 to December 31, 2012 was used for training and then tested with a prospective cohort of 875,979 patients from July 1, 2012, to June 30, 2013.

Results

The multivariate statistical analysis identified 101 variables predictive of future defined 6-month risk of ED visit: 4 age groups, history of 8 different encounter types, history of 17 primary and 8 secondary diagnoses, 8 specific chronic diseases, 28 laboratory test results, history of 3 radiographic tests, and history of 25 outpatient prescription medications. The c-statistics for the retrospective and prospective cohorts were 0.739 and 0.732 respectively. Integration of our method into the HIN secure statewide data system in real time prospectively validated its performance. Cluster analysis in both the retrospective and prospective analyses revealed discrete subpopulations of high-risk patients, grouped around multiple “anchoring” demographics and chronic conditions. With the Web-based population risk-monitoring enterprise dashboards, the effectiveness of the active case finding algorithm has been validated by clinicians and caregivers in Maine.

Conclusions

The active case finding model and associated real-time Web-based app were designed to track the evolving nature of total population risk, in a longitudinal manner, for ED visits across all payers, all diseases, and all age groups. Therefore, providers can implement targeted care management strategies to the patient subgroups with similar patterns of clinical histories, driving the delivery of more efficient and effective health care interventions. To the best of our knowledge, this prospectively validated EMR-based, Web-based tool is the first one to allow real-time total population risk assessment for statewide ED visits.

Risk prediction of emergency department revisit 30 days post discharge: a prospective study

BACKGROUND

Among patients who are discharged from the Emergency Department (ED), about 3% return within 30 days. Revisits can be related to the nature of the disease, medical errors, and/or inadequate diagnoses and treatment during their initial ED visit. Identification of high-risk patient population can help device new strategies for improved ED care with reduced ED utilization.

METHODS AND FINDINGS

A decision tree based model with discriminant Electronic Medical Record (EMR) features was developed and validated, estimating patient ED 30 day revisit risk. A retrospective cohort of 293,461 ED encounters from HealthInfoNet (HIN), Maine's Health Information Exchange (HIE), between January 1, 2012 and December 31, 2012, was assembled with the associated patients' demographic information and one-year clinical histories before the discharge date as the inputs. To validate, a prospective cohort of 193,886 encounters between January 1, 2013 and June 30, 2013 was constructed. The c-statistics for the retrospective and prospective predictions were 0.710 and 0.704 respectively. Clinical resource utilization, including ED use, was analyzed as a function of the ED risk score. Cluster analysis of high-risk patients identified discrete sub-populations with distinctive demographic, clinical and resource utilization patterns.

CONCLUSIONS

Our ED 30-day revisit model was prospectively validated on the Maine State HIN secure statewide data system. Future integration of our ED predictive analytics into the ED care work flow may lead to increased opportunities for targeted care intervention to reduce ED resource burden and overall healthcare expense, and improve outcomes.

A novel urine peptide biomarker-based algorithm for the prognosis of necrotising enterocolitis in human infants

OBJECTIVE

Necrotising enterocolitis (NEC) is a major source of neonatal morbidity and mortality. The management of infants with NEC is currently complicated by our inability to accurately identify those at risk for progression of disease prior to the development of irreversible intestinal necrosis. We hypothesised that integrated analysis of clinical parameters in combination with urine peptide biomarkers would lead to improved prognostic accuracy in the NEC population.

DESIGN

Infants under suspicion of having NEC (n=550) were prospectively enrolled from a consortium consisting of eight university-based paediatric teaching hospitals. Twenty-seven clinical parameters were used to construct a multivariate predictor of NEC progression. Liquid chromatography/mass spectrometry was used to profile the urine peptidomes from a subset of this population (n=65) to discover novel biomarkers of NEC progression. An ensemble model for the prediction of disease progression was then created using clinical and biomarker data.

RESULTS

The use of clinical parameters alone resulted in a receiver-operator characteristic curve with an area under the curve of 0.817 and left 40.1% of all patients in an 'indeterminate' risk group. Three validated urine peptide biomarkers (fibrinogen peptides: FGA1826, FGA1883 and FGA2659) produced a receiver-operator characteristic area under the curve of 0.856. The integration of clinical parameters with urine biomarkers in an ensemble model resulted in the correct prediction of NEC outcomes in all cases tested.

CONCLUSIONS

Ensemble modelling combining clinical parameters with biomarker analysis dramatically improves our ability to identify the population at risk for developing progressive NEC.

Urine protein biomarkers for the diagnosis and prognosis of necrotizing enterocolitis in infants

OBJECTIVES

To test the hypothesis that an exploratory proteomics analysis of urine proteins with subsequent development of validated urine biomarker panels would produce molecular classifiers for both the diagnosis and prognosis of infants with necrotizing enterocolitis (NEC).

STUDY DESIGN

Urine samples were collected from 119 premature infants (85 NEC, 17 sepsis, 17 control) at the time of initial clinical concern for disease. The urine from 59 infants was used for candidate biomarker discovery by liquid chromatography/mass spectrometry. The remaining 60 samples were subject to enzyme-linked immunosorbent assay for quantitative biomarker validation.

RESULTS

A panel of 7 biomarkers (alpha-2-macroglobulin-like protein 1, cluster of differentiation protein 14, cystatin 3, fibrinogen alpha chain, pigment epithelium-derived factor, retinol binding protein 4, and vasolin) was identified by liquid chromatography/mass spectrometry and subsequently validated by enzyme-linked immunosorbent assay. These proteins were consistently found to be either up- or down-regulated depending on the presence, absence, or severity of disease. Biomarker panel validation resulted in a receiver-operator characteristic area under the curve of 98.2% for NEC vs sepsis and an area under the curve of 98.4% for medical NEC vs surgical NEC.

CONCLUSIONS

We identified 7 urine proteins capable of providing highly accurate diagnostic and prognostic information for infants with suspected NEC. This work represents a novel approach to improving the efficiency with which we diagnose early NEC and identify those at risk for developing severe, or surgical, disease.

A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis

Background

Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. The objective in this study was to develop and validate new NEC scoring systems for automated staging and prognostic forecasting.

Study design

A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data.

Results

Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner.

Algorithm availability

http://translationalmedicine.stanford.edu/cgi-bin/NEC/index.pl and smartphone application upon request.