Similar Risk of Kidney Failure among Patients with Blinding Diseases Who Receive Ranibizumab, Aflibercept, and Bevacizumab: An Observational Health Data Sciences and Informatics Network Study.

PURPOSE: To characterize the incidence of kidney failure associated with intravitreal anti-VEGF exposure; and compare the risk of kidney failure in patients treated with ranibizumab, aflibercept, or bevacizumab. DESIGN: Retrospective cohort study across 12 databases in the Observational Health Data Sciences and Informatics (OHDSI) network. SUBJECTS: Subjects aged ≥ 18 years with ≥ 3 monthly intravitreal anti-VEGF medications for a blinding disease (diabetic retinopathy, diabetic macular edema, exudative age-related macular degeneration, or retinal vein occlusion). METHODS: The standardized incidence proportions and rates of kidney failure while on treatment with anti-VEGF were calculated. For each comparison (e.g., aflibercept versus ranibizumab), patients from each group were matched 1:1 using propensity scores. Cox proportional hazards models were used to estimate the risk of kidney failure while on treatment. A random effects meta-analysis was performed to combine each database's hazard ratio (HR) estimate into a single network-wide estimate. MAIN OUTCOME MEASURES: Incidence of kidney failure while on anti-VEGF treatment, and time from cohort entry to kidney failure. RESULTS: Of the 6.1 million patients with blinding diseases, 37 189 who received ranibizumab, 39 447 aflibercept, and 163 611 bevacizumab were included; the total treatment exposure time was 161 724 person-years. The average standardized incidence proportion of kidney failure was 678 per 100 000 persons (range, 0-2389), and incidence rate 742 per 100 000 person-years (range, 0-2661). The meta-analysis HR of kidney failure comparing aflibercept with ranibizumab was 1.01 (95% confidence interval [CI], 0.70-1.47; P = 0.45), ranibizumab with bevacizumab 0.95 (95% CI, 0.68-1.32; P = 0.62), and aflibercept with bevacizumab 0.95 (95% CI, 0.65-1.39; P = 0.60). CONCLUSIONS: There was no substantially different relative risk of kidney failure between those who received ranibizumab, bevacizumab, or aflibercept. Practicing ophthalmologists and nephrologists should be aware of the risk of kidney failure among patients receiving intravitreal anti-VEGF medications and that there is little empirical evidence to preferentially choose among the specific intravitreal anti-VEGF agents. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Machine Learning and Real-World Data to Predict Lung Cancer Risk in Routine Care.

BACKGROUND: This study used machine learning to develop a 3-year lung cancer risk prediction model with large real-world data in a mostly younger population. METHODS: Over 4.7 million individuals, aged 45 to 65 years with no history of any cancer or lung cancer screening, diagnostic, or treatment procedures, with an outpatient visit in 2013 were identified in Optum's de-identified Electronic Health Record (EHR) dataset. A least absolute shrinkage and selection operator model was fit using all available data in the 365 days prior. Temporal validation was assessed with recent data. External validation was assessed with data from Mercy Health Systems EHR and Optum's de-identified Clinformatics Data Mart Database. Racial inequities in model discrimination were assessed with xAUCs. RESULTS: The model AUC was 0.76. Top predictors included age, smoking, race, ethnicity, and diagnosis of chronic obstructive pulmonary disease. The model identified a high-risk group with lung cancer incidence 9 times the average cohort incidence, representing 10% of patients with lung cancer. Model performed well temporally and externally, while performance was reduced for Asians and Hispanics. CONCLUSIONS: A high-dimensional model trained using big data identified a subset of patients with high lung cancer risk. The model demonstrated transportability to EHR and claims data, while underscoring the need to assess racial disparities when using machine learning methods. IMPACT: This internally and externally validated real-world data-based lung cancer prediction model is available on an open-source platform for broad sharing and application. Model integration into an EHR system could minimize physician burden by automating identification of high-risk patients.

Seek COVER: using a disease proxy to rapidly develop and validate a personalized risk calculator for COVID-19 outcomes in an international network.

BACKGROUND: We investigated whether we could use influenza data to develop prediction models for COVID-19 to increase the speed at which prediction models can reliably be developed and validated early in a pandemic. We developed COVID-19 Estimated Risk (COVER) scores that quantify a patient's risk of hospital admission with pneumonia (COVER-H), hospitalization with pneumonia requiring intensive services or death (COVER-I), or fatality (COVER-F) in the 30-days following COVID-19 diagnosis using historical data from patients with influenza or flu-like symptoms and tested this in COVID-19 patients. METHODS: We analyzed a federated network of electronic medical records and administrative claims data from 14 data sources and 6 countries containing data collected on or before 4/27/2020. We used a 2-step process to develop 3 scores using historical data from patients with influenza or flu-like symptoms any time prior to 2020. The first step was to create a data-driven model using LASSO regularized logistic regression, the covariates of which were used to develop aggregate covariates for the second step where the COVER scores were developed using a smaller set of features. These 3 COVER scores were then externally validated on patients with 1) influenza or flu-like symptoms and 2) confirmed or suspected COVID-19 diagnosis across 5 databases from South Korea, Spain, and the United States. Outcomes included i) hospitalization with pneumonia, ii) hospitalization with pneumonia requiring intensive services or death, and iii) death in the 30 days after index date. RESULTS: Overall, 44,507 COVID-19 patients were included for model validation. We identified 7 predictors (history of cancer, chronic obstructive pulmonary disease, diabetes, heart disease, hypertension, hyperlipidemia, kidney disease) which combined with age and sex discriminated which patients would experience any of our three outcomes. The models achieved good performance in influenza and COVID-19 cohorts. For COVID-19 the AUC ranges were, COVER-H: 0.69-0.81, COVER-I: 0.73-0.91, and COVER-F: 0.72-0.90. Calibration varied across the validations with some of the COVID-19 validations being less well calibrated than the influenza validations. CONCLUSIONS: This research demonstrated the utility of using a proxy disease to develop a prediction model. The 3 COVER models with 9-predictors that were developed using influenza data perform well for COVID-19 patients for predicting hospitalization, intensive services, and fatality. The scores showed good discriminatory performance which transferred well to the COVID-19 population. There was some miscalibration in the COVID-19 validations, which is potentially due to the difference in symptom severity between the two diseases. A possible solution for this is to recalibrate the models in each location before use.

90-Day all-cause mortality can be predicted following a total knee replacement: an international, network study to develop and validate a prediction model.

PURPOSE: The purpose of this study was to develop and validate a prediction model for 90-day mortality following a total knee replacement (TKR). TKR is a safe and cost-effective surgical procedure for treating severe knee osteoarthritis (OA). Although complications following surgery are rare, prediction tools could help identify high-risk patients who could be targeted with preventative interventions. The aim was to develop and validate a simple model to help inform treatment choices. METHODS: A mortality prediction model for knee OA patients following TKR was developed and externally validated using a US claims database and a UK general practice database. The target population consisted of patients undergoing a primary TKR for knee OA, aged ≥ 40 years and registered for ≥ 1 year before surgery. LASSO logistic regression models were developed for post-operative (90-day) mortality. A second mortality model was developed with a reduced feature set to increase interpretability and usability. RESULTS: A total of 193,615 patients were included, with 40,950 in The Health Improvement Network (THIN) database and 152,665 in Optum. The full model predicting 90-day mortality yielded AUROC of 0.78 when trained in OPTUM and 0.70 when externally validated on THIN. The 12 variable model achieved internal AUROC of 0.77 and external AUROC of 0.71 in THIN. CONCLUSIONS: A simple prediction model based on sex, age, and 10 comorbidities that can identify patients at high risk of short-term mortality following TKR was developed that demonstrated good, robust performance. The 12-feature mortality model is easily implemented and the performance suggests it could be used to inform evidence based shared decision-making prior to surgery and targeting prophylaxis for those at high risk. LEVEL OF EVIDENCE: III.

Improving visual communication of discriminative accuracy for predictive models: the probability threshold plot.

OBJECTIVES: To propose a visual display-the probability threshold plot (PTP)-that transparently communicates a predictive models' measures of discriminative accuracy along the range of model-based predicted probabilities (Pt). MATERIALS AND METHODS: We illustrate the PTP by replicating a previously-published and validated machine learning-based model to predict antihyperglycemic medication cessation within 1-2 years following metabolic surgery. The visual characteristics of the PTPs for each model were compared to receiver operating characteristic (ROC) curves. RESULTS: A total of 18 887 patients were included for analysis. Whereas during testing each predictive model had nearly identical ROC curves and corresponding area under the curve values (0.672 and 0.673), the visual characteristics of the PTPs revealed substantive between-model differences in sensitivity, specificity, PPV, and NPV across the range of Pt. DISCUSSION AND CONCLUSIONS: The PTP provides improved visual display of a predictive model's discriminative accuracy, which can enhance the practical application of predictive models for medical decision making.

Machine-learning model to predict the cause of death using a stacking ensemble method for observational data.

OBJECTIVE: Cause of death is used as an important outcome of clinical research; however, access to cause-of-death data is limited. This study aimed to develop and validate a machine-learning model that predicts the cause of death from the patient's last medical checkup. MATERIALS AND METHODS: To classify the mortality status and each individual cause of death, we used a stacking ensemble method. The prediction outcomes were all-cause mortality, 8 leading causes of death in South Korea, and other causes. The clinical data of study populations were extracted from the national claims (n = 174 747) and electronic health records (n = 729 065) and were used for model development and external validation. Moreover, we imputed the cause of death from the data of 3 US claims databases (n = 994 518, 995 372, and 407 604, respectively). All databases were formatted to the Observational Medical Outcomes Partnership Common Data Model. RESULTS: The generalized area under the receiver operating characteristic curve (AUROC) of the model predicting the cause of death within 60 days was 0.9511. Moreover, the AUROC of the external validation was 0.8887. Among the causes of death imputed in the Medicare Supplemental database, 11.32% of deaths were due to malignant neoplastic disease. DISCUSSION: This study showed the potential of machine-learning models as a new alternative to address the lack of access to cause-of-death data. All processes were disclosed to maintain transparency, and the model was easily applicable to other institutions. CONCLUSION: A machine-learning model with competent performance was developed to predict cause of death.

Medical Conditions Predictive of Self-Reported Poor Health: Retrospective Cohort Study.

BACKGROUND: Identifying the medical conditions that are associated with poor health is crucial to prioritize decisions for future research and organizing care. However, assessing the burden of disease in the general population is complex, lengthy, and expensive. Claims databases that include self-reported health status can be used to assess the impact of medical conditions on the health in a population. OBJECTIVE: This study aimed to identify medical conditions that are highly predictive of poor health status using claims databases. METHODS: To determine the medical conditions most highly predictive of poor health status, we used a retrospective cohort study using 2 US claims databases. Subjects were commercially insured patients. Health status was measured using a self-report health status response. All medical conditions were included in a least absolute shrinkage and selection operator regression model to assess which conditions were associated with poor versus excellent health. RESULTS: A total of 1,186,871 subjects were included; 61.64% (731,587/1,186,871) reported having excellent or very good health. The leading medical conditions associated with poor health were cancer-related conditions, demyelinating disorders, diabetes, diabetic complications, psychiatric illnesses (mood disorders and schizophrenia), sleep disorders, seizures, male reproductive tract infections, chronic obstructive pulmonary disease, cardiomyopathy, dementia, and headaches. CONCLUSIONS: Understanding the impact of disease in a commercially insured population is critical to identify subjects who may be at risk for reduced productivity and job loss. Claims database studies can measure the impact of medical conditions on the health status in a population and to assess changes overtime and could limit the need to collect prospective collection of information, which is slow and expensive, to assess disease burden. Leading medical conditions associated with poor health in a commercially insured population were the ones associated with high burden of disease such as cancer-related conditions, demyelinating disorders, diabetes, diabetic complications, psychiatric illnesses (mood disorders and schizophrenia), infections, chronic obstructive pulmonary disease, cardiomyopathy, and dementia. However, sleep disorders, seizures, male reproductive tract infections, and headaches were also part of the leading medical conditions associated with poor health that had not been identified before as being associated with poor health and deserve more attention.

Supplementing claims data analysis using self-reported data to develop a probabilistic phenotype model for current smoking status.

OBJECTIVES: Smoking status is poorly record in US claims data. IBM MarketScan Commercial is a claims database that can be linked to an additional health risk assessment with self-reported smoking status for a subset of 1,966,174 patients. We investigate whether this subset could be used to learn a smoking status phenotype model generalizable to all US claims data that calculates the probability of being a current smoker. METHODS: 251,643 (12.8%) had self-reported their smoking status as 'current smoker'. A regularized logistic regression model, the Current Risk of Smoking Status (CROSS), was trained using the subset of patients with self-reported smoking status. CROSS considered 53,027 candidate covariates including demographics and conditions/drugs/measurements/procedures/observations recorded in the prior 365 days, The CROSS phenotype model was validated across multiple other claims data. RESULTS: The internal validation showed the CROSS model achieved an area under the receiver operating characteristic curve (AUC) of 0.76 and the calibration plots indicated it was well calibrated. The external validation across three US claims databases obtained AUCs ranging between 0.82 and 0.87 showing the model appears to be transportable across Claims data. CONCLUSION: CROSS predicts current smoking status based on the claims records in the prior year. CROSS can be readily implemented to any US insurance claims mapped to the OMOP common data model and will be a useful way to impute smoking status when conducting epidemiology studies where smoking is a known confounder but smoking status is not recorded. CROSS is available from https://github.com/OHDSI/StudyProtocolSandbox/tree/master/SmokingModel.

Using Machine Learning Applied to Real-World Healthcare Data for Predictive Analytics: An Applied Example in Bariatric Surgery.

OBJECTIVES: Laparoscopic metabolic surgery (MxS) can lead to remission of type 2 diabetes (T2D); however, treatment response to MxS can be heterogeneous. Here, we demonstrate an open-source predictive analytics platform that applies machine-learning techniques to a common data model; we develop and validate a predictive model of antihyperglycemic medication cessation (validated proxy for A1c control) in patients with treated T2D who underwent MxS. METHODS: We selected patients meeting the following criteria in 2 large US healthcare claims databases (Truven Health MarketScan Commercial [CCAE]; Optum Clinformatics [Optum]): underwent MxS between January 1, 2007, to October 1, 2013 (first = index); aged ≥18 years; continuous enrollment 180 days pre-index (baseline) to 730 days postindex; baseline T2D diagnosis and treatment. The outcome was no antihyperglycemic medication treatment from 365 to 730 days after MxS. A regularized logistic regression model was trained using the following candidate predictor categories measured at baseline: demographics, conditions, medications, measurements, and procedures. A 75% to 25% split of the CCAE group was used for model training and testing; the Optum group was used for external validation. RESULTS: 13 050 (CCAE) and 3477 (Optum) patients met the study inclusion criteria. Antihyperglycemic medication cessation rates were 72.9% (CCAE) and 70.8% (Optum). The model possessed good internal discriminative accuracy (area under the curve [AUC] = 0.778 [95% CI = 0.761-0.795] in CCAE test set N = 3527) and transportability (external AUC = 0.759 [95% CI = 0.741-0.777] in Optum N = 3477). CONCLUSION: The application of machine learning techniques to real-world healthcare data can yield useful predictive models to assist patient selection. In future practice, establishment of prerequisite technological infrastructure will be needed to implement such models for real-world decision support.

Risk Factors for Interstitial Cystitis in the General Population and in Individuals With Depression.

PURPOSE: To identify risk factors for interstitial cystitis (IC), a chronic bladder disorder that may have a significant detrimental impact on quality of life, in the general population and in individuals with depression. METHODS: This was a comparative study using a US claims database. Adults who had records of a visit to the health system in 2010 or later were included. The outcome was the development of IC within 2 years after the index date. The index date for the general population was the first outpatient visit, and for individuals with depression, it was the date of the diagnosis of depression. IC was defined using the concepts of ulcerative and IC. We included all medical conditions present any time prior to the index visit as potential risk factors. RESULTS: The incidence of IC was higher in individuals with depression than in the general population. Of the 3,973,000 subjects from the general population, 2,293 (0.06%) developed IC within 2 years. Of the 249,200 individuals with depression, 320 (0.13%) developed IC. The characteristics of the individuals who developed IC were similar in both populations. Those who developed IC were slightly older, more likely to be women, and had more chronic pain conditions, malaise, and inflammatory disorders than patients without IC. In the general population, subjects who developed IC were more likely to have mood disorders, anxiety, and hypothyroidism. CONCLUSION: The incidence of IC was higher in individuals with depression. Subjects who developed IC had more chronic pain conditions, depression, malaise, and inflammatory disorders.

A signalome screening approach in the autoinflammatory disease TNF receptor associated periodic syndrome (TRAPS) highlights the anti-inflammatory properties of drugs for repurposing.

TNF receptor associated periodic syndrome (TRAPS) is an autoinflammatory disease caused by mutations in TNF Receptor 1 (TNFR1). Current therapies for TRAPS are limited and do not target the pro-inflammatory signalling pathways that are central to the disease mechanism. Our aim was to identify drugs for repurposing as anti-inflammatories based on their ability to down-regulate molecules associated with inflammatory signalling pathways that are activated in TRAPS. This was achieved using rigorously optimized, high through-put cell culture and reverse phase protein microarray systems to screen compounds for their effects on the TRAPS-associated inflammatory signalome. 1360 approved, publically available, pharmacologically active substances were investigated for their effects on 40 signalling molecules associated with pro-inflammatory signalling pathways that are constitutively upregulated in TRAPS. The drugs were screened at four 10-fold concentrations on cell lines expressing both wild-type (WT) TNFR1 and TRAPS-associated C33Y mutant TNFR1, or WT TNFR1 alone; signalling molecule levels were then determined in cell lysates by the reverse-phase protein microarray. A novel mathematical methodology was developed to rank the compounds for their ability to reduce the expression of signalling molecules in the C33Y-TNFR1 transfectants towards the level seen in the WT-TNFR1 transfectants. Seven high-ranking drugs were selected and tested by RPPA for effects on the same 40 signalling molecules in lysates of peripheral blood mononuclear cells (PBMCs) from C33Y-TRAPS patients compared to PBMCs from normal controls. The fluoroquinolone antibiotic lomefloxacin, as well as others from this class of compounds, showed the most significant effects on multiple pro-inflammatory signalling pathways that are constitutively activated in TRAPS; lomefloxacin dose-dependently significantly reduced expression of 7/40 signalling molecules across the Jak/Stat, MAPK, NF-κB and PI3K/AKT pathways. This study demonstrates the power of signalome screening for identifying candidates for drug repurposing.

Comparing stochastic differential equations and agent-based modelling and simulation for early-stage cancer.

There is great potential to be explored regarding the use of agent-based modelling and simulation as an alternative paradigm to investigate early-stage cancer interactions with the immune system. It does not suffer from some limitations of ordinary differential equation models, such as the lack of stochasticity, representation of individual behaviours rather than aggregates and individual memory. In this paper we investigate the potential contribution of agent-based modelling and simulation when contrasted with stochastic versions of ODE models using early-stage cancer examples. We seek answers to the following questions: (1) Does this new stochastic formulation produce similar results to the agent-based version? (2) Can these methods be used interchangeably? (3) Do agent-based models outcomes reveal any benefit when compared to the Gillespie results? To answer these research questions we investigate three well-established mathematical models describing interactions between tumour cells and immune elements. These case studies were re-conceptualised under an agent-based perspective and also converted to the Gillespie algorithm formulation. Our interest in this work, therefore, is to establish a methodological discussion regarding the usability of different simulation approaches, rather than provide further biological insights into the investigated case studies. Our results show that it is possible to obtain equivalent models that implement the same mechanisms; however, the incapacity of the Gillespie algorithm to retain individual memory of past events affects the similarity of some results. Furthermore, the emergent behaviour of ABMS produces extra patters of behaviour in the system, which was not obtained by the Gillespie algorithm.