Derivation Dataset Research Articles

Clinical validated risk prediction model for development of heart failure after contemporary breast cancer treatment

Abstract Background Patients receiving breast cancer (BC) treatment are at risk for heart failure and cardiomyopathy (HF/CM). European Society of Cardiology (ESC) cardio-oncology guidelines recommend baseline cardiovascular (CV) assessment, however, there is limited data about cardiotoxicity risk specific to patients with BC. Our aim was to develop and validate model for prediction of HF/CM in women receiving contemporary treatment for invasive early-stage BC. Methods We assembled a cohort women diagnosed with Stage I-III BC from 2008-2020 and followed through 2021 in a large health care plan. Women age >80, with history of HF/CM, and women who received both anthracyclines and trastuzumab were excluded, leaving N=26,044 for analysis. Study cohort was randomly split into derivation (60%) and validation (40%) datasets. Elastic-net penalized Cox proportional hazard model was created using the derivation dataset to select risk factors and to calculate the panelized coefficient which defined the HF/CM risk score. Risk score system was assessed by Hosmer-Lemeshow goodness-of-fit test and area under the ROC curve (AUC). Event rates of <5% constituted low risk; 5-14% moderate; and >15% high risk category. Incident HF/CM events were examined using Kaplan-Meier approach in derivation and validation datasets. Results HF/CM risk score had high discrimination ability and sufficiently good model of fit regarding HF/CM events (P value=0.163 and 0.667 from Hosmer–Lemeshow test;AUC 0.751 and 0.764, in derivation and validation sets, respectively). There were 10% of women in the high risk; 30% in moderate; and 60% in low-risk group. Variables associated with the higher HF/CM risk score included age, receipt of anthracycline-based chemotherapy or anti-HER2 therapy, presence of hypertension, diabetes, or history of other CV conditions at baseline. The score pattern showed major effect of age, with anthracycline and anti-HER2 therapy increasing the risk across all age groups (Figure 1). Kaplan-Meier analysis of incident HF/CM over 14 years after BC diagnosis showed significantly lower number of HF/CM events in low risk compared to moderate and high-risk score groups (p<0.0001, Figure 2). Conclusion Our robust risk prediction model for HF/CM among women with early-stage BC provides a new tool to identify women at higher CV risk and inform cardiac function monitoring during and after BC treatment. Our findings may guide further validation studies and build evidence for the cardiotoxicity risk stratification in patients with BC.Risk Score for HF/CM by Age/ChemoTxK-M curves of freedom from HF/CM

OSTEO18, a novel urinary proteomic signature, associated with osteoporosis in heart transplant recipients

Abstract Background Immunosuppressive treatment in heart transplant (HTx) recipient causes osteoporosis. The urinary proteomic profile (UPP) includes peptide fragments derived from the bone extracellular matrix. Purpose Study aims were to develop and validate a multidimensional UPP biomarker for osteoporosis in HTx patients from single sequenced urinary peptides identifying the parent proteins. Methods A single-center HTx cohort was analyzed. Urine samples were measured by capillary electrophoresis coupled with mass spectrometry. Cases with osteoporosis and matching controls were randomly selected from all available 389 patients. In derivation case-control dataset, 1576 sequenced peptides detectable in ≥30% of patients. Applying statistical analysis on these, an 18-peptide multidimensional osteoporosis UPP biomarker (OSTEO18) was generated by support vector modeling. The 2 replication datasets included 118 and 94 patients. For further validation, the whole cohort was analyzed. Statistical methods included logistic regression and receiver operating characteristic curve (ROC) analysis. Results In derivation dataset, the AUC, sensitivity and specificity of OSTEO18 were 0.83 (95% CI: 0.76-0.90), 74.3% and 87.1%, respectively. In replication datasets, results were confirmatory. In the whole cohort (154 osteoporotic patients [39.6%]), the ORs for osteoporosis increased (p < 0.0001) across OSTEO18 quartiles from 0.39 (95% CI: 0.25-0.61) to 3.14 (2.08-4.75). With full adjustment for known osteoporosis risk factors, OSTEO18 improved AUC from 0.708 to 0.786 (p = 0.0003) for OSTEO18 categorized (optimized threshold: 0.095) and to 0.784 (p = 0.0004) for OSTEO18 as continuously distributed classifier. Conclusion OSTEO18 is a clinically meaningful novel biomarker indicative of osteoporosis in HTx recipients and is being certified as in-vitro diagnostic.

Development of a CVD mortality risk score using nutritional predictors: A risk prediction model in the Golestan Cohort Study

Background and AimWe aimed to develop a dietary score using prediction model method for evaluating the risk of cardiovascular disease (CVD) mortality and suggesting a simple and practical scoring system within the healthcare context. Method and ResultsA total of 43878 adult participants (aged 37-80 years) from the Golestan Cohort Study (GCS) were included in analysis. A random split of the subjects into the derivation (n=28930) and the validation sets (n=14948) was done. The Cox proportional hazard model was used to develop prediction model for the 8-year risk of CVD mortality. The model’s discrimination and calibration were assessed by C-statistic and calibration plot, respectively. To enhance clinical utility, we devised a point-based scoring system derived from our model. This prediction model was developed by nine predictors including age, physical activity level (MET minutes/week), waist-to-hip ratio, tea intake (cup/day), vegetable intake (gr/1000 kcal/day), white meat intake (gr/1000 kcal/day), salt intake (gr/1000 kcal/day), dairy intake (Cup/1000 kcal/day), and percentage of protein intake. The model had an acceptable discrimination in both derivation (C-statistic: 0.76, p<0.001) and validation (C- statistic: 0.77, p<0.001) samples. Also, the calibration of model in both derivation and validation datasets was 0.81. ConclusionThis is the first attempt to develop a risk prediction model of CVD mortality and the risk scoring system by the majority of nutritional predictors in a large cohort study. This nutritional risk assessment tool is suitable for motivating at-risk individuals to make lifestyle and dietary pattern changes to reduce future risk to prevent health problems.

Development and validation of a preliminary multivariable diagnostic model for identifying unusual infections in hospitalized patients.

Diagnostic delay leads to poor outcomes in infections, and it occurs more often when the causative agent is unusual. Delays are attributable to failing to consider such diagnoses in a timely fashion. Using routinely collected electronic health record (EHR) data, we built a preliminary multivariable diagnostic model for early identification of unusual fungal infections and tuberculosis in hospitalized patients. We conducted a two-gate case-control study. Cases encompassed adult patients admitted to 19 Mayo Clinic enterprise hospitals between January 2010 and March 2023 diagnosed with blastomycosis, cryptococcosis, histoplasmosis, mucormycosis, pneumocystosis, or tuberculosis. Control groups were drawn from all admitted patients (random controls) and those with community-acquired infections (ID-controls). Development and validation datasets were created using randomization for dividing cases and controls (7:3), with a secondary validation using ID-controls. A logistic regression model was constructed using baseline and laboratory variables, with the unusual infections of interest outcome. The derivation dataset comprised 1043 cases and 7000 random controls, while the 451 cases were compared to 3000 random controls and 1990 ID-controls for validation. Within the derivation dataset, the model achieved an area under the curve (AUC) of 0.88 (95% confidence interval [CI]: 0.87-0.89) with a good calibration accuracy (Hosmer-Lemeshow P = 0.623). Comparable performance was observed in the primary (AUC = 0.88; 95% CI: 0.86-0.9) and secondary validation datasets (AUC = 0.84; 95% CI: 0.82-0.86). In this multicenter study, an EHR-based preliminary diagnostic model accurately identified five unusual fungal infections and tuberculosis in hospitalized patients. With further validation, this model could help decrease time to diagnosis.

Comparison of machine-learning and logistic regression models for prediction of 30-day unplanned readmission in electronic health records: A development and validation study.

It is expected but unknown whether machine-learning models can outperform regression models, such as a logistic regression (LR) model, especially when the number and types of predictor variables increase in electronic health records (EHRs). We aimed to compare the predictive performance of gradient-boosted decision tree (GBDT), random forest (RF), deep neural network (DNN), and LR with the least absolute shrinkage and selection operator (LR-LASSO) for unplanned readmission. We used EHRs of patients discharged alive from 38 hospitals in 2015-2017 for derivation and in 2018 for validation, including basic characteristics, diagnosis, surgery, procedure, and drug codes, and blood-test results. The outcome was 30-day unplanned readmission. We created six patterns of data tables having different numbers of binary variables (that ≥5% or ≥1% of patients or ≥10 patients had) with and without blood-test results. For each pattern of data tables, we used the derivation data to establish the machine-learning and LR models, and used the validation data to evaluate the performance of each model. The incidence of outcome was 6.8% (23,108/339,513 discharges) and 6.4% (7,507/118,074 discharges) in the derivation and validation datasets, respectively. For the first data table with the smallest number of variables (102 variables that ≥5% of patients had, without blood-test results), the c-statistic was highest for GBDT (0.740), followed by RF (0.734), LR-LASSO (0.720), and DNN (0.664). For the last data table with the largest number of variables (1543 variables that ≥10 patients had, including blood-test results), the c-statistic was highest for GBDT (0.764), followed by LR-LASSO (0.755), RF (0.751), and DNN (0.720), suggesting that the difference between GBDT and LR-LASSO was small and their 95% confidence intervals overlapped. In conclusion, GBDT generally outperformed LR-LASSO to predict unplanned readmission, but the difference of c-statistic became smaller as the number of variables was increased and blood-test results were used.

Development and validation of a COVID-19 vaccination prediction model based on self-reporting results in Chinese older adults from September 2022 to November 2022: A nationwide cross-sectional study

ABSTRACT It was common to see that older adults were reluctant to be vaccinated for coronavirus disease 2019 (COVID-19) in China. There is a lack of practical prediction models to guide COVID-19 vaccination program. A nationwide, self-reported, cross-sectional survey was conducted from September 2022 to November 2022, including people aged 60 years or older. Stratified random sampling was used to divide the dataset into derivation, validation, and test datasets at a ratio of 6:2:2. Least absolute shrinkage and selection operator and multivariable logistic regression were used for variable screening and model construction. Discrimination and calibration were assessed primarily by area under the receiver operating characteristic curve (AUC) and calibration curve. A total of 35057 samples (53.65% males and mean age of 69.64 ± 7.24 years) were finally selected, which constitutes 93.73% of the valid samples. From 33 potential predictors, 19 variables were screened and included in the multivariable logistic regression model. The mean AUC in the validation dataset was 0.802, with sensitivity, specificity, and accuracy of 0.732, 0.718 and 0.729 respectively, which were similar to the parameters in the test dataset of 0.755, 0.715 and 0.720, respectively, and the mean AUC in the test dataset was 0.815. There were no significant differences between the model predicted values and the actual observed values for calibration in these groups. The prediction model based on self-reported characteristics of older adults was developed that could be useful for predicting the willingness for COVID-19 vaccines, as well as providing recommendations in improving vaccine acceptance.

Structural and Physicochemical Features of Oral PROTACs.

Achieving oral bioavailability with Proteolysis Targeting Chimeras (PROTACs) is a key challenge. Here, we report the in vivo pharmacokinetic properties in mouse, rat, and dog of four clinical oral PROTACs and compare with an internally derived data set. We use NMR to determine 3D molecular conformations and structural preorganization free in solution, and we introduce the new experimental descriptors, solvent-exposed H-bond donors (eHBD), and acceptors (eHBA). We derive an upper limit of eHBD ≤ 2 for oral PROTACs in apolar environments and show a greater tolerance for other properties (eHBA, polarity, lipophilicity, and molecular weight) than for Rule-of-5 compliant oral drugs. Within a set of structurally related PROTACs, we show that examples with eHBD > 2 have much lower oral bioavailability than those that have eHBD ≤ 2. We summarize our findings as an experimental "Rule-of-oral-PROTACs" in order to assist medicinal chemists to achieve oral bioavailability in this challenging space.

Development and validation of a Non-INvaSive Pregnancy RIsk ScoRE (INSPIRE) for the screening of high-risk pregnant women for gestational diabetes mellitus in Pakistan

IntroductionThe prevalence of gestational diabetes mellitus (GDM) is on the rise in low-income and middle-income countries, such as Pakistan. Therefore, the development of a risk score that is simple, affordable...

Development and validation of an interpretable model for predicting sepsis mortality across care settings

There are numerous prognostic predictive models for evaluating mortality risk, but current scoring models might not fully cater to sepsis patients’ needs. This study developed and validated a new model for sepsis patients that is suitable for any care setting and accurately forecasts 28-day mortality. The derivation dataset, gathered from 20 hospitals between September 2019 and December 2021, contrasted with the validation dataset, collected from 15 hospitals from January 2022 to December 2022. In this study, 7436 patients were classified as members of the derivation dataset, and 2284 patients were classified as members of the validation dataset. The point system model emerged as the optimal model among the tested predictive models for foreseeing sepsis mortality. For community-acquired sepsis, the model’s performance was satisfactory (derivation dataset AUC: 0.779, 95% CI 0.765–0.792; validation dataset AUC: 0.787, 95% CI 0.765–0.810). Similarly, for hospital-acquired sepsis, it performed well (derivation dataset AUC: 0.768, 95% CI 0.748–0.788; validation dataset AUC: 0.729, 95% CI 0.687–0.770). The calculator, accessible at https://avonlea76.shinyapps.io/shiny_app_up/, is user-friendly and compatible. The new predictive model of sepsis mortality is user-friendly and satisfactorily forecasts 28-day mortality. Its versatility lies in its applicability to all patients, encompassing both community-acquired and hospital-acquired sepsis.

Estimating risk for pancreatic cancer among 9.4 million veterans in care.

10544 Background: Screening for pancreatic ductal adenocarcinoma (PDAC) has focused on individuals with a hereditary component, accounting for only 10% of PDAC events. Using the electronic health record, we developed a PDAC risk prediction model in a general population in the Veterans Health Administration (VA), the largest integrated health system in the US. Methods: We included all individuals from 2002- 2021 with ≥1 inpatient or outpatient VA encounter and recorded race, starting follow-up 1.5 years after first VA encounter. We excluded those who developed PDAC before start of follow-up. We used the multivariable Cox proportional hazards model in the derivation dataset (random 70% of cohort) to estimate the coefficients associated with each predictor for our outcome, time to PDAC (3 and 10 years), censoring at loss to follow-up or 12/31/2021. Candidate predictors included age, gender, race/ethnicity, sex, BMI, smoking status, alcohol use (alcohol use/related disorders and AUDIT-C), diabetes, pancreatitis, Hepatitis C, HIV, liver disease, cholecystectomy, pancreatic cysts, Charlson comorbidity index and common laboratory values. Selection of predictors was based on clinical reasoning, extent of missing values and model fit (Akaike Information Criterion and Harrell’s c–statistic). We evaluated model discrimination using c – statistic and model calibration comparing observed Kaplan – Meier estimated incidence vs. predicted risk score. Results: Among 9.4 million individuals, we observed 19,839 cases of PDAC within 10 years (6,022 cases within 3 years). Median baseline age was 58.5 years, 75.0% were White, and 16.3% were Black. Final predictors included age, gender, smoking, alcohol use (alcohol use/related disorders and AUDIT-C), BMI, diabetes, pancreatitis, pancreatic cyst, and history of cancer (Table, c-statistic in the derivation cohort 3 years: 0.79; 10 years: 0.77). Ten-year risk ranged maximally from 0-5.5%. Preliminary studies suggest labs do not clinically improve model performance. Conclusions: We developed a novel prediction model using available clinical data in a general population that identifies PDAC with high accuracy. Future work will try to identify additional predictors to improve the range of risk predicted. We will validate our findings in the testing set and in external cohorts. [Table: see text]

Biomarkers to improve functional outcome prediction after ischemic stroke: Results from the SICFAIL, STRAWINSKI, and PREDICT studies.

Acute ischemic stroke (AIS) outcome prognostication remains challenging despite available prognostic models. We investigated whether a biomarker panel improves the predictive performance of established prognostic scores. We investigated the improvement in discrimination, calibration, and overall performance by adding five biomarkers (procalcitonin, copeptin, cortisol, mid-regional pro-atrial natriuretic peptide (MR-proANP), and N-terminal pro-B-type natriuretic peptide (NT-proBNP)) to the Acute Stroke Registry and Analysis of Lausanne (ASTRAL) and age/NIHSS scores using data from two prospective cohort studies (SICFAIL, PREDICT) and one clinical trial (STRAWINSKI). Poor outcome was defined as mRS > 2 at 12 (SICFAIL, derivation dataset) or 3 months (PREDICT/STRAWINSKI, pooled external validation dataset). Among 412 SICFAIL participants (median age 70 years, quartiles 59-78; 63% male; median NIHSS score 3, quartiles 1-5), 29% had a poor outcome. Area under the curve of the ASTRAL and age/NIHSS were 0.76 (95% CI 0.71-0.81) and 0.77 (95% CI 0.73-0.82), respectively. Copeptin (0.79, 95% CI 0.74-0.84), NT-proBNP (0.80, 95% CI 0.76-0.84), and MR-proANP (0.79, 95% CI 0.75-0.84) significantly improved ASTRAL score's discrimination, calibration, and overall performance. Copeptin improved age/NIHSS model's discrimination, copeptin, MR-proANP, and NT-proBNP improved its calibration and overall performance. In the validation dataset (450 patients, median age 73 years, quartiles 66-81; 54% men; median NIHSS score 8, quartiles 3-14), copeptin was independently associated with various definitions of poor outcome and also mortality. Copeptin did not increase model's discrimination but it did improve calibration and overall model performance. Copeptin, NT-proBNP, and MR-proANP improved modest but consistently the predictive performance of established prognostic scores in patients with mild AIS. Copeptin was most consistently associated with poor outcome in patients with moderate to severe AIS, although its added prognostic value was less obvious.

A COVID-19 specific multiparametric and ECG-based score for the prediction of in-hospital mortality: ELCOVID score.

We aimed to develop and validate a COVID-19 specific scoring system, also including some ECG features, to predict all-cause in-hospital mortality at admission. Patients were retrieved from the ELCOVID study (ClinicalTrials.gov identifier: NCT04367129), a prospective, multicenter Italian study enrolling COVID-19 patients between May to September 2020. For the model validation, we randomly selected two-thirds of participants to create a derivation dataset and we used the remaining one-third of participants as the validation set. Over the study period, 1014 hospitalized COVID-19 patients (mean age 74years, 61% males) met the inclusion criteria and were included in this analysis. During a median follow-up of 12 (IQR 7-22) days, 359 (35%) patients died. Age (HR 2.25 [95%CI 1.72-2.94], p < 0.001), delirium (HR 2.03 [2.14-3.61], p = 0.012), platelets (HR 0.91 [0.83-0.98], p = 0.018), D-dimer level (HR 1.18 [1.01-1.31], p = 0.002), signs of right ventricular strain (RVS) (HR 1.47 [1.02-2.13], p = 0.039) and ECG signs of previous myocardial necrosis (HR 2.28 [1.23-4.21], p = 0.009) were independently associated to in-hospital all-cause mortality. The derived risk-scoring system, namely EL COVID score, showed a moderate discriminatory capacity and good calibration. A cut-off score of ≥ 4 had a sensitivity of 78.4% and 65.2% specificity in predicting all-cause in-hospital mortality. ELCOVID score represents a valid, reliable, sensitive, and inexpensive scoring system that can be used for the prognostication of COVID-19 patients at admission and may allow the earlier identification of patients having a higher mortality risk who may be benefit from more aggressive treatments and closer monitoring.

Prognostic performance of MRI LI-RADS version 2018 features and clinical-pathological factors in alpha-fetoprotein-negative hepatocellular carcinoma.

To evaluate the role of the magnetic resonance imaging (MRI) Liver Imaging Reporting and Data System (LI-RADS) version 2018 features and clinical-pathological factors for predicting the prognosis of alpha-fetoprotein (AFP)-negative (≤ 20ng/ml) hepatocellular carcinoma (HCC) patients, and to compare with other traditional staging systems. We retrospectively enrolled 169 patients with AFP-negative HCC who received preoperative MRI and hepatectomy between January 2015 and August 2020 (derivation dataset:validation dataset = 118:51). A prognostic model was constructed using the risk factors identified via Cox regression analysis. Predictive performance and discrimination capability were evaluated and compared with those of two traditional staging systems. Six risk factors, namely the LI-RADS category, blood products in mass, microvascular invasion, tumor size, cirrhosis, and albumin-bilirubin grade, were associated with recurrence-free survival. The prognostic model constructed using these factors achieved C-index of 0.705 and 0.674 in the derivation and validation datasets, respectively. Furthermore, the model performed better in predicting patient prognosis than traditional staging systems. The model effectively stratified patients with AFP-negative HCC into high- and low-risk groups with significantly different outcomes (p < 0.05). A prognostic model integrating the LI-RADS category, blood products in mass, microvascular invasion, tumor size, cirrhosis, and albumin-bilirubin grade may serve as a valuable tool for refining risk stratification in patients with AFP-negative HCC.

Risk calculator for incident atrial fibrillation across a range of prediction horizons

The increasing burden of atrial fibrillation (AF) emphasizes the need to identify high-risk individuals for enrolment in clinical trials of AF screening and primary prevention. We aimed to develop prediction models to identify individuals at high-risk of AF across prediction horizons from 6-months to 10-years. We used secondary-care linked primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between January 2, 1998 and November 30, 2018; randomly divided into derivation (80%) and validation (20%) datasets. Models were derived using logistic regression from known AF risk factors for incident AF in prediction periods of 6 months, 1-year, 2-years, 5-years, and 10-years. Performance was evaluated using in the validation dataset with bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc and C2HEST scores. Of 2,081,139 individuals in the cohort (1,664,911 in the development dataset, 416,228 in the validation dataset), the mean age was 49.9 (SD 15.4), 50.7% were women, and 86.7% were white. New cases of AF were 7,386 (0.4%) within 6 months, 15,349 (0.7%) in 1 year, 38,487 (1.8%) in 5 years, and 79,997 (3.8%) by 10 years. Valvular heart disease and heart failure were the strongest predictors, and association of hypertension with AF increased at longer prediction horizons. The optimal risk models incorporated age, sex, ethnicity, and 8 comorbidities. The models demonstrated good-to-excellent discrimination and strong calibration across prediction horizons (AUROC, 95%CI, calibration slope: 6-months, 0.803, 0.789-0.821, 0.952; 1-year, 0.807, 0.794-0.819, 0.962; 2-years, 0.815, 0.807-0.823, 0.973; 5-years, 0.807, 0.803-0.812, 1.000; 10-years 0.780, 0.777-0.784, 1.010), and superior to the CHA2DS2-VASc and C2HEST scores. The models are available as a web-based FIND-AF calculator. The FIND-AF models demonstrate high discrimination and calibration across short- and long-term prediction horizons in 2 million individuals. Their utility to inform trial enrolment and clinical decisions for AF screening and primary prevention requires further study.

Catheterization for Congenital Heart Disease Adjustment for Risk Method II.

Current metrics used to adjust for case mix complexity in congenital cardiac catheterization are becoming outdated due to the introduction of novel procedures, innovative technologies, and expanding patient subgroups. This study aims to develop a risk adjustment methodology introducing a novel, clinically meaningful adverse event outcome and incorporating a modern understanding of risk. Data from diagnostic only and interventional cases with defined case types were collected for patients ≤18 years of age and ≥2.5 kg at all Congenital Cardiac Catheterization Project on Outcomes participating centers. The derivation data set consisted of cases performed from 2014 to 2017, and the validation data set consisted of cases performed from 2019 to 2020. Severity level 3 adverse events were stratified into 3 tiers by clinical impact (3a/b/c); the study outcome was clinically meaningful adverse events, severity level ≥3b (3bc/4/5). The derivation data set contained 15 224 cases, and the validation data set included 9462 cases. Clinically meaningful adverse event rates were 4.5% and 4.2% in the derivation and validation cohorts, respectively. The final risk adjustment model included age <30 days, Procedural Risk in Congenital Cardiac Catheterization risk category, and hemodynamic vulnerability score (C statistic, 0.70; Hosmer-Lemeshow P value, 0.83; Brier score, 0.042). CHARM II (Congenital Heart Disease Adjustment for Risk Method II) risk adjustment methodology allows for equitable comparison of clinically meaningful adverse events among institutions and operators with varying patient populations and case mix complexity performing pediatric cardiac catheterization.

HyperPCM: Robust Task-Conditioned Modeling of Drug-Target Interactions.

A central problem in drug discovery is to identify the interactions between drug-like compounds and protein targets. Over the past few decades, various quantitative structure-activity relationship (QSAR) and proteo-chemometric (PCM) approaches have been developed to model and predict these interactions. While QSAR approaches solely utilize representations of the drug compound, PCM methods incorporate both representations of the protein target and the drug compound, enabling them to achieve above-chance predictive accuracy on previously unseen protein targets. Both QSAR and PCM approaches have recently been improved by machine learning and deep neural networks, that allow the development of drug-target interaction prediction models from measurement data. However, deep neural networks typically require large amounts of training data and cannot robustly adapt to new tasks, such as predicting interaction for unseen protein targets at inference time. In this work, we propose to use HyperNetworks to efficiently transfer information between tasks during inference and thus to accurately predict drug-target interactions on unseen protein targets. Our HyperPCM method reaches state-of-the-art performance compared to previous methods on multiple well-known benchmarks, including Davis, DUD-E, and a ChEMBL derived data set, and particularly excels at zero-shot inference involving unseen protein targets. Our method, as well as reproducible data preparation, is available at https://github.com/ml-jku/hyper-dti.

Creating a Modified Version of the Cambridge Multimorbidity Score to Predict Mortality in People Older Than 16 Years: Model Development and Validation.

No single multimorbidity measure is validated for use in NHS (National Health Service) England's General Practice Extraction Service Data for Pandemic Planning and Research (GDPPR), the nationwide primary care data set created for COVID-19 pandemic research. The Cambridge Multimorbidity Score (CMMS) is a validated tool for predicting mortality risk, with 37 conditions defined by Read Codes. The GDPPR uses the more internationally used Systematized Nomenclature of Medicine clinical terms (SNOMED CT). We previously developed a modified version of the CMMS using SNOMED CT, but the number of terms for the GDPPR data set is limited making it impossible to use this version. We aimed to develop and validate a modified version of CMMS using the clinical terms available for the GDPPR. We used pseudonymized data from the Oxford-Royal College of General Practitioners Research and Surveillance Centre (RSC), which has an extensive SNOMED CT list. From the 37 conditions in the original CMMS model, we selected conditions either with (1) high prevalence ratio (≥85%), calculated as the prevalence in the RSC data set but using the GDPPR set of SNOMED CT codes, divided by the prevalence included in the RSC SNOMED CT codes or (2) conditions with lower prevalence ratios but with high predictive value. The resulting set of conditions was included in Cox proportional hazard models to determine the 1-year mortality risk in a development data set (n=500,000) and construct a new CMMS model, following the methods for the original CMMS study, with variable reduction and parsimony, achieved by backward elimination and the Akaike information stopping criterion. Model validation involved obtaining 1-year mortality estimates for a synchronous data set (n=250,000) and 1-year and 5-year mortality estimates for an asynchronous data set (n=250,000). We compared the performance with that of the original CMMS and the modified CMMS that we previously developed using RSC data. The initial model contained 22 conditions and our final model included 17 conditions. The conditions overlapped with those of the modified CMMS using the more extensive SNOMED CT list. For 1-year mortality, discrimination was high in both the derivation and validation data sets (Harrell C=0.92) and 5-year mortality was slightly lower (Harrell C=0.90). Calibration was reasonable following an adjustment for overfitting. The performance was similar to that of both the original and previous modified CMMS models. The new modified version of the CMMS can be used on the GDPPR, a nationwide primary care data set of 54 million people, to enable adjustment for multimorbidity in predicting mortality in people in real-world vaccine effectiveness, pandemic planning, and other research studies. It requires 17 variables to produce a comparable performance with our previous modification of CMMS to enable it to be used in routine data using SNOMED CT.

Osteoporosis in Relation to a Bone-Related Aging Biomarker Derived from the Urinary Proteomic Profile: A Population Study.

Screening for and prevention of osteoporosis and osteoporotic fractures is imperative, given the high burden on individuals and society. This study constructed and validated an aging-related biomarker derived from the urinary proteomic profile (UPP) indicative of osteoporosis (UPPost-age). In a prospective population study done in northern Belgium (1985-2019), participants were invited for a follow-up examination in 2005-2010 and participants in the 2005-2010 examination again invited in 2009-2013. Participants in both the 2005-2010 and 2009-2013 examinations (n = 519) constituted the derivation (2005-2016 data) and time-shifted validation (2009-2013 data) datasets; 187 participants with only 2005-2010 data formed the synchronous validation dataset. The UPP was assessed by capillary electrophoresis coupled with mass spectrometry. Analyses focused on 2372 sequenced urinary peptides (101 proteins) with key roles in maintaining the integrity of bone tissue. In multivariable analyses with correction for multiple testing, chronological age was associated with 99 urinary peptides (16 proteins). Peptides derived from IGF2 and MGP were upregulated in women compared to men, whereas COL1A2, COL3A1, COL5A2, COL10A1 and COL18A1 were downregulated. Via application of a 1000-fold bootstrapped elastic regression procedure, finally, 29 peptides (10 proteins) constituted the UPPost-age biomarker, replicated across datasets. In cross-sectional analyses of 2009-2013 data (n = 706), the body-height-to-arm-span ratio, an osteoporosis marker, was negatively associated with UPPost-age (p&;lt0.0001). Over 4.89 years (median), the 10-year risk of osteoporosis associated with chronological age and UPPost-age (53 cases including 37 fractures in 706 individuals) increased by 21% and 36% (p ≤ 0.044). Among 357 women, the corresponding estimates were 55% and 60% for incident osteoporosis (37 cases; p ≤ 0.0003) and 42% and 44% for osteoporotic fractures (25 cases; p ≤ 0.017). In conclusion, an aging-related UPP signature with focus on peptide fragments derived from bone-related proteins is associated with osteoporosis risk and available for clinical and trial research.

Sparse identification of dynamical systems by reweighted [formula omitted]-regularized least absolute deviation regression

This work proposes a generalized methodology for sparse identification of dynamical systems (SID), utilizing reweighted l1-regularized least absolute deviation (LAD) regression to recover the governing equation of dynamical systems. To programmatically implement the proposed method, a stabilized and efficient resolution scheme is developed by combining the solution method of the classical LAD-based least absolute shrinkage and selection operator (LAD-lasso) and the threshold iterative idea of the sequentially thresholded least-squares (STLS) method. The new method relaxes the assumption of normality for the error terms in the linear regression model employed by traditional SID techniques. Additionally, it overcomes the low identification accuracy deficiency of the recently proposed regularized least absolute deviation-based sparse identification of dynamics method (RLAD-SID) under some poor data conditions. The performance of the proposed approach is investigated by simulations of two well-known dynamical systems, that is, the Lorenz system and the Duffing system. The reliability of this approach in recovering the governing equation of dynamical systems from noise-contaminated datasets is firstly demonstrated. Furthermore, the advantage of the proposed method is illustrated by comparing it with four traditional techniques in relatively poor data environments. Finally, we display the robustness of the new method when the time derivative dataset is affected by different types of noise, and reveal its superiority compared to the traditional RLAD-SID.

Machine learning-based gait analysis to predict clinical frailty scale in elderly patients with heart failure.

Although frailty assessment is recommended for guiding treatment strategies and outcome prediction in elderly patients with heart failure (HF), most frailty scales are subjective, and the scores vary among raters. We sought to develop a machine learning-based automatic rating method/system/model of the clinical frailty scale (CFS) for patients with HF. We prospectively examined 417 elderly (≥75 years) with symptomatic chronic HF patients from 7 centres between January 2019 and October 2023. The patients were divided into derivation (n = 194) and validation (n = 223) cohorts. We obtained body-tracking motion data using a deep learning-based pose estimation library, on a smartphone camera. Predicted CFS was calculated from 128 key features, including gait parameters, using the light gradient boosting machine (LightGBM) model. To evaluate the performance of this model, we calculated Cohen's weighted kappa (CWK) and intraclass correlation coefficient (ICC) between the predicted and actual CFSs. In the derivation and validation datasets, the LightGBM models showed excellent agreements between the actual and predicted CFSs [CWK 0.866, 95% confidence interval (CI) 0.807-0.911; ICC 0.866, 95% CI 0.827-0.898; CWK 0.812, 95% CI 0.752-0.868; ICC 0.813, 95% CI 0.761-0.854, respectively]. During a median follow-up period of 391 (inter-quartile range 273-617) days, the higher predicted CFS was independently associated with a higher risk of all-cause death (hazard ratio 1.60, 95% CI 1.02-2.50) after adjusting for significant prognostic covariates. Machine learning-based algorithms of automatically CFS rating are feasible, and the predicted CFS is associated with the risk of all-cause death in elderly patients with HF.