Prognostic modelling with logistic regression analysis: a comparison of selection and estimation methods in small data sets

Development of a processing factor prediction model for pesticides in processed tomato foods using elastic net regularization

A novel regularized elastic net regression model was developed to predict processing factor (PF) for pesticide residues, which represents a change in the residue levels during food processing. The PF values for tomato juice, wet pomace and dry pomace in the evaluations and reports published by the Joint FAO/WHO Meeting on Pesticide Residues significantly correlated with the physicochemical properties of pesticides, and subsequently the correlation was observed in the present tomato processing study. The elastic net regression model predicted the PF values using the physicochemical properties as predictor variables for both training and test data within a 2-fold range for 80-100% of the pesticides tested in the tomato processing study while overcoming multicollinearity. These results suggest that the PF values are predictable at a certain degree of accuracy from the unique sets of physicochemical properties of pesticides using the developed model based on a processing study with representative pesticides.

Antibiotic Implant Irrigation and Deep Infection: A Retrospective Study of 1508 Patients Undergoing Breast Reconstruction with Implants

BACKGROUND

Antibiotic implant irrigation is increasingly used to prevent deep infection after implant-based breast reconstruction. However, there is limited evidence of the clinical effect. In this study, the authors compare the risk of a deep infection in a Danish population of women who received antibiotic implant irrigation with either gentamicin or vancomycin, or no irrigation.

METHODS

The authors retrospectively reviewed consecutive patients undergoing all types of breast reconstruction with implants at Rigshospitalet and Herlev Hospital, Denmark, from 2010 to 2019. Logistic regression was used to compare the risk of deep infection between no irrigation and irrigation with gentamicin or vancomycin, and to account for the difference in risk between patient subgroups and risk factors.

RESULTS

The authors included 1508 patients who received antibiotic irrigation with gentamicin (500 patients), vancomycin (304 patients), or no irrigation (704 patients). The univariable risk analysis showed a significant decreased risk of deep infection using gentamicin irrigation compared with no irrigation (OR, 0.58; P < 0.05). However, when adjusting for risk factors for infection, there was no significant decrease in the risk of infection when using gentamicin (OR, 0.90; P = 0.71) or vancomycin (OR, 1.0; P = 0.99) compared with the control group.

CONCLUSIONS

The authors found no significant effect of using antibiotic implant irrigation after isolating it from risk factors for deep infection. However, because of the limitations of the study, the authors cannot conclude that there is no effect of antibiotic implant irrigation. There is a need for a randomized, placebo-controlled trial to investigate the effect, and potential side-effects, of antibiotic implant irrigation.

CLINICAL QUESTION/LEVEL OF EVIDENCE

Risk, II.

Development and Validation of the GAASThyriC Model for Predicting Patients with Suboptimal Clinical Response After Laparoscopic Sleeve Gastrectomy and a Practical Calculator: A Retrospective Cohort Study

BACKGROUND

It might not be possible to achieve the desired outcome in every patient following bariatric surgery, even though every patient is thoroughly examined before surgery. This study aimed to develop a regression model based on parameters that affect weight loss success in patients scheduled for laparoscopic sleeve gastrectomy (LSG) and thus preoperatively predict whether the patients will have an optimal clinical response in terms of weight loss at the end of the first year.

MATERIALS AND METHODS

Between January 2018 and August 2022, patients who underwent LSG were analyzed retrospectively. Age, sex, comorbidities, smoking status, alcohol use status, preoperative weight, preoperative body mass index (BMI), preoperative laboratory data, weight, and total weight loss (TWL)% values at the end of the first year were recorded. At the end of the first year following LSG, patients with TWL% above 20% were defined as having an optimal clinical response in terms of weight loss. This study is designed, conducted, and reported regarding the "transparent reporting of a multivariable prediction model for individual prognosis or diagnosis" (TRIPOD) statement. The final model was used to construct an Excel-based calculator.

RESULTS

Four hundred thirty-eight patients underwent the sleeve gastrectomy procedure, and 38 of them were excluded from the study because of a lack of 1-year follow-up information, resulting in 400 eligible patients for our study. Age, glucose, thyroid stimulating hormone (TSH), alcohol consumption, systemic immune inflammation index (SII), and tobacco were the independent predictors of optimal clinical response (P<0.001, P<0.001, P<0.001, P=0.011, P=0.039, P=0.045, respectively). The model was called the GAASThyriC score. When the final model was tested in the validation cohort, the AUC was 0.875 (95% CI, 0.742-0.999), the sensitivity was 83.3% (95% CI, 51.6-97.9), specificity was 86.4% (95% CI, 77.4-92.8), negative likelihood ratio was 0.19 (95% CI, 0.05-0.68), and accuracy was 86% (95% CI, 77.6-92.1) when the cutoff value was set to the optimal threshold (logit = 0.8451).

CONCLUSION

The GAASThyriC score can be used as an effective auxiliary tool to predict the patient population with suboptimal clinical response in terms of TWL% at the end of the first year after LSG.

Prediction of developmental toxic effects of fine particulate matter (PM2.5) water-soluble components via machine learning through observation of PM2.5 from diverse urban areas

The global health implications of fine particulate matter (PM2.5) underscore the imperative need for research into its toxicity and chemical composition. In this study, zebrafish embryos exposed to the water-soluble components of PM2.5 from two cities (Harbin and Hangzhou) with differences in air quality, underwent microscopic examination to identify primary target organs. The Harbin PM2.5 induced dose-dependent organ malformation in zebrafish, indicating a higher level of toxicity than that of the Hangzhou sample. Harbin PM2.5 led to severe deformities such as pericardial edema and a high mortality rate, while the Hangzhou sample exhibited hepatotoxicity, causing delayed yolk sac absorption. The experimental determination of PM2.5 constituents was followed by the application of four algorithms for predictive toxicological assessment. The random forest algorithm correctly predicted each of the effect classes and showed the best performance, suggesting that zebrafish malformation rates were strongly correlated with water-soluble components of PM2.5. Feature selection identified the water-soluble ions F- and Cl- and metallic elements Al, K, Mn, and Be as potential key components affecting zebrafish development. This study provides new insights into the developmental toxicity of PM2.5 and offers a new approach for predicting and exploring the health effects of PM2.5.

An integrated radiology-pathology machine learning classifier for outcome prediction following radical prostatectomy: Preliminary findings

Objectives

To evaluate the added benefit of integrating features from pre-treatment MRI (radiomics) and digitized post-surgical pathology slides (pathomics) in prostate cancer (PCa) patients for prognosticating outcomes post radical-prostatectomy (RP) including a) rising prostate specific antigen (PSA), and b) extraprostatic-extension (EPE).

Methods

Multi-institutional data (N = 58) of PCa patients who underwent pre-treatment 3-T MRI prior to RP were included in this retrospective study. Radiomic and pathomic features were extracted from PCa regions on MRI and RP specimens delineated by expert clinicians. On training set (D1, N = 44), Cox Proportional-Hazards models MR, MP and MRaP were trained using radiomics, pathomics, and their combination, respectively, to prognosticate rising PSA (PSA > 0.03 ng/mL). Top features from MRaP were used to train a model to predict EPE on D1 and test on external dataset (D2, N = 14). C-index, Kalplan-Meier curves were used for survival analysis, and area under ROC (AUC) was used for EPE. MRaP was compared with the existing post-treatment risk-calculator, CAPRA (MC).

Results

Patients had median follow-up of 34 months. MRaP (c-index = 0.685 ± 0.05) significantly outperformed MR (c-index = 0.646 ± 0.05), MP (c-index = 0.631 ± 0.06) and MC (c-index = 0.601 ± 0.071) (p < 0.0001). Cross-validated Kaplan-Meier curves showed significant separation among risk groups for rising PSA for MRaP (p < 0.005, Hazard Ratio (HR) = 11.36) as compared to MR (p = 0.64, HR = 1.33), MP (p = 0.19, HR = 2.82) and MC (p = 0.10, HR = 3.05). Integrated radio-pathomic model MRaP (AUC = 0.80) outperformed MR (AUC = 0.57) and MP (AUC = 0.76) in predicting EPE on external-data (D2).

Conclusions

Results from this preliminary study suggest that a combination of radiomic and pathomic features can better predict post-surgical outcomes (rising PSA and EPE) compared to either of them individually as well as extant prognostic nomogram (CAPRA).

Environmental and Genetic Risk Factors in Developmental Dysplasia of the Hip for Early Detection of the Affected Population

Diagnosis of developmental dysplasia of the hip (DDH) mostly relies on physical examination and ultrasound, and both methods are operator-dependent. Late detection can lead to complications in young adults. Current evidence supports the involvement of environmental and genetic factors, such as single nucleotide variants (SNVs). Incorporating genetic factors into diagnostic methods would be useful for implementing early detection and management of affected individuals. Our aim was to analyze environmental factors and SNVs in DDH patients. We included 287 DDH cases and 284 controls. Logistic regression demonstrated an association for sex (OR 9.85, 95% CI 5.55-17.46, p = 0.0001), family history (OR 2.4, 95% CI 1.2-4.5, p = 0.006), fetal presentation (OR 3.19, 95% CI 1.55-6.54, p = 0.002), and oligohydramnios (OR 2.74, 95%CI 1.12-6.70, p = 0.026). A model predicting the risk of DDH including these variables showed sensitivity, specificity, PPV, and NPV of 0.91, 0.53, 0.74, and 0.80 respectively. The SNV rs1800470 in TGFB1 showed an association when adjusted for covariables, OR 0.49 (95% CI 0.27-0.90), p = 0.02. When rs1800470 was included in the equation, sensitivity, specificity, PPV and NPV were 0.90, 0.61, 0.84, and 0.73, respectively. Incorporating no-operator dependent variables and SNVs in detection methods could be useful for establishing uniform clinical guidelines and optimizing health resources.

A population health approach to workplace mental health: rationale, implementation and engagement

Objectives

To describe a population health-based program to support employee and dependent mental health and learn from engagement trends.

Methods

Retrospective analysis of a program utilizing an assessment of mental health risk. For scoring "at risk," a Care Concierge is offered to connect users with resources.

Results

Participation was offered to 56,442 employees and dependents. Eight thousand seven hundred thirty-one completed the assessment (15%). Of those, 4,644 (53%) scored moderate or higher. A total of 418 (9%) engaged the Care Concierge. Factors that negatively influenced the decision to engage care included bodily pain, financial concerns. Positive influences were younger age, high stress, anxiety, PTSD and low social support.

Conclusion

Proactive assessment plus access to a Care Concierge facilitates mental healthcare utilization. Several factors influence likelihood to engage in care. A better understanding of these factors may allow for more targeted outreach and improved engagement.

Effective sample size: A measure of individual uncertainty in predictions

Clinical prediction models are estimated using a sample of limited size from the target population, leading to uncertainty in predictions, even when the model is correctly specified. Generally, not all patient profiles are observed uniformly in model development. As a result, sampling uncertainty varies between individual patients' predictions. We aimed to develop an intuitive measure of individual prediction uncertainty. The variance of a patient's prediction can be equated to the variance of the sample mean outcome inn ∗ $$ {n}_{\ast } $$ hypothetical patients with the same predictor values. This hypothetical sample sizen ∗ $$ {n}_{\ast } $$ can be interpreted as the number of similar patientsn eff $$ {n}_{\mathrm{eff}} $$ that the prediction is effectively based on, given that the model is correct. For generalized linear models, we derived analytical expressions for the effective sample size. In addition, we illustrated the concept in patients with acute myocardial infarction. In model development,n eff $$ {n}_{\mathrm{eff}} $$ can be used to balance accuracy versus uncertainty of predictions. In a validation sample, the distribution ofn eff $$ {n}_{\mathrm{eff}} $$ indicates which patients were more and less represented in the development data, and whether predictions might be too uncertain for some to be practically meaningful. In a clinical setting, the effective sample size may facilitate communication of uncertainty about predictions. We propose the effective sample size as a clinically interpretable measure of uncertainty in individual predictions. Its implications should be explored further for the development, validation and clinical implementation of prediction models.

Incidence of T2DM and the role of baseline glycaemic status as a determinant in a metropolitan population in northern Madrid (Spain)

AIM

To estimate the incidence of T2DM and assess the effect of pre-T2DM (isolated impaired fasting glucose [iIFG], isolated impaired glucose tolerance [iIGT] or both) on progress to T2DM in the adult population of Madrid.

METHODS

Population-based cohort comprising 1,219 participants (560 normoglycaemic and 659 preT2DM [418 iIFG, 70 iIGT or 171 IFG-IGT]). T2DM was defined based on fasting plasma glucose or HbA1c or use of glucose-lowering medication. We used a Cox model with normoglycaemia as reference category.

RESULTS

During 7.26 years of follow-up, the unadjusted incidence of T2DM was 11.21 per 1000 person-years (95 %CI, 9.09-13.68) for the whole population, 5.60 (3.55-8.41) for normoglycaemic participants and 16.28 (12.78-20.43) for pre-T2DM participants. After controlling for potential confounding factors, the baseline glycaemic status was associated with higher primary effect on developing T2DM was iIGT (HR = 3.96 [95 %CI, 1.93-8.10]) and IFG-IGT (3.42 [1.92-6.08]). The HR for iIFG was 1.67 (0.96-2.90). Obesity, as secondary effect, was strongly significantly associated (HR = 2.50 [1.30-4.86]).

CONCLUSIONS

Our incidence of T2DM is consistent with that reported elsewhere in Spain. While baseline iIGT and IFG-IGT behaved a primary effect for progression to T2DM, iIFG showed a trend in this direction.

A blood-based multi-pathway biomarker assay for early detection and staging of Alzheimer's disease across ethnic groups

INTRODUCTION

Existing blood-based biomarkers for Alzheimer's disease (AD) mainly focus on its pathological features. However, studies on blood-based biomarkers associated with other biological processes for a comprehensive evaluation of AD status are limited.

METHODS

We developed a blood-based, multiplex biomarker assay for AD that measures the levels of 21 proteins involved in multiple biological pathways. We evaluated the assay's performance for classifying AD and indicating AD-related endophenotypes in three independent cohorts from Chinese or European-descent populations.

RESULTS

The 21-protein assay accurately classified AD (area under the receiver operating characteristic curve [AUC] = 0.9407 to 0.9867) and mild cognitive impairment (MCI; AUC = 0.8434 to 0.8945) while also indicating brain amyloid pathology. Moreover, the assay simultaneously evaluated the changes of five biological processes in individuals and revealed the ethnic-specific dysregulations of biological processes upon AD progression.

DISCUSSION

This study demonstrated the utility of a blood-based, multi-pathway biomarker assay for early screening and staging of AD, providing insights for patient stratification and precision medicine.

HIGHLIGHTS

The authors developed a blood-based biomarker assay for Alzheimer's disease. The 21-protein assay classifies AD/MCI and indicates brain amyloid pathology. The 21-protein assay can simultaneously assess activities of five biological processes. Ethnic-specific dysregulations of biological processes in AD were revealed.

Modifiable prognostic factors of high societal costs among people on sick leave due to musculoskeletal disorders: findings from an occupational cohort study

OBJECTIVES

The objective was to identify modifiable prognostic factors of high societal costs among people on sick leave due to musculoskeletal disorders, and to identify modifiable prognostic factors of high costs related to separately healthcare utilisation and productivity loss.

DESIGN

A prospective cohort study with a 1-year follow-up.

PARTICIPANTS AND SETTING

A total of 549 participants (aged 18-67 years) on sick leave (≥ 4 weeks) due to musculoskeletal disorders in Norway were included.

OUTCOME MEASURES AND METHOD

The primary outcome was societal costs aggregated for 1 year of follow-up and dichotomised as high or low, defined by the top 25th percentile. Secondary outcomes were high costs related to separately healthcare utilisation and productivity loss aggregated for 1 year of follow-up. Healthcare utilisation was collected from public records and included primary, secondary and tertiary healthcare use. Productivity loss was collected from public records and included absenteeism, work assessment allowance and disability pension. Nine modifiable prognostic factors were selected based on previous literature. Univariable and multivariable binary logistic regression analyses were performed to identify associations (crude and adjusted for selected covariates) between each modifiable prognostic factor and having high costs.

RESULTS

Adjusted for selected covariates, six modifiable prognostic factors associated with high societal costs were identified: pain severity, disability, self-perceived health, sleep quality, return to work expectation and long-lasting disorder expectation. Depressive symptoms, work satisfaction and health literacy showed no prognostic value. More or less similar results were observed when high costs were related to separately healthcare utilisation and productivity loss.

CONCLUSION

Factors identified in this study are potential target areas for interventions which could reduce high societal costs among people on sick leave due to musculoskeletal disorders. However, future research aimed at replicating these findings is warranted.

TRIAL REGISTRATION NUMBER

NCT04196634, 12 December 2019.

Changes in spinal motor behaviour are associated with reduction in disability in chronic low back pain: A longitudinal cohort study with 1-year follow-up

BACKGROUND

The need to improve spinal motor behaviour in chronic low back pain (CLBP) rehabilitation remains unclear. The objective of this study was to test if changes in spinal motor behaviour were associated with changes in disability after an interdisciplinary rehabilitation program (IRP) in patients with CLBP.

METHODS

Seventy-one patients with CLBP participating in an IRP were included. Spinal motor behaviour was assessed with biomechanical (lumbar angular amplitude and velocity, erector spinae muscle activity and duration of the task), cognitive-emotional (task-specific fear [PRF]) and pain-related (movement-evoked pain [MEP]) measures during a lifting task before and after the IRP. Disability was measured before and after the IRP, and at 3-month and 1-year follow-ups.

RESULTS

After adjusting for confounders, changes in disability were significantly associated with MEP changes (β adj. = 0.49, p < 0.001) and PRF changes (β adj. = 0.36, p = 0.008), but not with changes in any of the biomechanical measures. MEP at the end of IRP was also associated with disability at 3 months (β adj. = 0.37, p = 0.001) and 1 year (β adj. = 0.42, p = 0.01). Biomechanical measures at the end of the IRP were not associated with disability, except for the duration of the task that was significantly associated with reduction of disability at 3 months (β non-adj = 0.5, p < 0.001).

CONCLUSIONS

Pain-related and cognitive-emotional measures of spinal motor behaviour were associated with reduction in disability following an IRP. Future research is needed to further investigate causal relationships between spinal motor behaviour and disability.

SIGNIFICANCE STATEMENT

This study supports a multidimensional understanding and analysis of spinal motor behaviour, integrating the cognitive-emotional, pain-related and biomechanical domains. It also supports the consideration of spinal motor behaviour as a potentially important treatment target in chronic low back pain management. Moreover, it suggests that reducing movement-evoked pain and task-specific fear may have more influence on disability than changing lumbar amplitude, lumbar angular velocity or erector muscle activity, which may have important implications for rehabilitation.

Prognostic Significance of Grade Discrepancy Between Primary Tumor and Venous Thrombus in Nonmetastatic Clear-cell Renal Cell Carcinoma: Analysis of the REMEMBER Registry and Implications for Adjuvant Therapy

BACKGROUND

Further stratification of the risk of recurrence of clear-cell renal cell carcinoma (ccRCC) with venous tumor thrombus (VTT) will facilitate selection of candidates for adjuvant therapy.

OBJECTIVE

To assess the impact of tumor grade discrepancy (GD) between the primary tumor (PT) and VTT in nonmetastatic ccRCC on disease-free survival (DFS), overall survival (OS), and cancer-specific survival (CSS).

DESIGN, SETTING, AND PARTICIPANTS

This was a retrospective analysis of a multi-institutional nationwide data set for patients with pT3N0M0 ccRCC who underwent radical nephrectomy and thrombectomy.

OUTCOMES MEASUREMENTS AND STATISTICAL ANALYSIS

Pathology slides were centrally reviewed. GD, a bidirectional variable (upgrading or downgrading), was numerically defined as the VTT grade minus the PT grade. Multivariable models were built to predict DFS, OS, and CSS.

RESULTS AND LIMITATIONS

We analyzed data for 604 patients with median follow-up of 42 mo (excluding events). Tumor GD between VTT and PT was observed for 47% (285/604) of the patients and was an independent risk factor with incremental value in predicting the outcomes of interest (all p < 0.05). Incorporation of tumor GD significantly improved the performance of the ECOG-ACRIN 2805 (ASSURE) model. A GD-based model (PT grade, GD, pT stage, PT sarcomatoid features, fat invasion, and VTT consistency) had a c index of 0.72 for DFS. The hazard ratios were 8.0 for GD = +2 (p < 0.001), 1.9 for GD = +1 (p < 0.001), 0.57 for GD = -1 (p = 0.001), and 0.22 for GD = -2 (p = 0.003) versus GD = 0 as the reference. According to model-converted risk scores, DFS, OS, and CSS significantly differed between subgroups with low, intermediate, and high risk (all p < 0.001).

CONCLUSIONS

Routine reporting of VTT upgrading or downgrading in relation to the PT and use of our GD-based nomograms can facilitate more informed treatment decisions by tailoring strategies to an individual patient's risk of progression.

PATIENT SUMMARY

We developed a tool to improve patient counseling and guide decision-making on other therapies in addition to surgery for patients with the clear-cell type of kidney cancer and tumor invasion of a vein.

Building a predictive model for hypertension related to environmental chemicals using machine learning

Hypertension is a chronic cardiovascular disease characterized by elevated blood pressure that can lead to a number of complications. There is evidence that the numerous environmental substances to which humans are exposed facilitate the emergence of diseases. In this work, we sought to investigate the relationship between exposure to environmental contaminants and hypertension as well as the predictive value of such exposures. The National Health and Nutrition Survey (NHANES) provided us with the information we needed (2005-2012). A total of 4492 participants were included in our study, and we incorporated more common environmental chemicals and covariates by feature selection followed by regularized network analysis. Then, we applied various machine learning (ML) methods, such as extreme gradient boosting (XGBoost), random forest classifier (RF), logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM), to predict hypertension by chemical exposure. Finally, SHapley Additive exPlanations (SHAP) were further applied to interpret the features. After the initial feature screening, we included a total of 29 variables (including 21 chemicals) for ML. The areas under the curve (AUCs) of the five ML models XGBoost, RF, LR, MLP, and SVM were 0.729, 0.723, 0.721, 0.730, and 0.731, respectively. Butylparaben (BUP), propylparaben (PPB), and 9-hydroxyfluorene (P17) were the three factors in the prediction model with the highest SHAP values. Comparing five ML models, we found that environmental exposure may play an important role in hypertension. The assessment of important chemical exposure parameters lays the groundwork for more targeted therapies, and the optimized ML models are likely to predict hypertension.

Understanding the association of mass media with the timing of antenatal care in Ethiopia: an impression from the 2016 Ethiopia demographic and health survey

INTRODUCTION

Although the timing of antenatal care has a high potential of reducing maternal and child health problems and can be improved through different mass media exposure, it has been overlooked and remained a major life-costing delinquent issue. Therefore, the aim of this study is to identify the relationship between mass media exposure and ANC for further insight.

METHODS

We used the 2016 Ethiopian Health and Demography (EDHS) data. EDHS is a community-based cross-sectional survey that applies a two-stage stratified cluster sampling and it is a country-representative. We included 4740 reproductive-age women with complete records in EDHS dataset in this study. We excluded records with missing data from the analysis. We used ordinal logistic regression followed by generalized ordinal logistic to examine mass media relationships with timely antenatal care (ANC). We presented data using numbers, mean, standard deviations, percent or proportions, coefficient of regression, and 95% confidence interval. All analyses were performed using STATA version 15.

RESULT

We examined the data of 4740 participants for the history of timely initiation of ANC and found 32.69% (95% CI = 31.34, 34.03) timely ANC. Factors such as watching television (TV) less than once a week [coef. = -0.72, CI: -1.04, -0.38], watching TV at least once a week [coef. = -0.60, CI: -0.84, -0.36], listening to radio [coef. = -0.38, CI: -0.84, -0.25], and use internet every day[coef. = -1.37, CI: -2.65, -0.09], are associated with the timely ANC.

CONCLUSION

Despite its association with improving the timing of ANC, our findings showed mothers need additional support on the use of the media and the timing of ANC. In addition to the mass media, other covariates such as educational status, family size, and husband's desire affected the timely ANC imitation. These need attention during implementation to avert the current. This is also an essential input for policy and decision-makers.

New class of RNA biomarker for endometriosis diagnosis: The potential of salivary piRNA expression

OBJECTIVES

In contrast to miRNA expression, little attention has been given to piwiRNA (piRNA) expression among endometriosis patients. The aim of the present study was to explore the human piRNAome and to investigate a potential piRNA saliva-based diagnostic signature for endometriosis.

METHODS

Data from the prospective "ENDOmiRNA" study (ClinicalTrials.gov Identifier: NCT04728152) were used. Saliva samples from 200 patients were analyzed in order to evaluate human piRNA expression using the piRNA bank. Next Generation Sequencing (NGS), barcoding of unique molecular identifiers and both Artificial Intelligence (AI) and machine learning (ML) were used. For each piRNA, sensitivity, specificity, and ROC AUC values were calculated for the diagnosis of endometriosis.

RESULTS

201 piRNAs were identified, none had an AUC ≥ 0.70, and only three piRNAs (piR-004153, piR001918, piR-020401) had an AUC between ≥ 0.6 and < 0.70. Seven were differentially expressed: piR-004153, piR-001918, piR-020401, piR-012864, piR-017716, piR-020326 and piR-016904. The respective correlation and accuracy to diagnose endometriosis according to the F1-score, sensitivity, specificity, and AUC ranged from 0 to 0.862 %, 0-0.961 %, 0.085-1, and 0.425-0.618. A correlation was observed between the patients' age (≥35 years) and piR-004153 (p = 0.002) and piR-017716 (p = 0.030). Among the 201 piRNAs, four were differentially expressed in patients with and without hormonal treatment: piR-004153 (p = 0.015), piR-020401 (p = 0.001), piR-012864 (p = 0.036) and piR-017716 (p = 0.009).

CONCLUSION

Our results support the link between piRNAs and endometriosis physiopathology and establish its utility as a potential diagnostic biomarker using saliva samples. Per se, piRNA expression should be analyzed along with the clinical status of a patient.

Prediction models in prehospital and emergency medicine research: How to derive and internally validate a clinical prediction model

Clinical prediction models are created to help clinicians with medical decision making, aid in risk stratification, and improve diagnosis and/or prognosis. With growing availability of both prehospital and in-hospital observational registries and electronic health records, there is an opportunity to develop, validate, and incorporate prediction models into clinical practice. However, many prediction models have high risk of bias due to poor methodology. Given that there are no methodological standards aimed at developing prediction models specifically in the prehospital setting, the objective of this paper is to describe the appropriate methodology for the derivation and validation of clinical prediction models in this setting. What follows can also be applied to the emergency medicine (EM) setting. There are eight steps that should be followed when developing and internally validating a prediction model: (1) problem definition, (2) coding of predictors, (3) addressing missing data, (4) ensuring adequate sample size, (5) variable selection, (6) evaluating model performance, (7) internal validation, and (8) model presentation. Subsequent steps include external validation, assessment of impact, and cost-effectiveness. By following these steps, researchers can develop a prediction model with the methodological rigor and quality required for prehospital and EM research.

CARRoT: R-package for predictive modelling by means of regression, adjusted for multiple regularisation methods

We present an R-package for predictive modelling, CARRoT (Cross-validation, Accuracy, Regression, Rule of Ten). CARRoT is a tool for initial exploratory analysis of the data, which performs exhaustive search for a regression model yielding the best predictive power with heuristic 'rules of thumb' and expert knowledge as regularization parameters. It uses multiple hold-outs in order to internally validate the model. The package allows to take into account multiple factors such as collinearity of the predictors, event per variable rules (EPVs) and R-squared statistics during the model selection. In addition, other constraints, such as forcing specific terms and restricting complexity of the predictive models can be used. The package allows taking pairwise and three-way interactions between variables into account as well. These candidate models are then ranked by predictive power, which is assessed via multiple hold-out procedures and can be parallelised in order to reduce the computational time. Models which exhibited the highest average predictive power over all hold-outs are returned. This is quantified as absolute and relative error in case of continuous outcomes, accuracy and AUROC values in case of categorical outcomes. In this paper we briefly present statistical framework of the package and discuss the complexity of the underlying algorithm. Moreover, using CARRoT and a number of datasets available in R we provide comparison of different model selection techniques: based on EPVs alone, on EPVs and R-squared statistics, on lasso regression, on including only statistically significant predictors and on stepwise forward selection technique.

Predicting lung cancer survival based on clinical data using machine learning: A review

Machine learning has gained popularity in predicting survival time in the medical field. This review examines studies utilizing machine learning and data-mining techniques to predict lung cancer survival using clinical data. A systematic literature review searched MEDLINE, Scopus, and Google Scholar databases, following reporting guidelines and using the COVIDENCE system. Studies published from 2000 to 2023 employing machine learning for lung cancer survival prediction were included. Risk of bias assessment used the prediction model risk of bias assessment tool. Thirty studies were reviewed, with 13 (43.3%) using the surveillance, epidemiology, and end results database. Missing data handling was addressed in 12 (40%) studies, primarily through data transformation and conversion. Feature selection algorithms were used in 19 (63.3%) studies, with age, sex, and N stage being the most chosen features. Random forest was the predominant machine learning model, used in 17 (56.6%) studies. While the number of lung cancer survival prediction studies is limited, the use of machine learning models based on clinical data has grown since 2012. Consideration of diverse patient cohorts and data pre-processing are crucial. Notably, most studies did not account for missing data, normalization, scaling, or standardized data, potentially introducing bias. Therefore, a comprehensive study on lung cancer survival prediction using clinical data is needed, addressing these challenges.

A two-step workflow based on plasma p-tau217 to screen for amyloid β positivity with further confirmatory testing only in uncertain cases

Cost-effective strategies for identifying amyloid-β (Aβ) positivity in patients with cognitive impairment are urgently needed with recent approvals of anti-Aβ immunotherapies for Alzheimer's disease (AD). Blood biomarkers can accurately detect AD pathology, but it is unclear whether their incorporation into a full diagnostic workflow can reduce the number of confirmatory cerebrospinal fluid (CSF) or positron emission tomography (PET) tests needed while accurately classifying patients. We evaluated a two-step workflow for determining Aβ-PET status in patients with mild cognitive impairment (MCI) from two independent memory clinic-based cohorts (n = 348). A blood-based model including plasma tau protein 217 (p-tau217), age and APOE ε4 status was developed in BioFINDER-1 (area under the curve (AUC) = 89.3%) and validated in BioFINDER-2 (AUC = 94.3%). In step 1, the blood-based model was used to stratify the patients into low, intermediate or high risk of Aβ-PET positivity. In step 2, we assumed referral only of intermediate-risk patients to CSF Aβ42/Aβ40 testing, whereas step 1 alone determined Aβ-status for low- and high-risk groups. Depending on whether lenient, moderate or stringent thresholds were used in step 1, the two-step workflow overall accuracy for detecting Aβ-PET status was 88.2%, 90.5% and 92.0%, respectively, while reducing the number of necessary CSF tests by 85.9%, 72.7% and 61.2%, respectively. In secondary analyses, an adapted version of the BioFINDER-1 model led to successful validation of the two-step workflow with a different plasma p-tau217 immunoassay in patients with cognitive impairment from the TRIAD cohort (n = 84). In conclusion, using a plasma p-tau217-based model for risk stratification of patients with MCI can substantially reduce the need for confirmatory testing while accurately classifying patients, offering a cost-effective strategy to detect AD in memory clinic settings.

Predicting deep surgical site infection in patients receiving open posterior instrumented thoracolumbar surgery: A-DOUBLE-SSI risk score - a large retrospective multicenter cohort study in China

BACKGROUND

To develop a practical prediction model to predict the risk of deep surgical site infection (SSI) in patients receiving open posterior instrumented thoracolumbar surgery.

METHODS

Data of 3419 patients in four hospitals from 1 January 2012 to 30 December 2021 were evaluated. The authors used clinical knowledge-driven, data-driven, and decision tree model to identify predictive variables of deep SSI. Forty-three candidate variables were collected, including 5 demographics, 29 preoperative, 5 intraoperative, and 4 postoperative variables. According to model performance and clinical practicability, the best model was chosen to develop a risk score. Internal validation was performed by using bootstrapping methods.

RESULTS

After open posterior instrumented thoracolumbar surgery, 158 patients (4.6%) developed deep SSI. The clinical knowledge-driven model yielded 12 predictors of deep SSI, while the data-driven and decision tree model produced 11 and 6 predictors, respectively. A knowledge-driven model, which had the best C-statistics [0.81 (95% CI: 0.78-0.85)] and superior calibration, was chosen due to its favorable model performance and clinical practicality. Moreover, 12 variables were identified in the clinical knowledge-driven model, including age, BMI, diabetes, steroid use, albumin, duration of operation, blood loss, instrumented segments, powdered vancomycin administration, duration of drainage, postoperative cerebrospinal fluid leakage, and early postoperative activities. In bootstrap internal validation, the knowledge-driven model still showed optimal C-statistics (0.79, 95% CI: 0.75-0.83) and calibration. Based on these identified predictors, a risk score for deep SSI incidence was created: the A-DOUBLE-SSI (Age, D [Diabetes, Drainage], O [duration of Operation, vancOmycin], albUmin, B [BMI, Blood loss], cerebrospinal fluid Leakage, Early activities, Steroid use, and Segmental Instrumentation) risk score. Based on the A-DOUBLE-SSI score system, the incidence of deep SSI increased in a graded fashion from 1.06% (A-DOUBLE-SSIs score ≤8) to 40.6% (A-DOUBLE-SSIs score>15).

CONCLUSIONS

The authors developed a novel and practical model, the A-DOUBLE-SSIs risk score, that integrated easily accessible demographics, preoperative, intraoperative, and postoperative variables and could be used to predict individual risk of deep SSI in patients receiving open posterior instrumented thoracolumbar surgery.

Diagnosis of autism spectrum disorder based on functional brain networks and machine learning

Autism is a multifaceted neurodevelopmental condition whose accurate diagnosis may be challenging because the associated symptoms and severity vary considerably. The wrong diagnosis can affect families and the educational system, raising the risk of depression, eating disorders, and self-harm. Recently, many works have proposed new methods for the diagnosis of autism based on machine learning and brain data. However, these works focus on only one pairwise statistical metric, ignoring the brain network organization. In this paper, we propose a method for the automatic diagnosis of autism based on functional brain imaging data recorded from 500 subjects, where 242 present autism spectrum disorder considering the regions of interest throughout Bootstrap Analysis of Stable Cluster map. Our method can distinguish the control group from autism spectrum disorder patients with high accuracy. Indeed the best performance provides an AUC near 1.0, which is higher than that found in the literature. We verify that the left ventral posterior cingulate cortex region is less connected to an area in the cerebellum of patients with this neurodevelopment disorder, which agrees with previous studies. The functional brain networks of autism spectrum disorder patients show more segregation, less distribution of information across the network, and less connectivity compared to the control cases. Our workflow provides medical interpretability and can be used on other fMRI and EEG data, including small data sets.

Evaluation of premature ventricular complexes during in-hospital ECG monitoring as a predictor of ventricular tachycardia in an intensive care unit cohort

In-hospital electrocardiographic (ECG) monitors are typically configured to alarm for premature ventricular complexes (PVCs) due to the potential association of PVCs with ventricular tachycardia (VT). However, no contemporary hospital-based studies have examined the association of PVCs with VT. Hence, the benefit of PVC monitoring in hospitalized patients is largely unknown. This secondary analysis used a large PVC alarm data set to determine whether PVCs identified during continuous ECG monitoring were associated with VT, in-hospital cardiac arrest (IHCA), and/or death in a cohort of adult intensive care unit patients. Six PVC types were examined (i.e., isolated, bigeminy, trigeminy, couplets, R-on-T, and run PVCs) and were compared between patients with and without VT, IHCA, and/or death. Of 445 patients, 48 (10.8%) had VT; 11 (2.5%) had IHCA; and 49 (11%) died. Isolated and run PVC counts were higher in the VT group (p = 0.03 both), but group differences were not seen for the other four PVC types. The regression models showed no significant associations between any of the six PVC types and VT or death, although confidence intervals were wide. Due to the small number of cases, we were unable to test for associations between PVCs and IHCA. Our findings suggest that we should question the clinical relevance of activating PVC alarms as a forewarning of VT, and more work should be done with larger sample sizes. A more precise characterization of clinically relevant PVCs that might be associated with VT is warranted.

The circadian clock remains intact, but with dampened hormonal output in heart failure

BACKGROUND

Circadian (24-h) rhythms are important regulators in physiology and disease, but systemic disease may disrupt circadian rhythmicity. Heart failure (HF) is a systemic disease affecting hormonal regulation. We investigate whether HF affects the rhythmic expression of melatonin and cortisol, main endocrine products of the central clock, and cardiac-specific troponin in patients. We corroborate the functionality of the peripheral clock directly in the organs of translational models, inaccessible in human participants.

METHODS

We included 46 HF patients (71.7% male, median age of 60 years, NYHA class II (32.6%) or III (67.4%), ischemic cardiomyopathy (43.5%), comorbidities: diabetes 21.7%, atrial fibrillation 30.4%), and 24 matched controls. Blood was collected at seven time-points during a 24-h period (totalling 320 HF and 167 control samples) for melatonin, cortisol, and cardiac troponin T (cTnT) measurements after which circadian rhythms were assessed through cosinor analyses, both on the individual and the group level. Next, we analysed peripheral circadian clock functionality using cosinor analysis in male animal HF models: nocturnal mice and diurnal zebrafish, based on expression of core clock genes in heart, kidneys, and liver, every 4 h during a 24-h period in a light/darkness synchronised environment.

FINDINGS

Melatonin and cortisol concentrations followed a physiological 24-h pattern in both patients and controls. For melatonin, acrophase occurred during the night for both groups, with significantly decreased amplitude (median 5.2 vs 8.8, P = 0.0001) and circadian variation ([maximum]/[minimum]) in heart failure patients. For cortisol, mesor showed a significant increase for HF patients (mean 331.9 vs 275.1, P = 0.017) with a difference of 56.8 (95% CI 10.3-103.3) again resulting in a relatively lower variation: median 3.9 vs 6.3 (P = 0.0058). A nocturnal blood pressure dip was absent in 77.8% of HF patients. Clock gene expression profiles (Bmal, Clock, Per, Cry) were similar and with expected phase relations in animal HF models and controls, demonstrating preserved peripheral clock functionality in HF. Furthermore, oscillations in diurnal zebrafish were expectedly in opposite phases to those of nocturnal mice. Concordantly, cTnT concentrations in HF patients revealed significant circadian oscillations.

INTERPRETATION

Central clock output is dampened in HF patients while the molecular peripheral clock, as confirmed in animal models, remains intact. This emphasises the importance of taking timing into account in research and therapy for HF, setting the stage for another dimension of diagnostic, prognostic and therapeutic approaches.

FUNDING

Hartstichting.

Erector Spinae Plane Block versus Paravertebral Block after Thoracic Surgery for Lung Cancer: A Propensity Score Study

INTRODUCTION

The prevention of respiratory complications is a major issue after thoracic surgery for lung cancer, and requires adequate post-operative pain management. The erector spinae plane block (ESPB) may decrease post-operative pain. The objective of this study was to evaluate the impact of ESPB on pain after video or robot-assisted thoracic surgery (VATS or RATS).

METHODS

The main outcome of this retrospective study with a propensity score analysis (PSA) was to compare the post-operative pain at 24 h at rest and at cough between a group that received ESPB and a group that received paravertebral block (PVB). Post-operative morphine consumption at 24 h and complications were also assessed.

RESULTS

One hundred and seven patients were included: 54 in the ESPB group and 53 in the PVB group. The post-operative median pain score at rest and cough was lower in the ESPB group compared to the PVB group at 24 h (respectively, at rest 2 [1; 3.5] vs. 2 [0; 4], p = 0.0181, with PSA; ESPB -0.80 [-1.50; -0.10], p = 0.0255, and at cough (4 [3; 6] vs. 5 [4; 6], p = 0.0261, with PSA; ESPB -1.48 [-2.65; -0.31], p = 0.0135). There were no differences between groups concerning post-operative morphine consumption at 24 h and respiratory complications.

CONCLUSIONS

Our results suggest that ESPB is associated with less post-operative pain at 24 h than PVB after VATS or RATS for lung cancer. Furthermore, ESPB is an acceptable and safe alternative compared to PVB.

A comprehensive regulatory and industry review of modeling and simulation practices in oncology clinical drug development

Exposure-response (E-R) analyses are an integral component in the development of oncology products. Characterizing the relationship between drug exposure metrics and response allows the sponsor to use modeling and simulation to address both internal and external drug development questions (e.g., optimal dose, frequency of administration, dose adjustments for special populations). This white paper is the output of an industry-government collaboration among scientists with broad experience in E-R modeling as part of regulatory submissions. The goal of this white paper is to provide guidance on what the preferred methods for E-R analysis in oncology clinical drug development are and what metrics of exposure should be considered.

Subsampling based variable selection for generalized linear models

A novel variable selection method for low-dimensional generalized linear models is introduced. The new approach called AIC OPTimization via STABility Selection (OPT-STABS) repeatedly subsamples the data, minimizes Akaike's Information Criterion (AIC) over a sequence of nested models for each subsample, and includes in the final model those predictors selected in the minimum AIC model in a large fraction of the subsamples. New methods are also introduced to establish an optimal variable selection cutoff over repeated subsamples. An extensive simulation study examining a variety of proposec variable selection methods shows that, although no single method uniformly outperforms the others in all the scenarios considered, OPT-STABS is consistently among the best-performing methods in most settings while it performs competitively for the rest. This is in contrast to other candidate methods which either have poor performance across the board or exhibit good performance in some settings, but very poor in others. In addition, the asymptotic properties of the OPT-STABS estimator are derived, and its root-n consistency and asymptotic normality are proved. The methods are applied to two datasets involving logistic and Poisson regressions.

Determinants of nutritional status among primary school students in Dilla Town; Application of an ordinal logistic regression model

Background

One of the most frequent reasons for children's poor physical and mental development is malnutrition, becoming a more significant issue in most developing nations, including Ethiopia. Prior research used multiple anthropometric measurements separately to pinpoint undernutrition concerns in children. However, the impact of each explanatory variable on a single response category was not considered in these investigations. This study used a single composite index of anthropometric parameters to identify the factors affecting elementary school students' nutritional condition.

Methods

In Dilla, Ethiopia, 494 primary school students took part in a cross-sectional institutional survey during the 2021 academic year. Principal component analysis was used to create a single composite measure of nutritional status using z-scores for the anthropometric indices of height-for-age and body mass index-for-age. The relative effectiveness of a partial proportional odds model was compared with several other ordinal regression models to identify the important variables for children's nutritional status.

Results

27.94% of primary school students were undernourished (7.29% severely and 20.65% moderately). According to the fitted partial proportional odds model, the mother's education level (secondary or higher) was positively correlated with the nutritional status of primary school students, given that in this case the students ate three or more times per day and had a high dietary diversity score (OR = 5.94; CI: 2.2-16.0). Nevertheless, there was a negative correlation between larger family size (OR = 0.56; CI: 0.32-0.97), unprotected groundwater (OR = 0.76; CI: 0.6-0.96), and severely food insecure households (OR = 0.3; CI: 0.14-0.68).

Conclusion

In Dilla, Ethiopia, undernutrition among primary school students is a serious issue. It is essential to implement nutrition education and school feeding programs, improve drinking water sources, and boost the community's economy to alleviate the problems.

Development and validation of a bleeding risk prediction score for patients with mitral valve stenosis and atrial fibrillation or mechanical heart valves receiving long-term warfarin therapy

AIMS

This study aimed to develop and validate a new bleeding risk score to predict warfarin-associated major bleeding for patients with mitral valve stenosis with atrial fibrillation (MSAF) or mechanical heart valves (MHV).

METHODS

A multicentre, retrospective cohort study was conducted at 3 hospitals in Thailand. Adult patients with MSAF or MHV receiving warfarin for ≥3 months during 2011-2015 were identified. Data collection and case validation were performed electronically and manually. Potential variables were screened using the least absolute shrinkage and selection operator. Multivariate logistic regression analysis using stepwise backward selection was used to construct a risk score. Predictive discrimination of the score was evaluated using the C-statistic. Calibration was assessed using the Hosmer-Lemeshow goodness-of-fit test.

RESULTS

There were 1287 patients (3903.41 patient-year of follow-up), with 192 experiencing bleeding (4.92 event/100 patient-year) in the derivation cohort. A new bleeding risk score termed, the HEARTS-60 + 3 score (hypertension/history of bleeding; external factors, e.g., alcohol/drugs [aspirin or nonsteroidal anti-inflammatory drugs]; anaemia/hypoalbuminaemia; renal/hepatic insufficiency; time in therapeutic range of <60%; stroke; age ≥60 y; target international normalized ratio of 3.0 [2.5-3.5]), was developed and showed good predictive performance (C-statistic [95% confidence interval] of 0.88 [0.85-0.91]). In the external validation cohort of 832 patients (2018.45 patient-year with a bleeding rate of 4.31 event/100 patient-year), the HEARTS-60 + 3 score showed a good predictive performance with a C-statistic (95% confidence interval) of 0.84 (0.81-0.89).

CONCLUSION

The HEARTS-60 + 3 score shows a potential as a bleeding risk prediction score in MSAF or MHV patients.

Blood-Type-A is a COVID-19 infection and hospitalization risk in a Turkish cohort

We have shown in an ethnically homogenous Turkey cohort with more than six thousand cases and 25 thousand controls that ABO blood types that contain anti-A antibody (O and B) are protective against COVID-19 infection and hospitalization, whereas those without the anti-A antibody (A and AB) are risks. The A + AB frequency increases from 54.7 % in uninfected controls to 57.6 % in COVID-19 outpatients, and to 62.5 % in COVID-19 inpatients. The odds-ratio (OR) for lacking of anti-A antibody risk for infection is 1.16 (95 % confidence interval (CI) 1.1-1.22, and Fisher test p-value 1.8 × 10^-7). The OR for hospitalization is 1.23 (95 %CI 1.06-1.42, Fisher test p-value 0.005). A linear regression treating controls, outpatients, inpatients as three numerical levels over anti-A antibody leads to a p-value of 5.9 × 10^-9. All these associations remain to be statistically significant after conditioning over age, even though age itself is a risk for both infection and hospitalization. We also attempted to correct the potential effect from vaccination, even though vaccination information is not available, by using the date of the data collection as a surrogate to vaccination status. Although no significant association between infection/hospitalization with Rhesus blood system was found, forest plots are used to illustrate possible trends.

Pharyngeal biorhythms during oral milk challenge in high-risk infants: Do they predict chronic tube feeding?

BACKGROUND

Eating difficulties are common in high-risk neonatal intensive care unit (NICU) infants; mechanisms remain unclear. Crib-side pharyngo-esophageal motility testing is utilized to assess contiguous swallowing physiology, and cross-system interplay with cardio-respiratory rhythms. Aims were to: (1) identify whether distinct pharyngeal rhythms exist during oral milk challenge (OMC), and (2) develop a chronic tube feeding risk prediction model in high-risk infants.

METHODS

Symptomatic NICU infants (N = 56, 29.7 ± 3.7 weeks birth gestation) underwent pharyngo-esophageal manometry with OMC at 40.9 ± 2.5 weeks postmenstrual age (PMA). Exploratory cluster data analysis (partitioning around k-medoids) was performed to identify patient groups using pharyngeal contractile rhythm data (solitary swallows and swallows within bursts). Subsequently, (a) pharyngeal-esophageal, cardio-respiratory, and eating method characteristics were compared among patient groups using linear mixed models, and (b) chronic tube feeding prediction model was created using linear regression.

RESULTS

Three distinct patient groups were identified with validity score of 0.6, and termed sparse (high frequency of solitary swallows), intermediate, or robust (high swallow rate within bursts). Robust group infants had: lesser pharyngeal and esophageal variability, greater deglutition apnea, pharyngeal activity, and esophageal activity (all p < 0.05), but less frequent heart rate decreases (p < 0.05) with improved clinical outcomes (milk transfer rate, p < 0.001, and independent oral feeding at discharge, p < 0.03). Chronic tube feeding risk = -11.37 + (0.22 × PMA) + (-0.73 × bronchopulmonary dysplasia) + (1.46 × intermediate group) + (2.57 × sparse group).

CONCLUSIONS

Robust pharyngeal rhythm may be an ideal neurosensorimotor biomarker of independent oral feeding. Differential maturation of cranial nerve-mediated excitatory and inhibitory components involving foregut, airway, and cardiac rhythms distinguishes the physiologic and pathophysiologic basis of swallowing and cardio-respiratory adaptation.

Identifying Patient Characteristics Associated With the Occurrence of Post Treatment Non-serious Adverse Events After Cervical Spine Manual Therapy Treatment in Patients With Neck Pain

OBJECTIVES

To compare prevalence rates of serious and non-serious adverse events after manipulation and mobilization and to identify risk factors of serious and non-serious adverse events following 4 types of manual therapy treatment in patients with neck pain.

DESIGN

A prospective cohort study in primary care manual therapy practice.

PARTICIPANTS

Patients with neck pain (N=686) provided data on adverse events after 1014 manipulation treatments, 829 mobilization treatments, 437 combined manipulation and mobilization treatments, and 891 treatments consisting of "other treatment modality".

INTERVENTIONS

Usual care manual therapy.

MAIN OUTCOME MEASURES

A chi-square test was performed to explore differences in prevalence rates. Logistic regression analysis was performed within the 4 treatment groups. A priori we defined associations between patient-characteristics and adverse events of odds ratio (OR)>2 or OR<0.5 as clinically relevant.

RESULTS

No serious adverse events, such as cervical artery dissection or stroke, were reported. With regard to non-serious adverse events, we found that these are common after manual therapy treatment: prevalence rates are ranging from 0.3% to 64.7%. We found a statistically significant difference between the 4 types of treatments, detrimental to mobilization treatment. Logistic regression analysis resulted in 3 main predictors related to non-serious adverse events after manual therapy treatment: smoking (OR ranges from 2.10 [95% confidence interval [CI] 1.37-3.11] to 3.33 [95% CI 1.83-5.93]), the presence of comorbidity (OR ranges from 2.32 [95% CI 1.22-4.44] to 3.88 [95% CI 1.62-9.26]), and female sex (OR ranges from 0.22 [95% CI 0.11-0.46] to 0.49 [95% CI 0.28-0.86]).

CONCLUSION

There is a significant difference in the occurrence of non-serious adverse events after mobilization compared with manipulation or a combination of manipulation and mobilization. Non-serious adverse events in manual therapy practice are common and are associated with smoking and the presence of comorbidity. In addition, women are more likely to report non-serious adverse events.

Predictive models for the incidence of Parkinson's disease: systematic review and critical appraisal

Numerous predictive models for Parkinson's disease (PD) incidence have been published recently. However, the model performance and methodological quality of those available models are yet needed to be summarized and assessed systematically. In this systematic review, we systematically reviewed the published predictive models for PD incidence and assessed their risk of bias and applicability. Three international databases were searched. Cohort or nested case-control studies that aimed to develop or validate a predictive model for PD incidence were considered eligible. The Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used for risk of bias and applicability assessment. Ten studies covering 10 predictive models were included. Among them, four studies focused on model development, covering eight models, while the remaining six studies focused on model external validation, covering two models. The discrimination of the eight new development models was generally poor, with only one model reported C index > 0.70. Four out of the six external validation studies showed excellent or outstanding discrimination. All included studies had high risk of bias. Three predictive models (the International Parkinson and Movement Disorder Society [MDS] prodromal PD criteria, the model developed by Karabayir et al. and models validated by Faust et al.) are recommended for clinical application by considering model performance and resource-demanding. In conclusion, the performance and methodological quality of most of the identified predictive models for PD incidence were unsatisfactory. The MDS prodromal PD criteria, model developed by Karabayir et al. and model validated by Faust et al. may be considered for clinical use.

Endometriosis-associated infertility diagnosis based on saliva microRNA signatures

RESEARCH QUESTION

Can a saliva-based miRNA signature for endometriosis-associated infertility be designed and validated by analysing the human miRNome?

DESIGN

The prospective ENDOmiARN study (NCT04728152) included 200 saliva samples obtained between January 2021 and June 2021 from women with pelvic pain suggestive of endometriosis. All patients underwent either laparoscopy, magnetic resonance imaging, or both. Patients diagnosed with endometriosis were allocated to one of two groups according to their fertility status. Data analysis consisted of identifying a set of miRNA biomarkers using next-generation sequencing, and development of a saliva-based miRNA signature of infertility among patients with endometriosis based on a random forest model.

RESULTS

Among the 153 patients diagnosed with endometriosis, 24% (n = 36) were infertile and 76% (n = 117) were fertile. Small RNA-sequencing of the 153 saliva samples yielded approximately 3712 M raw sequencing reads (from ∼13.7 M to ∼39.3 M reads/sample). Of the 2561 known miRNAs, the feature selection method generated a signature of 34 miRNAs linked to endometriosis-associated infertility. After validation, the most accurate signature model had a sensitivity, specificity and area under the curve of 100%.

CONCLUSION

A saliva-based miRNA signature for endometriosis-associated infertility is reported. Although the results still require external validation before using the signature in routine practice, this non-invasive tool is likely to have a major effect on care provided to women with endometriosis.

Accuracy of self-perceived risk of falls among hospitalised adults in China: an observational study

OBJECTIVE

To evaluate the accuracy of self-perceived risk of falls in hospitalised adults and explore factors associated with the differences.

DESIGN

Cross-sectional study.

SETTING

We conducted the study in two tertiary general hospitals located in Zhejiang province and Shandong province in China.

PARTICIPANTS

339 patients were recruited using convenient sampling. The majority of them were men (54%), aged 61-70 (40.1%) and had received secondary school education or lower (82%).

OUTCOME MEASURES

The Fall Risk Perception Questionnaire and the Morse Fall Scale (MFS) were used to measure patients' self-perceived risk of falls and nurses' assessment. Other risk factors of falls were assessed to identify the determinants of disparities.

RESULTS

Most patients (74.6%) had a high risk of falls according to MFS. Only 61.9% of the patients' perceived risk matched with the assessment of nurses. Nearly one-third (27.5%) underestimated their fall risk, while the remaining (10.6%) overestimated. Multivariable logistic regression analyses revealed that older age, lower number of comorbidities, not having fear of falling and emergency department were the significant factors associated with underestimated risk of falls (p<0.05). Besides, endocrine department and having fall-related injuries were significantly associated with overestimated risk of falls (p<0.05).

CONCLUSION

Hospitalised patients were proven to be poor at recognising their risk of falls. Measurement of patients' self-perceived and health professionals' assessment of fall risk should be conducted to evaluate the disparity. This study provides a solid foundation to raise medical staff's awareness of the targeted population, identify the underlying factors and implement tailored fall prevention strategies and education.

Clinical characteristics do not reliably identify non-adherence in patients with uncontrolled hypertension

PURPOSE

Chemical adherence testing is a reliable method to assess adherence to antihypertensive drugs. However, it is expensive and has limited availability in clinical practice. To reduce the number and costs of chemical adherence tests, we aimed to develop and validate a clinical screening tool to identify patients with a low probability of non-adherence in patients with uncontrolled hypertension.

MATERIALS AND METHODS

In 495 patients with uncontrolled hypertension referred to the University Medical Centre Utrecht (UMCU), the Netherlands, a penalised logistic regression model including seven pre-specified easy-to-measure clinical variables was derived to estimate the probability of non-adherence. Non-adherence was defined as not detecting at least one of the prescribed antihypertensive drugs in plasma or urine. Model performance and test characteristics were evaluated in 240 patients with uncontrolled hypertension referred to the Heartlands Hospital, United Kingdom.

RESULTS

Prevalence of non-adherence to antihypertensive drugs was 19% in the UMCU and 44% in the Heartlands Hospital population. After recalibration of the model's intercept, predicted probabilities agreed well with observed frequencies. The c-statistic of the model was 0.63 (95%CI 0.53-0.72). Predicted probability cut-off values of 15%-22.5% prevented testing in 5%-15% of the patients, carrying sensitivities between 97% (64-100) and 90% (80-95), and negative predictive values between 74% (10-99) and 70% (50-85).

CONCLUSION

The combination of seven clinical variables is not sufficient to reliably discriminate adherent from non-adherent individuals to safely reduce the number of chemical adherence tests. This emphasises the complex nature of non-adherence behaviour and thus the need for objective chemical adherence tests in patients with uncontrolled hypertension.

Screening Echocardiography Identifies Risk Factors for Pulmonary Hypertension at Discharge in Premature Infants with Bronchopulmonary Dysplasia

HYPOTHESIS

Premature infants with bronchopulmonary dysplasia (BPD) are at increased risk of secondary pulmonary hypertension (BPD-PH). Prior studies yielded mixed results on the utility of echocardiographic screening at 36 weeks post-menstrual age (PMA). We present our experience using echocardiographic screening at the time of BPD diagnosis to identify infants at highest risk of BPD-PH at discharge.

MATERIALS AND METHODS

Retrospective cohort analysis of clinical/ demographic data and screening echocardiograms in patients with BPD. Discharge echocardiograms identified infants with or without BPD-PH at discharge. 36 weeks PMA screening echocardiograms and clinical data were then reviewed to identify which factors were associated with increased odds of BPD-PH at discharge. Associations between echocardiographic findings were evaluated with 2- and 3-variable models to predict increased risk of BPD-PH at discharge.

RESULTS

In our cohort of 64 infants with severe BPD, BPD-PH was present in 22/64 (34%) infants at discharge. There were no clinical differences at time of 36 weeks PMA screening evaluation (mean PMA 36.6 ± 2.9 weeks). PH at screening was poorly predictive of PH at discharge as PH at screening resolved in 49% of patients. However, having an ASD, RV dilation, hypertrophy, or reduced function on screening, especially in combination, were associated with BPD-PH at discharge.

CONCLUSION

In our cohort of premature infants with BPD, 36 weeks PMA screening echocardiogram identified patients at increased risk for BPD-PH at discharge when ASD, RVH, or impaired RV function were present. Larger prospective studies are indicated to validate these findings.

Predicting the risk of nodular thyroid disease in coal miners based on different machine learning models

Background

Nodular thyroid disease is by far the most common thyroid disease and is closely associated with the development of thyroid cancer. Coal miners with chronic coal dust exposure are at higher risk of developing nodular thyroid disease. There are few studies that use machine learning models to predict the occurrence of nodular thyroid disease in coal miners. The aim of this study was to predict the high risk of nodular thyroid disease in coal miners based on five different Machine learning (ML) models.

Methods

This is a retrospective clinical study in which 1,708 coal miners who were examined at the Huaihe Energy Occupational Disease Control Hospital in Anhui Province in April 2021 were selected and their clinical physical examination data, including general information, laboratory tests and imaging findings, were collected. A synthetic minority oversampling technique (SMOTE) was used for sample balancing, and the data set was randomly split into a training and Test dataset in a ratio of 8:2. Lasso regression and correlation heat map were used to screen the predictors of the models, and five ML models, including Extreme Gradient Augmentation (XGBoost), Logistic Classification (LR), Gaussian Parsimonious Bayesian Classification (GNB), Neural Network Classification (MLP), and Complementary Parsimonious Bayesian Classification (CNB) for their predictive efficacy, and the model with the highest AUC was selected as the optimal model for predicting the occurrence of nodular thyroid disease in coal miners.

Result

Lasso regression analysis showed Age, H-DLC, HCT, MCH, PLT, and GGT as predictor variables for the ML models; in addition, heat maps showed no significant correlation between the six variables. In the prediction of nodular thyroid disease, the AUC results of the five ML models, XGBoost (0.892), LR (0.577), GNB (0.603), MLP (0.601), and CNB (0.543), with the XGBoost model having the largest AUC, the model can be applied in clinical practice.

Conclusion

In this research, all five ML models were found to predict the risk of nodular thyroid disease in coal miners, with the XGBoost model having the best overall predictive performance. The model can assist clinicians in quickly and accurately predicting the occurrence of nodular thyroid disease in coal miners, and in adopting individualized clinical prevention and treatment strategies.

Nomogram to predict postoperative complications after cytoreductive surgery for advanced epithelial ovarian cancer: A multicenter retrospective cohort study

Objective

To establish nomograms to predict the risk of postoperative complications following cytoreductive surgery in patients with advanced epithelial ovarian cancer (AEOC).

Methods

A multicenter retrospective cohort study that included patients with FIGO stage IIIC-IV epithelial ovarian cancer who underwent cytoreductive surgery was designed. By using univariate and multivariate analyses, patient preoperative characteristics were used to predict the risk of postoperative complications. Multivariate modeling was used to develop Nomograms.

Results

Overall, 585 AEOC patients were included for analysis (training cohort = 426, extrapolation cohort = 159). According to the findings, the training cohort observed an incidence of postoperative overall and severe complications of 28.87% and 6.10%, respectively. Modified frailty index (mFI) (OR 1.96 and 2.18), FIGO stage (OR 2.31 and 3.22), and Surgical Complexity Score (SCS) (OR 1.16 and 1.23) were the clinical factors that were most substantially associated to the incidence of overall and severe complications, respectively. The resulting nomograms demonstrated great internal discrimination, good consistency, and stable calibration, with C-index of 0.74 and 0.78 for overall and severe complications prediction, respectively. A satisfactory external discrimination was also indicated by the extrapolation cohort, with the C-index for predicting overall and severe complications being 0.92 and 0.91, respectively.

Conclusions

The risk of considerable postoperative morbidity exists after cytoreductive surgery for AEOC. These two nomograms with good discrimination and calibration might be useful to guide clinical decision-making and help doctors assess the probability of postoperative complications for AEOC patients.

Demographic, behavioural and occupational risk factors associated with SARS-CoV-2 infection in UK healthcare workers: a retrospective observational study

OBJECTIVE

Healthcare workers (HCWs) are at higher risk of SARS-CoV-2 infection than the general population. This group is pivotal to healthcare system resilience during the COVID-19, and future, pandemics. We investigated demographic, social, behavioural and occupational risk factors for SARS-CoV-2 infection among HCWs.

DESIGN/SETTING/PARTICIPANTS

HCWs enrolled in a large-scale sero-epidemiological study at a UK university teaching hospital were sent questionnaires spanning a 5-month period from March to July 2020. In a retrospective observational cohort study, univariate logistic regression was used to assess factors associated with SARS-CoV-2 infection. A Least Absolute Shrinkage Selection Operator regression model was used to identify variables to include in a multivariate logistic regression model.

RESULTS

Among 2258 HCWs, highest ORs associated with SARS-CoV-2 antibody seropositivity on multivariate analysis were having a household member previously testing positive for SARS-CoV-2 antibodies (OR 6.94 (95% CI 4.15 to 11.6); p&lt;0.0001) and being of black ethnicity (6.21 (95% CI 2.69 to 14.3); p&lt;0.0001). Occupational factors associated with a higher risk of seropositivity included working as a physiotherapist (OR 2.78 (95% CI 1.21 to 6.36); p=0.015) and working predominantly in acute medicine (OR 2.72 (95% CI 1.57 to 4.69); p&lt;0.0001) or medical subspecialties (not including infectious diseases) (OR 2.33 (95% CI 1.4 to 3.88); p=0.001). Reporting that adequate personal protective equipment (PPE) was 'rarely' available had an OR of 2.83 (95% CI 1.29 to 6.25; p=0.01). Reporting attending a handover where social distancing was not possible had an OR of 1.39 (95% CI 1.02 to 1.9; p=0.038).

CONCLUSIONS

The emergence of SARS-CoV-2 variants and potential vaccine escape continue to threaten stability of healthcare systems worldwide, and sustained vigilance against HCW infection remains a priority. Enhanced risk assessments should be considered for HCWs of black ethnicity, physiotherapists and those working in acute medicine or medical subspecialties. Workplace risk reduction measures include ongoing access to high-quality PPE and effective social distancing measures.

Incorporation of Tumor-Free Distance and Other Alternative Ultrasound Biomarkers into a Myometrial Invasion-Based Model Better Predicts Lymph Node Metastasis in Endometrial Cancer: Evidence and Future Prospects

Myometrial invasion (MI) is a parameter currently used in transvaginal ultrasound (TVS) in endometrial cancer (EC) to determine local staging; however, without molecular diagnostics, it is insufficient for the selection of high-risk cases, i.e., those with a high risk of lymph node metastases (LNM). The study’s objective was to answer the question of which TVS markers, or their combination, reflecting the molecular changes in EC, can improve the prediction of LNM. Methods: The TVS examination was performed on 116 consecutive EC patients included in this prospective study. The results from the final histopathology were a reference standard. Univariate and multivariate logistic models of analyzed TVS biomarkers (tumor [T] size, T area [AREA], T volume [SPE-VOL], MI, T-free distance to serosa [TFD], endo-myometrial irregularity, [EMIR], cervical stromal involvement, CSI) were evaluated to assess the relative accuracy of the possible LNM predictors., Spline functions were applied to avoid a potential bias in assuming linear relations between LNM and continuous predictors. Calculations were made in R using libraries splines, glmulti, and pROC. Results: LNM was found in 20 out of the 116 (17%) patients. In univariate analysis, only uMI, EMIR, uCSI and uTFD were significant predictors of LNM. The accuracy was 0.707 (AUC 0.684, 95% CI 0.568−0.801) for uMI (p < 0.01), 0.672 (AUC 0.664, 95% CI 0.547−0.781) for EMIR (p < 0.01), 0.776 (AUC 0.647, 95% CI 0.529−0.765) for uCSI (p < 0.01), and 0.638 (AUC 0.683, 95% CI 0.563−0.803) for uTFD (p < 0.05). The cut-off value for uTFD was 5.2 mm. However, AREA and VOL revealed a significant relationship by nonlinear analysis as well. Among all possible multivariate models, the one comprising interactions of splines of uTFD with uMI and splines of SPE-VOL with uCSI showed the most usefulness. Accuracy was 0.802 (AUC 0.791, 95% CI 0.673−0.91) Conclusions: A combination of uTFD for patients with uMI > 50%, and SPE-VOL for patients with uCSI, allows for the most accurate prediction of LNM in EC, rather than uMI alone.

Development of a clinical prediction instrument to estimate risk of initial violent injury

BACKGROUND

Interpersonal violent injury is a public health crisis, disproportionately affecting young people of color. We aimed to evaluate associations between sociobehavioral predictors and first-time violent injury, and to develop a predictive risk score for violent injury.

METHODS

We performed a retrospective case-cohort study of adolescents aged 12-18 years. Multivariable logistic regression was used to estimate associations between 35 candidate variables and interpersonal first-time violent injury resulting in an emergency department (ED) visit. Multiple imputation was used to account for missing values and a risk score was developed by multiplying regression coefficients by 10 to generate a composite tool to predict initial violent injury (IVI). Discrimination and calibration were assessed using 10-fold cross validation.

RESULTS

19,210 adolescents were included, 276 (1.4%) as victims of IVI. The final model, the Initial Violent Injury Risk Prediction Tool (IVI-RPT), included: age, fight within the prior year, trouble with the law, and alcohol use. IVI-RPT scores were categorized as: 0-7 (low risk), 8-16 (moderate), and 17-26 (high), and IVI prevalence was 0.8% (95% confidence interval [CI]: 0.6%, 0.9%), 2.5% (95% CI: 1.9%, 3.1%), and 5.3% (95% CI: 4.1%, 6.6%), respectively. The area under the receiver operating characteristic curve was 0.70 (95% CI: 0.66, 0.73), while the slope of the calibration curve was 1.1 (95% CI: 0.9, 1.2).

CONCLUSIONS

We developed a promising clinical prediction instrument, the IVI-RPT, that categorizes individuals into risk groups with increasing probabilities of violent injury. External validation of this tool is required prior to clinical practice implementation.

The Global Pregnancy Collaboration (CoLab) symposium on short- and long-term outcomes in offspring whose mothers had preeclampsia: A scoping review of clinical evidence

Preeclampsia is a maternal syndrome characterized by the new onset of hypertension after 20 weeks of gestation associated with multisystemic complications leading to high maternal and fetal/neonatal morbidity and mortality. However, sequelae of preeclampsia may extend years after pregnancy in both mothers and their children. In addition to the long-term adverse cardiovascular effects of preeclampsia in the mother, observational studies have reported elevated risk of cardiovascular, metabolic, cerebral and cognitive complications in children born from women with preeclampsia. Less clear is whether the association between maternal preeclampsia and offspring sequelae are causal, or to what degree the associations might be driven by fetal factors including impaired growth and the health of its placenta. Our discussion of these complexities in the 2018 Global Pregnancy Collaboration annual meeting prompted us to write this review. We aimed to summarize the evidence of an association between maternal preeclampsia and neurobehavioral developmental disorders in offspring in hopes of generating greater research interest in this important topic.

Determinants of anemia status among pregnant women in ethiopia: using 2016 ethiopian demographic and health survey data; application of ordinal logistic regression models

Background

Anemia is a serious public health problem that occurs when the blood contains fewer red blood cells than normal. In Ethiopia, the prevalence of anemia in pregnancy increased between 2005 and 2016. The aim of this study was to determine what factors influence the anemia status of pregnant women in Ethiopia.

Methods

Anemia status in a sample of 1053 pregnant women was studied using data from Ethiopia's Demographic and Health Survey 2016. Percentages and graphs were used to show the prevalence of anemia. The marginal probability effect was used to determine the contribution of each explanatory variable category to a single response category of anemia level. Ordinal logistic regression models were constructed, and the best-fitting model was selected to reveal significant anemia status variables.

Results

The prevalence of anemia in pregnant women was found to be 37.51% (3.04% severe, 17.28% moderate, and 17.1% mild anemic). The fitted partial proportional odds model revealed that anemia status of pregnant women was significantly associated with region afar (OR = 0.45; CI: 0.21–0.96), antenatal care visits above 4 (OR = 1.58; CI: 1.03–2.43), parity between 1–2 (OR = 0.47;CI: 0.26–0.85), iron taking (OR = 3.68;CI: 2.41–5.64), and higher education (OR = 4.75;CI: 2.29–9.85).

Conclusions

Anemia among pregnant women has been identified as a moderate public health issue in Ethiopia. The study revealed that the prevalence of anemia varied among regions which the highest (65.9%) and the lowest (9%) being from Somali and Addis Ababa, respectively. As a result, it is argued that treatments target iron consumption, maternal education, antenatal visits, and mothers' access to health care.

Prediction of Relapse After Anti-Tumor Necrosis Factor Cessation in Crohn's Disease: Individual Participant Data Meta-analysis of 1317 Patients From 14 Studies

BACKGROUND & AIMS

Tools for stratification of relapse risk of Crohn's disease (CD) after anti-tumor necrosis factor (TNF) therapy cessation are needed. We aimed to validate a previously developed prediction model from the diSconTinuation in CrOhn's disease patients in stable Remission on combined therapy with Immunosuppressants (STORI) trial, and to develop an updated model.

METHODS

Cohort studies were selected that reported on anti-TNF cessation in 30 or more CD patients in remission. Individual participant data were requested for luminal CD patients and anti-TNF treatment duration of 6 months or longer. The discriminative ability (concordance-statistic [C-statistic]) and calibration (agreement between observed and predicted risks) were explored for the STORI model. Next, an updated prognostic model was constructed, with performance assessment by cross-validation.

RESULTS

This individual participant data meta-analysis included 1317 patients from 14 studies in 11 countries. Relapses after anti-TNF cessation occurred in 632 of 1317 patients after a median of 13 months. The pooled 1-year relapse rate was 38%. The STORI prediction model showed poor discriminative ability (C-statistic, 0.51). The updated model reached a moderate discriminative ability (C-statistic, 0.59), and included clinical symptoms at cessation (hazard ratio [HR], 2.2; 95% CI, 1.2-4), younger age at diagnosis (HR, 1.5 for A1 (age at diagnosis ≤16 years) vs A2 (age at diagnosis 17 - 40 years); 95% CI, 1.11-1.89), no concomitant immunosuppressants (HR, 1.4; 95% CI, 1.18-172), smoking (HR, 1.4; 95% CI, 1.15-1.67), second line anti-TNF (HR, 1.3; 95% CI, 1.01-1.69), upper gastrointestinal tract involvement (HR, 1.3 for L4 vs non-L4; 95% CI, 0.96-1.79), adalimumab (HR, 1.22 vs infliximab; 95% CI, 0.99-1.50), age at cessation (HR, 1.2 per 10 years younger; 95% CI, 1-1.33), C-reactive protein (HR, 1.04 per doubling; 95% CI, 1.00-1.08), and longer disease duration (HR, 1.07 per 5 years; 95% CI, 0.98-1.17). In subanalysis, the discriminative ability of the model improved by adding fecal calprotectin (C-statistic, 0.63).

CONCLUSIONS

This updated prediction model showed a reasonable discriminative ability, exceeding the performance of a previously published model. It might be useful to guide clinical decisions on anti-TNF therapy cessation in CD patients after further validation.

A Bioinformatics Approach to MicroRNA-Sequencing Analysis Based on Human Saliva Samples of Patients with Endometriosis

Endometriosis, defined by the presence of endometrium-like tissue outside the uterus, affects 2–10% of the female population, i.e., around 190 million women, worldwide. The aim of the prospective ENDO-miRNA study was to develop a bioinformatics approach for microRNA-sequencing analysis of 200 saliva samples for miRNAome expression and to test its diagnostic accuracy for endometriosis. Among the 200 patients, 76.5% (n = 153) had confirmed endometriosis and 23.5% (n = 47) had no endometriosis (controls). Small RNA-seq of 200 saliva samples yielded ~4642 M raw sequencing reads (from ~13.7 M to ~39.3 M reads/sample). The number of expressed miRNAs ranged from 1250 (outlier) to 2561 per sample. Some 2561 miRNAs were found to be differentially expressed in the saliva samples of patients with endometriosis compared with the control patients. Among these, 1.17% (n = 30) were up- or downregulated. Among these, the F1-score, sensitivity, specificity, and AUC ranged from 11–86.8%, 5.8–97.4%, 10.6–100%, and 39.3–69.2%, respectively. Here, we report a bioinformatic approach to saliva miRNA sequencing and analysis. We underline the advantages of using saliva over blood in terms of ease of collection, reproducibility, stability, safety, non-invasiveness. This report describes the whole saliva transcriptome to make miRNA quantification a validated, standardized, and reliable technique for routine use. The methodology could be applied to build a saliva signature of endometriosis.