Prospective Validation Research Articles

Recent developments in machine learning modeling methods for hypertension treatment.

Hypertension is the leading cause of cardiovascular complications. This review focuses on the advancements in medical artificial intelligence (AI) models aimed at individualized treatment for hypertension, with particular emphasis on the approach to time-series big data on blood pressure and the development of interpretable medical AI models. The digitalization of daily blood pressure records and the downsizing of measurement devices enable the accumulation and utilization of time-series data. As mainstream blood pressure data shift from snapshots to time series, the clinical significance of blood pressure variability will be clarified. The time-series blood pressure prediction model demonstrated the capability to forecast blood pressure variabilities with a reasonable degree of accuracy for up to four weeks in advance. In recent years, various explainable AI techniques have been proposed for different purposes of model interpretation. It is essential to select the appropriate technique based on the clinical aspects; for example, actionable path-planning techniques can present individualized intervention plans to efficiently improve outcomes such as hypertension. Despite considerable progress in this field, challenges remain, such as the need for the prospective validation of AI-driven interventions and the development of comprehensive systems that integrate multiple AI methods. Future research should focus on addressing these challenges and refining the AI models to ensure their practical applicability in real-world clinical settings. Furthermore, the implementation of interdisciplinary collaborations among AI experts, clinicians, and healthcare providers are crucial to further optimizing and validate AI-driven solutions for hypertension management.

Ophthalmic artery Doppler at 36 weeks' gestation in prediction of pre-eclampsia: validation and update of previous model.

To validate and extend a model incorporating maternal ophthalmic artery Doppler at 35-37 weeks' gestation in the prediction of subsequent development of pre-eclampsia (PE). This was a prospective validation study of screening for PE (defined according to the 2019 American College of Obstetricians and Gynecologists criteria) by maternal ophthalmic artery peak systolic velocity (PSV) ratio in 6746 singleton pregnancies undergoing routine care at 35 + 0 to 36 + 6 weeks' gestation (validation dataset). Additionally, the data from the validation dataset were combined with those of 2287 pregnancies that were previously used for development of the model (training dataset), and the combined data were used to update the original model parameters. The competing-risks model was used to estimate the individual patient-specific risk of delivery with PE at any time and within 3 weeks from assessment by a combination of maternal demographic characteristics and medical history with PSV ratio alone and in combination with the established PE biomarkers of mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI), serum placental growth factor (PlGF) and serum soluble fms-like tyrosine kinase-1 (sFlt-1). We evaluated the predictive performance of the model by examining, first, the ability to discriminate between the PE and non-PE groups using the area under the receiver-operating-characteristics curve and the detection rate (DR) at fixed screen-positive (SPR) and false-positive rates of 10% and, second, calibration by measuring the calibration slope and calibration-in-the-large. McNemar's test was used to compare the performance of screening by a biophysical test (maternal factors, MAP, UtA-PI and PSV ratio) vs a biochemical test (maternal factors, PlGF and sFlt-1), low PlGF concentration (< 10th percentile) or high sFlt-1/PlGF concentration ratio (> 90th percentile). In the validation dataset, the performance of screening by maternal factors and PSV ratio for delivery with PE within 3 weeks and at any time after assessment was consistent with that in the training dataset, and there was good agreement between the predicted and observed incidence of PE. In the combined data from the training and validation datasets, good prediction for PE was achieved in screening by a combination of maternal factors, MAP, UtA-PI, PlGF, sFlt-1 and PSV ratio, with a DR, at a 10% SPR, of 85.0% (95% CI, 76.5-91.4%) for delivery with PE within 3 weeks and 65.7% (95% CI, 59.2-71.7%) for delivery with PE at any time after assessment. The performance of a biophysical test was superior to that of screening by low PlGF concentration or high sFlt-1/PlGF concentration ratio but not significantly different from the performance of a biochemical test combining maternal factors with PlGF and sFlt-1 for both PE within 3 weeks and PE at any time after assessment. Maternal ophthalmic artery PSV ratio at 35-37 weeks' gestation in combination with other biomarkers provides effective prediction of subsequent development of PE. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Accuracy of Smartwatch Electrocardiographic Recording in the Acute Coronary Syndrome Setting: Rationale and Design of the ACS WATCH II Study.

Background: Acute Coronary Syndrome (ACS), with or without ST-segment elevation, is a major contributor to global mortality and morbidity. Swift diagnosis and treatment are vital for mitigating cardiac damage and improving long-term outcomes. The 12-lead electrocardiogram (ECG) currently serves as the gold standard for diagnosis in ACS with ST-segment elevation and may support the diagnosis in ACS without ST-segment elevation. However, the growing prevalence of smartwatches enables the acquisition of electrocardiographic data without traditional ECG equipment. While smaller studies support smartwatch ECG use, larger-scale validation within ACS remains lacking. The ACS WATCH II study aims to validate smartwatch ECG recordings for ACS. Methods: The primary objective is to validate smartwatch-obtained electrocardiographic data in patients presenting with ACS. Two cohorts of 120 patients each, presenting ACS with and without ST-segment elevation, will be assessed. Smartwatches will capture recordings of leads I, III, and V2 alongside standard ECGs. These leads, chosen due to a 97% ACS diagnosis sensitivity in previous studies, will undergo blind evaluation by two experienced external assessors against conventional ECG. Additionally, a control sample of 60 healthy individuals will be included. Conclusions: ACS WATCH II pioneers large-scale prospective validation of smartwatch ECG recordings in ACS patients. Additionally, it indirectly validates a swift diagnostic approach using three leads (I, III, and V2). This could expedite time-critical ACS diagnoses and simplify access through smartwatch-based diagnosis.

Abnormal preoperative haematological parameters in Endometrial cancer; reflecting tumour aggressiveness or reduced response to radiotherapy?

Background In endometrial cancer (EC), preoperative anaemia, thrombocytosis and leucocytosis appear to be associated with worse prognosis. It remains unclear whether these parameters solely reflect tumour aggressiveness, or also impact response to adjuvant treatment. Therefore, our primary aim is to evaluate the prognostic relevance of anaemia, thrombocytosis and leucocytosis on survival in EC. Secondary, to explore their predictive relevance in response to radiotherapy in EC. Methods A retrospective multicentre cohort study was performed within 10 hospitals. Preoperative haematological parameters were defined as: Anaemia – haemoglobin <7.45 mmol/L (<12 g/Dl), thrombocytosis – platelets >400 × 109 platelets/L, leucocytosis – leukocytes >10 × 109/L. The relationship of haematological parameters with clinicopathological characteristics, ESGO/ESTRO/ESP risk groups and survival were evaluated. Furthermore, the predictive value of haematological parameters was determined on the overall response to adjuvant radiotherapy and for the ESGO/ESTRO/ESP intermediate-risk group solely receiving radiotherapy. Results A total of 894 patients were included with a median follow-up of 4.5 years. Anaemia was present in 103 (11.5%), thrombocytosis in 79 (8.8%) and leucocytosis in 114 (12.7%) patients. The presence of anaemia or thrombocytosis was significantly associated with ESGO/ESTRO/ESP high-risk (respectively, P = 0.002 and P = 0.041). In the entire cohort, anaemia remained independently associated with decreased disease-specific survival (HR 2.31, 95% CI (1.19–4.50), P = 0.013) after adjusting for age, the abnormal haematological parameters and ESGO/ESTRO/ESP risk groups. In patients that were treated with adjuvant radiotherapy (n = 239), anaemia was associated with significant reduced 5-year disease-specific and recurrence-free survival (P = 0.005 and P = 0.025, respectively). In ESGO/ESTRO/ESP intermediate risk patients that received solely vaginal brachytherapy (n = 74), anaemia was associated with reduced disease-specific survival (P = 0.041). Conclusions Current data demonstrate the importance of preoperative anaemia as independent prognostic factor in patients with EC. Moreover, anaemia seems to be associated with reduced response to radiotherapy. Prospective validation in a larger study cohort is needed to verify anaemia as predictive biomarker for radiotherapy. What is already known on this subject? In endometrial cancer, preoperative abnormal haematological parameters like, anaemia, thrombocytosis and leucocytosis appears to be associated with FIGO advanced-stage and unfavourable outcome. What do the results of this study add? It remains unclear whether anaemia, thrombocytosis or leucocytosis solely reflecting worse prognosis by advanced tumour stage, or also impact response to adjuvant treatment. Current data demonstrate that anaemia is independent associated with decreased disease-specific survival and anaemia seems related with reduced response to radiotherapy and in specific to vaginal brachytherapy in ESGO/ESTRO/ESP intermediate risk patients. What are the implications of these findings for clinical practice and/or further research? Specific applied adjuvant treatment is needed if patients with anaemia have a reduced response to radiotherapy in EC. Prospective validation in a larger study cohort is required to verify anaemia as predictive biomarker for radiotherapy and to further evaluate the prognostic/predictive impact of anaemia in addition to the molecular subgroups.

Determining Pneumocystis jirovecii Colonisation from Infection Using PCR-Based Diagnostics in HIV-Negative Individuals.

Pneumocystis jirovecii pneumonia is increasingly diagnosed with highly sensitive PCR diagnostics in immunocompromised, HIV-negative individuals. We assessed the performance of our in-house quantitative PCR with the aim to optimise interpretation. Retrospective audit of all positive P. jirovecii qPCRs on induced sputum or BAL fluid at a single centre from 2012 to 2023. Medical and laboratory records were analysed and people with HIV were excluded. Cases were categorised as colonisation, high-probability PCP or uncertain PCP infection against a clinical gold standard incorporating clinico-radiological data. Quantitative PCR assay targeting the 5s gene was utilised throughout the time period. Of the 82 positive qPCRs, 28 were categorised as high-probability PCP infection, 30 as uncertain PCP and 24 as colonisation. There was a significant difference in qPCR values stratified by clinical category but not respiratory sample type. Current assay performance with a cutoff of 2.5 × 105 copies/mL had a sensitivity of 50% (95% CI, 30.65-69.35%) and specificity of 83.33% (95% CI, 62.62-95.26%). Youden Index calculated at 6.5 × 104 copies/mL had a sensitivity of 75% (56.64-87.32%, 95% CI) and specificity of 66.67% (46.71-82.03%, 95% CI). High and low cutoffs were explored. Significant variables associated with infection were age > 70 years old, the presence of fever, hypoxia or ground glass changes. A single qPCR cutoff cannot reliably determine P. jirovecii infection from colonisation. Low and high cutoffs are useful, however, a large "possible infection" cohort will remain where interpretation of clinic-radiological factors remains essential. Standardisation of assays with prospective validation in specific immunocompromised groups will allow greater generalisability and allow large-scale prospective assay validation to be performed.

Pulmonary Computed Tomography Screening Frequency in Primary Antibody Deficiency

BackgroundPatients with primary antibody deficiency (PAD) frequently suffer from pulmonary complications, associated with severe morbidity and mortality. Hence, regular pulmonary screening by computed tomography (CT) scanning is advised. However, predictive risk factors for pulmonary morbidity are lacking. ObjectiveTo identify PAD patients at risk for pulmonary complications necessitating regular CT screening. MethodsA retrospective longitudinal cohort study of PAD patients (median follow-up 7.4 (2.3 – 14.8) years). CTs were scored using the modified Brody-II scoring system. Clinical and laboratory parameters were retrospectively collected. Potential risk factors were identified by univariate analysis when p<0.2 and confirmed by multivariable logistic regression when p<0.05. ResultsThe following independent risk factors for progression of airway disease (AD) were identified: 1) diagnosis of X-linked agammaglobulinemia (XLA), 2) recurrent airway infections (2.5/year), 3) presence of AD at baseline. Signs of AD progression were detected in 5/11 XLA patients and in 17/80 of the other PAD patients. Of the patients who progressed, 17/22 had preexistent AD scores ≥7.0%. Increased AD scores were related to poorer FEV1 values and chronic cough. CVID and increased CD4 effector/memory cells were risk factors for an interstitial lung disease (ILD) score ≥13.0%. ILD ≥13.0% occurred in 12/80 patients. Signs of ILD progression were detected in 8/80 patients and 4/8 patients showing progression had preexistent ILD scores ≥13.0%. ConclusionWe identified risk factors that distinguished PAD patients at risk for airway disease and interstitial lung disease presence and progression which could guide future screening frequency, however independent and preferably prospective validation is needed.

Development of a Novel Biomarker for the Progression of Idiopathic Pulmonary Fibrosis.

The progression of idiopathic pulmonary fibrosis (IPF) is diverse and unpredictable. We identified and validated a new biomarker for IPF progression. To identify a candidate gene to predict progression, we assessed differentially expressed genes in patients with advanced IPF compared with early IPF and controls in three lung sample cohorts. Candidate gene expression was confirmed using immunohistochemistry and Western blotting of lung tissue samples from an independent IPF clinical cohort. Biomarker potential was assessed using an enzyme-linked immunosorbent assay of serum samples from the retrospective validation cohort. We verified that the final candidate gene reflected the progression of IPF in a prospective validation cohort. In the RNA-seq comparative analysis of lung tissues, CD276, COL7A1, CTSB, GLI2, PIK3R2, PRAF2, IGF2BP3, and NUPR1 were up-regulated, and ADAMTS8 was down-regulated in the samples of advanced IPF. Only CTSB showed significant differences in expression based on Western blotting (n = 12; p < 0.001) and immunohistochemistry between the three groups of the independent IPF cohort. In the retrospective validation cohort (n = 78), serum CTSB levels were higher in the progressive group (n = 25) than in the control (n = 29, mean 7.37 ng/mL vs. 2.70 ng/mL, p < 0.001) and nonprogressive groups (n = 24, mean 7.37 ng/mL vs. 2.56 ng/mL, p < 0.001). In the prospective validation cohort (n = 129), serum CTSB levels were higher in the progressive group than in the nonprogressive group (mean 8.30 ng/mL vs. 3.00 ng/mL, p < 0.001). After adjusting for baseline FVC, we found that CTSB was independently associated with IPF progression (adjusted OR = 2.61, p < 0.001). Serum CTSB levels significantly predicted IPF progression (AUC = 0.944, p < 0.001). Serum CTSB level significantly distinguished the progression of IPF from the non-progression of IPF or healthy control.

Translating the potential of the urine steroid metabolome to stage NAFLD (TrUSt-NAFLD): study protocol for a multicentre, prospective validation study

IntroductionNon-alcoholic fatty liver disease (NAFLD) affects approximately one in four individuals and its prevalence continues to rise. The advanced stages of NAFLD with significant liver fibrosis are associated with adverse...

Simple versus radical cholecystectomy and survival for pathologic stage T1B gallbladder cancer

BackgroundRadical cholecystectomy is recommended for T1B and greater gallbladder cancer, however, there are conflicting reports on the utility of extended resection for T1B disease. Herein, we characterize outcomes following simple and radical cholecystectomy for pathologic stage T1B gallbladder cancer. MethodsThe National Cancer Database (NCDB) was queried for patients with pathologic T1B gallbladder cancer diagnosed from 2004 to 2018. Patients were stratified by surgical management. Overall survival (OS) was compared with Kaplan–Meier and multivariable Cox proportional hazards methods. ResultsAltogether, 950 patients were identified with pathologic T1B gallbladder cancer: 187 (19.7 %) receiving simple and 763 (80.3 %) radical cholecystectomy. Median OS was 89.5 (95 % CI 62.5–137) and 91.4 (95 % CI 75.9–112) months for simple and radical cholecystectomy, respectively (log-rank p = 0.55). Receipt of simple cholecystectomy was not associated with greater hazard of mortality compared to radical cholecystectomy (HR 1.23, 95 % CI 0.95–1.59, p = 0.12). DiscussionIn this analysis, we report comparable outcomes with simple cholecystectomy among patients with pathologic T1B gallbladder cancer. These findings suggest that highly selected patients, such as those with R0 resection and imaging at low risk for residual disease and/or nodal metastasis, may not benefit from extended resection; however, radical cholecystectomy remains standard of care until prospective validation can be achieved.

Validation of an established TW3 artificial intelligence bone age assessment system: a prospective, multicenter, confirmatory study.

In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using a convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, upon which our study is based, lacked a gold standard for comparison and had not undergone thorough evaluation in different working environments. To further verify the applicability of the AI system in clinical bone age assessment (BAA) and to enhance the accuracy and homogeneity of BAA, a prospective multi-center validation was conducted. This study utilized 744 left-hand radiographs of patients, ranging from 1 to 20 years of age, with 378 boys and 366 girls. These radiographs were obtained from nine different children's hospitals between August and December 2020. The BAAs were performed using the TW3 AI system and were also reviewed by experienced reviewers. Bone age accuracy within 1 year, root mean square error (RMSE), and mean absolute error (MAE) were statistically calculated to evaluate the accuracy. Kappa test and Bland-Altman (B-A) plot were conducted to measure the diagnostic consistency. The system exhibited a high level of performance, producing results that closely aligned with those of the reviewers. It achieved a RMSE of 0.52 years and an accuracy of 94.55% for the radius, ulna, and short bones series. When assessing the carpal series of bones, the system achieved a RMSE of 0.85 years and an accuracy of 80.38%. Overall, the system displayed satisfactory accuracy and RMSE, particularly in patients over 7 years old. The system excelled in evaluating the carpal bone age of patients aged 1-6. Both the Kappa test and B-A plot demonstrated substantial consistency between the system and the reviewers, although the model encountered challenges in consistently distinguishing specific bones, such as the capitate. Furthermore, the system's performance proved acceptable across different genders and age groups, as well as radiography instruments. In this multi-center validation, the system showcased its potential to enhance the efficiency and consistency of healthy delivery, ultimately resulting in improved patient outcomes and reduced healthcare costs.

987 Prospective validation of an automated Peripartum Risk Score Model to predict severe maternal morbidity (SMM)

987 Prospective validation of an automated Peripartum Risk Score Model to predict severe maternal morbidity (SMM)

Determination and prospective validation of cut-off values for the diagnosis of liver cirrhosis for point shear-wave elastography/acoustic radiation force impulse imaging using the ACUSON Sequoia ultrasound system.

Point shear-wave elastography (pSWE) alias acoustic radiation force impulse (ARFI) imaging is a well-established ultrasound-based technique for the non-invasive assessment of liver tissue stiffness. As cut-off values for liver cirrhosis cannot be transferred from one ultrasound system to another, this study aimed at determining cut-off values for the newly developed Siemens ACUSON Sequoia ultrasound system. In a pilot study phase, two independent examiners conducted 10 pSWE measurements in an elasticity phantom and 32 healthy individuals for the determination of inter-examiner agreement. Afterwards, 22 cirrhotic patients and 57 patients with chronic liver disease undergoing liver biopsy underwent pSWE. Patient characteristics and stiffness values were compared for individuals with and without liver cirrhosis. Diagnostic accuracies of cut-off values for the diagnosis of liver cirrhosis were calculated using areas under the receiver operating characteristics analysis and Youden's index. In a subsequent validation study phase, these cut-off values were validated prospectively in 107 cirrhotic and 68 non-cirrhotic patients. Inter-examiner agreement was excellent for measurements in the elasticity phantom (intra-class correlation coefficient [ICC] = 0.998; P < 0.001), and good for measurements in patients (ICC = 0.844; P < 0.001). The best cut-off value for the diagnosis of liver cirrhosis was 1.405 m/s with an AUC of 0.872, a sensitivity of 88.2% and a specificity of 88.2% (P < 0.001). ARFI elastography using the Siemens ACUSON Sequoia showed a good inter-examiner agreement. The optimal cut-off value was lower than the cut-off values described for former generations of ultrasound devices. These preliminary results should be confirmed in larger patient collectives with histology as the reference standard.

Pulmonary embolism risk stratification: external validation of the 4-level Clinical Pretest Probability Score (4PEPS)

BackgroundThe 4-level clinical pretest probability score (4PEPS) was recently introduced as a clinical decision rule for the diagnosis of pulmonary embolism (PE). Based on the score, patients are classified into clinical pretest probability categories (c-PTP). The “very low” category aims at excluding PE without further testing; “low” and “moderate” categories require D-dimer testing with specific thresholds, while patients with a “high” pretest directly proceed to imaging. ObjectivesTo provide further external validation of the 4PEPS model. MethodsThe 4PEPS was applied to a previously collected prospective database of 756 patients with clinically suspected PE enrolled from European emergency departments in 2002 to 2003. The safety threshold for the failure rate in our study was calculated at 1.95% based on a 26% prevalence of PE in our study, as per the International Society on Thrombosis and Haemostasis Scientific and Standardization Committee guidance. ResultsPatients were classified as follows: 90 (12%) in the very low c-PTP group, of whom 5 (5.6%; 95% CI, 2.4%-12.4%) had PE; 363 (49%) in the low c-PTP group, of whom 34 had PE (9.4%); 246 (34%) in the moderate c-PTP group, of whom 124 (50%) had PE; and 35 (5%) in the high c-PTP group of whom 30 (86%) had PE. Overall, the failure rate of the 4PEPS was 9/734 (1.2%; 95% CI, 0.59%-2.23%) Overall, 9 out of 734 patients (1.2%; 95% CI, 0.59%-2.23%) were diagnosed with PE despite a negative 4PEPS rule; 5 (5.6%) from the very low c-PTP group, 3 (1.4%) in the low c-PTP group, and 1 (3.2%) in the moderate c-PTP group. ConclusionWe provide external validation data of the 4PEPS. In this high-prevalence cohort (26% prevalence), PE prevalence in the very low-risk group was higher than expected. A prospective validation study is needed before implementing the 4PEPS model in routine clinical practice.

Optically Guided High-Frequency Ultrasound Shows Superior Efficacy for Preoperative Estimation of Breslow Thickness in Comparison with Multispectral Imaging: A Single-Center Prospective Validation Study.

Melanoma is the most aggressive form of skin cancer that is known for its metastatic potential and has an increasing incidence worldwide. Breslow thickness, which determines the staging and surgical margin of the tumor, is unavailable at initial diagnosis. Novel imaging techniques for assessing Breslow thickness lack comparative data. This study evaluates optically guided high-frequency ultrasound (OG-HFUS) and multispectral imaging (MSI) for preoperative estimation of Breslow thickness and staging. We enrolled 101 patients with histologically confirmed primary melanoma and categorized them based on tumor thickness. Optically guided 33 MHz HFUS and MSI were utilized for the assessment. Our MSI-based algorithm categorized melanomas into three subgroups with a sensitivity of 62.6%, specificity of 81.3%, and fair agreement (κ = 0.440, CI: 0.298-0.583). In contrast, OG-HFUS demonstrated a sensitivity of 91.8%, specificity of 96.0%, and almost perfect agreement (κ = 0.858, CI: 0.763-0.952). OG-HFUS performed better than MSI in estimating Breslow thickness, emphasizing its potential as a valuable tool for melanoma diagnosis and patient management. OG-HFUS holds promise for enhancing preoperative staging and treatment decision-making in melanoma.

Adding a Coefficient for Race to the 4Kscore Improves Calibration for Black Men.

Black men face a higher incidence of high-risk prostate cancer (PCa) compared with non-Black men. While the 4Kscore is a widely utilized commercial test for PCa risk assessment, it does not currently account for racial differences. The aim of this study is to describe and validate a prespecified race coefficient for the 4Kscore with the goal of improving the accuracy of this test for Black men. Using data from 85 Black men from the initial US prospective validation study, a race coefficient of 0.6 on the log-odds scale was prespecified. We calculated discrimination, calibration, and clinical utility of the 4Kscore with and without this coefficient for Black race in our primary analysis cohort of 205 Black men undergoing biopsy for PCa in a Veterans Affairs (VA) institution. We performed a sensitivity analysis using a combined cohort from the US prospective validation and the VA studies. The mean probability of high-grade PCa from the 4Kscore in the primary cohort increased from 25% to 37% with race coefficient addition. Incorporating the race coefficient improved 4Kscore's calibration in Black men, with consequent improvements in clinical utility based on decision curve analysis. Model discrimination was maintained (AUC 0.825 vs 0.828, P = .14) in the combined cohort of Black and non-Black men from the US prospective and VA studies and the calibration remained largely unchanged. Incorporating a prespecified coefficient for Black race improved calibration and clinical utility of the 4Kscore among Black men and should be added to the 4Kscore.

New postoperative pain instrument for toddlers-Secondary analysis of prospectively collected assessments after tonsil surgery.

The Children's and Infant's Postoperative Pain Scale (CHIPPS) and the German version of the Parent's Postoperative Pain Measure (PPPM-D) are used to assess postoperative pain intensity in preschool children. However, they have shown low concordance in previous prospective studies on quality improvement. Our secondary analysis aimed to estimate the association strength between the pain score items and indication for rescue medication defined as CHIPPS ≥4 and/or PPPD-D ≥ 6. Thus, we intended to create a further developed pain instrument with fewer variables for easier routine use. We analyzed 1067 pain intensity assessments of hospitalized children for the development of our novel tool in two steps using modern statistical and machine-learning methods: (1) Boruta variable selection to analyze the association strength between CHIPPS score, PPPM-D items, age, weight, and elapsed time after surgery, including their interactions and pattern stability, and the binary outcome (analgesics required yes/no). (2) Symbolic regression to generate a short formula with the least number of variables and highest accuracy for rescue medication indication. Additional analgesics were required in 19.96% of pain intensity assessments, whereby the PPPM-D showed higher variance than CHIPPS. Boruta identified PPPM-D score, CHIPPS score, 9 of the 15 PPPM-D variables, and time of assessment as associated with the indication for RM. Symbolic regression revealed that additional analgesics are required if CHIPPS is ≥4 OR PPPM-D item "less energy than usual" AND one of the items "more easily cry" or "more groan/moan" are answered with "yes." These PPPM-D items were not redundant and showed nonlinear course over time. The cross-validated accuracy for this assessment tool was 94.94%. The new instrument is easy to use and may improve postoperative pain intensity assessment in children. However, it requires prospective validation in a new cohort.

Correlation Between Rod Fracture and Shear Stress: A Novel Parameter

We sought to assess the accuracy of a novel parameter proportional to the rod shear stress (RSS) in identifying patients at risk of rod fracture (RF) after surgery for correction of adult spinal deformity. We performed a retrospective medical record review of patients aged ≥18 years treated for adult spinal deformity between 2004 and 2014 with ≥24 months of follow-up. The primary outcome was RFs identified radiographically. Patient weight (w), number of instrumented levels (N), and minimum rod diameter (d) were recorded and used to calculate the RSS parameter (RSS=Nwd2). Receiver operating characteristic curves were produced and the area under the curve (AUC ± 95% confidence interval [CI]) was calculated to compare this parameter's discriminative accuracy to that of its constituent variables. The sensitivity, specificity, and likelihood ratios (LRs) were calculated. A total of 28 RF-positive and 154 RF-negative patients were included. The average age was 59.2 ± 9.6 years, and 93.4% were women. The RSS parameter produced the greatest AUC (0.73 ± 0.11). At an RSS cutoff of 30.1, it achieved a sensitivity of 71.4% and specificity of 71.4% (LR, 2.5; 95% CI, 1.8-3.5). The number of instrumented levels produced the next-greatest AUC (0.65 ± 0.12), with a sensitivity of 78.6% and specificity of 50.0% at a cutoff of 15 (LR, 1.6; 95% CI, 1.2-2.0). The RSS is calculated using easily obtainable information and shows potential as a tool for predicting patient-specific risk of RF after spinal fusion. The number of instrumented levels also correlates strongly with the occurrence of RFs and is not significantly less accurate than the RSS. A larger sample size and prospective validation would be useful in determining with greater confidence which parameter is superior for predicting RFs after spinal fusion.

Machine learning based outcome prediction of microsurgically treated unruptured intracranial aneurysms

Machine learning (ML) has revolutionized data processing in recent years. This study presents the results of the first prediction models based on a long-term monocentric data registry of patients with microsurgically treated unruptured intracranial aneurysms (UIAs) using a temporal train-test split. Temporal train-test splits allow to simulate prospective validation, and therefore provide more accurate estimations of a model’s predictive quality when applied to future patients. ML models for the prediction of the Glasgow outcome scale, modified Rankin Scale (mRS), and new transient or permanent neurological deficits (output variables) were created from all UIA patients that underwent microsurgery at the Kepler University Hospital Linz (Austria) between 2002 and 2020 (n = 466), based on 18 patient- and 10 aneurysm-specific preoperative parameters (input variables). Train-test splitting was performed with a temporal split for outcome prediction in microsurgical therapy of UIA. Moreover, an external validation was conducted on an independent external data set (n = 256) of the Department of Neurosurgery, University Medical Centre Hamburg-Eppendorf. In total, 722 aneurysms were included in this study. A postoperative mRS > 2 was best predicted by a quadratic discriminant analysis (QDA) estimator in the internal test set, with an area under the receiver operating characteristic curve (ROC-AUC) of 0.87 ± 0.03 and a sensitivity and specificity of 0.83 ± 0.08 and 0.71 ± 0.07, respectively. A Multilayer Perceptron predicted the post- to preoperative mRS difference > 1 with a ROC-AUC of 0.70 ± 0.02 and a sensitivity and specificity of 0.74 ± 0.07 and 0.50 ± 0.04, respectively. The QDA was the best model for predicting a permanent new neurological deficit with a ROC-AUC of 0.71 ± 0.04 and a sensitivity and specificity of 0.65 ± 0.24 and 0.60 ± 0.12, respectively. Furthermore, these models performed significantly better than the classic logistic regression models (p < 0.0001). The present results showed good performance in predicting functional and clinical outcomes after microsurgical therapy of UIAs in the internal data set, especially for the main outcome parameters, mRS and permanent neurological deficit. The external validation showed poor discrimination with ROC-AUC values of 0.61, 0.53 and 0.58 respectively for predicting a postoperative mRS > 2, a pre- and postoperative difference in mRS > 1 point and a GOS < 5. Therefore, generalizability of the models could not be demonstrated in the external validation. A SHapley Additive exPlanations (SHAP) analysis revealed that this is due to the most important features being distributed quite differently in the internal and external data sets. The implementation of newly available data and the merging of larger databases to form more broad-based predictive models is imperative in the future.

Proteomics-driven noninvasive screening of circulating serum protein panels for the early diagnosis of hepatocellular carcinoma

Early diagnosis of hepatocellular carcinoma (HCC) lacks highly sensitive and specific protein biomarkers. Here, we describe a staged mass spectrometry (MS)-based discovery-verification-validation proteomics workflow to explore serum proteomic biomarkers for HCC early diagnosis in 1002 individuals. Machine learning model determined as P4 panel (HABP2, CD163, AFP and PIVKA-II) clearly distinguish HCC from liver cirrhosis (LC, AUC 0.979, sensitivity 0.925, specificity 0.915) and healthy individuals (HC, AUC 0.992, sensitivity 0.975, specificity 1.000) in an independent validation cohort, outperforming existing clinical prediction strategies. Furthermore, the P4 panel can accurately predict LC to HCC conversion (AUC 0.890, sensitivity 0.909, specificity 0.877) with predicting HCC at a median of 11.4 months prior to imaging in prospective external validation cohorts (No.: Keshen 2018_005_02 and NCT03588442). These results suggest that proteomics-driven serum biomarker discovery provides a valuable reference for the liquid biopsy, and has great potential to improve early diagnosis of HCC.

The value of subcutaneous xenografts for individualised radiotherapy in HNSCC: Robust gene signature correlates with radiotherapy outcome in patients and xenografts

PurposeTo assess the robustness of prognostic biomarkers and molecular tumour subtypes developed for patients with head and neck squamous cell carcinoma (HNSCC) on cell-line derived HNSCC xenograft models, and to develop a novel biomarker signature by combining xenograft and patient datasets. Materials and methodsMice bearing xenografts (n = 59) of ten HNSCC cell lines and a retrospective, multicentre patient cohort (n = 242) of the German Cancer Consortium-Radiation Oncology Group (DKTK-ROG) were included. All patients received postoperative radiochemotherapy (PORT-C). Gene expression analysis was conducted using GeneChip Human Transcriptome Arrays. Xenografts were stratified based on their molecular subtypes and previously established gene classifiers. The dose to control 50 % of tumours (TCD50) was compared between these groups. Using differential gene expression analyses combining xenograft and patient data, a gene signature was developed to define risk groups for the primary endpoint loco-regional control (LRC). ResultsTumours of mesenchymal subtype were characterized by a higher TCD50 (xenografts, p < 0.001) and lower LRC (patients, p < 0.001) compared to the other subtypes. Similar to previously published patient data, hypoxia- and radioresistance-related gene signatures were associated with high TCD50 values. A 2-gene signature (FN1, SERPINE1) was developed that was prognostic for TCD50 (xenografts, p < 0.001) and for patient outcome in independent validation (LRC: p = 0.007). ConclusionGenetic prognosticators of outcome for patients after PORT-C and subcutaneous xenografts after primary clinically relevant irradiation show similarity. The identified robust 2-gene signature may help to guide patient stratification, after prospective validation. Thus, xenografts remain a valuable resource for translational research towards the development of individualized radiotherapy.