Search

The study aims to acquaint readers with six widely used machine learning (ML) techniques (Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), k-means, hierarchical clustering and the decision tree models (rpart and random forest)) that might be useful for the analysis of laboratory data.

Although there are several indirect methods that can be used to verify reference limits, they have a common weakness in that they assume a low proportion of pathological values. This paper investigates whether a Gaussian decomposition algorithm can identify the non-pathological fraction even if it is not the main subset of mixed data.

Reference intervals are indispensable for the interpretation of medical laboratory results to distinguish "normal" from "pathological" values. Recently, indirect methods have been published, which estimate reference intervals from a mixture of normal and pathological values based on certain statistical assumptions on the distribution of the values from the healthy population. Some analytes face the problem that a significant proportion of the measurements are below the limit of detection ( LOD ), meaning that there are no quantitative data for these values, only the information that they are smaller than the LOD . Standard statistical methods for reference interval estimation are not designed to incorporate values below the LOD . We propose two variants of the indirect method reflimR—a quantile- and maximum likelihood-based estimator—that are able to cope with values below the LOD . We show, based on theoretical analyses, simulation experiments, and real data, that our approach yields good estimates for the reference interval, even when the values below the LOD contribute a substantial proportion to the data. [ABSTRACT FROM AUTHOR]

The WHO Classification of Tumours (WCT) guides cancer diagnosis, treatment, and research. However, research evidence in pathology continuously changes, and new evidence emerges. Correct assessment of evidence in the WCT 5th edition (WCT-5) and identification of high level of evidence (LOE) studies based on study design are needed to improve future editions. We aimed at producing exploratory evidence maps for WCT-5 Thoracic Tumours, specifically lung and thymus tumors. We extracted citations from WCT-5, and imported and coded them in EPPI-Reviewer. The maps were plotted using EPPI-Mapper. Maps displayed tumor types (columns), descriptors (rows), and LOE (bubbles using a four-color code). We included 1434 studies addressing 51 lung, and 677 studies addressing 25 thymus tumor types from WCT-5 thoracic tumours volume. Overall, 87.7% (n = 1257) and 80.8% (n = 547) references were low, and 4.1% (n = 59) and 2.2% (n = 15) high LOE for lung and thymus tumors, respectively. Invasive non-mucinous adenocarcinoma of the lung (n = 215; 15.0%) and squamous cell carcinoma of the thymus (n = 93; 13.7%) presented the highest number of references. High LOE was observed for colloid adenocarcinoma of the lung (n = 11; 18.2%) and type AB thymoma (n = 4; 1.4%). Tumor descriptors with the highest number of citations were prognosis and prediction (n = 273; 19.0%) for lung, and epidemiology (n = 186; 28.0%) for thymus tumors. LOE was generally low for lung and thymus tumors. This study represents an initial step in the WCT Evidence Gap Map (WCT-EVI-MAP) project for mapping references in WCT-5 for all tumor types to inform future WCT editions. [ABSTRACT FROM AUTHOR]

Background/Objectives: We present a software package called reflimR (Version 1.0.6), which enables rapid and transparent verification of reference intervals from routine laboratory measurements. Our method makes it easy to compare the results with specified target values and facilitates the interpretation of deviations using traffic light colors. Methods: The algorithm includes three procedural steps: (a) definition of an appropriate distribution model, based on Bowley's quartile skewness, (b) iterative truncation, based on a modified boxplot method to obtain the central 95% of presumably inconspicuous results, and (c) extrapolation of reference limits from a truncated normal quantile–quantile plot. Results: All algorithms have been combined into one consolidated library, which can be called in the R environment with a single command reflim (x). Using an example dataset included in the package, we demonstrate that our method can be applied to mixed data containing a substantial proportion of pathological values. It leads to similar results as the direct guideline approach as well as the more sophisticated indirect refineR software package. As compared to the latter, reflimR works much faster and needs smaller datasets for robust estimates. For the interpretation of the results, we present an intuitive color scheme based on tolerance ranges (permissible uncertainty of laboratory results). We show that a relatively high number of published reference limits require careful reevaluation. Conclusions: The reflimR package closes the gap between direct guideline methods and the more sophisticated indirect refineR method. We recommend reflimR for the rapid routine verification of large amounts of reference limits and refineR for a careful analysis of unclear or doubtful results from this check. [ABSTRACT FROM AUTHOR]

BACKGROUND: Therapeutic possibilities for non-small cell lung cancer (NSCLC) have considerably increased during recent decades. OBJECTIVE: To summarize the prognostic relevance of serum tumor markers (STM) for early and late-stage NSCLC patients treated with classical chemotherapies, novel targeted and immune therapies. METHODS: A PubMed database search was conducted for prognostic studies on carcinoembryonic antigen (CEA), cytokeratin-19 fragment (CYFRA 21-1), neuron-specific enolase, squamous-cell carcinoma antigen, progastrin-releasing-peptide, CA125, CA 19-9 and CA 15-3 STMs in NSCLC patients published from 2008 until June 2022. RESULTS: Out of 1069 studies, 141 were identified as meeting the inclusion criteria. A considerable heterogeneity regarding design, patient number, analytical and statistical methods was observed. High pretherapeutic CYFRA 21-1 levels and insufficient decreases indicated unfavorable prognosis in many studies on NSCLC patients treated with chemo-, targeted and immunotherapies or their combinations in early and advanced stages. Similar results were seen for CEA in chemotherapy, however, high pretherapeutic levels were sometimes favorable in targeted therapies. CA125 is a promising prognostic marker in patients treated with immunotherapies. Combinations of STMs further increased the prognostic value over single markers. CONCLUSION: Protein STMs, especially CYFRA 21-1, have prognostic potential in early and advanced stage NSCLC. For future STM investigations, better adherence to comparable study designs, analytical methods, outcome measures and statistical evaluation standards is recommended. [ABSTRACT FROM AUTHOR]

BACKGROUND: The value of serum tumor markers (STMs) in the current therapeutic landscape of lung cancer is unclear. OBJECTIVE: This scoping review gathered evidence of the predictive, prognostic, and monitoring value of STMs for patients with advanced lung cancer receiving immunotherapy (IT) or targeted therapy (TT). METHODS: Literature searches were conducted (cut-off: May 2022) using PubMed and Cochrane CENTRAL databases. Medical professionals advised on the search strategies. RESULTS: Study heterogeneity limited the evidence and inferences from the 36 publications reviewed. While increased baseline levels of serum cytokeratin 19 fragment antigen (CYFRA21-1) and carcinoembryonic antigen (CEA) may predict IT response, results for TT were less clear. For monitoring IT-treated patients, STM panels (including CYFRA21-1, CEA, and neuron-specific enolase) may surpass the power of single analyses to predict non-response. CYFRA21-1 measurement could aid in monitoring TT-treated patients, but the value of CEA in this context requires further investigation. Overall, baseline and dynamic changes in individual or combined STM levels have potential utility to predict treatment outcome and for monitoring of patients with advanced lung cancer. CONCLUSIONS: In advanced lung cancer, STMs provide additional relevant clinical information by predicting treatment outcome, but further standardization and validation is warranted. [ABSTRACT FROM AUTHOR]

In der Laboratoriumsmedizin kann maschinelles Lernen eingesetzt werden, um in den reichlich vorhandenen Daten verborgene Strukturen und Zusammenhänge zu entdecken oder die Diagnosefindung zu unterstützen. Am Beispiel eines Datensatzes aus der Onkologie werden die einzelnen Prozessschritte von den Rohdaten bis zum fertigen Ergebnis demonstriert. Dabei verursacht die Datenaufbereitung den höchsten Aufwand. [ABSTRACT FROM AUTHOR]

Die prognostische Bedeutung von NT-proBNP bei Kindern mit angeborenen Herzfehlern konnte wegen der vor allem im ersten Lebensjahr ausgeprägten Altersdynamik bislang nur unzureichend untersucht werden. Abhilfe schafft die altersangepasste Standardisierung der Absolutwerte mithilfe des kürzlich eingeführten NT-proBNP-spezifischen zlog-Wertes, der analog zu einem Z-Score interpretiert wird. Wir zeigen, dass die Wahrscheinlichkeit schwerer kardialer Ereignisse bei Kindern mit angeborenen Herzfehlern stark zunimmt, je höher dieser Wert liegt. [ABSTRACT FROM AUTHOR]

Copyright of Der Chirurg is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Pelvic fractures are rare but serious injuries. The influence of a concomitant abdominal trauma on the time point of surgery and the quality of care regarding quality of reduction or the clinical course in pelvic injuries has not been investigated yet. Methods: We retrospectively analyzed the prospective consecutive cohort from the multicenter German Pelvic Registry of the German Trauma Society in the years 2003–2017. Demographic, clinical, and operative parameters were recorded and compared for two groups (isolated pelvic fracture vs. combined abdominal/pelvic trauma). Results: 16.359 patients with pelvic injuries were treated during this period. 21.6% had a concomitant abdominal trauma. The mean age was 61.4 ± 23.5 years. Comparing the two groups, patients with a combination of pelvic and abdominal trauma were significantly younger (47.3 ± 22.0 vs. 70.5 ± 20.4 years; p < 0.001). Both, complication (21.9% vs. 9.9%; p < 0.001) and mortality (8.0% vs. 1.9%; p < 0.001) rates, were significantly higher. In the subgroup of acetabular fractures, the operation time was significantly longer in the group with the combined injury (198 ± 104 vs. 176 ± 81 min, p = 0.001). The grade of successful anatomic reduction of the acetabular fracture did not differ between the two groups. Conclusion: Patients with a pelvic injury have a concomitant abdominal trauma in about 20% of the cases. The clinical course is significantly prolonged in patients with a combined injury, with increased rates of morbidity and mortality. However, the quality of the reduction in the subgroup of acetabular fractures is not influenced by a concomitant abdominal injury. Trial registration: ClinicalTrials.gov, NCT03952026, Registered 16 May 2019, retrospectively registered [ABSTRACT FROM AUTHOR]

Background: Therapeutic possibilities for non-small cell lung cancer (NSCLC) have considerably increased during recent decades., Objective: To summarize the prognostic relevance of serum tumor markers (STM) for early and late-stage NSCLC patients treated with classical chemotherapies, novel targeted and immune therapies., Methods: A PubMed database search was conducted for prognostic studies on carcinoembryonic antigen (CEA), cytokeratin-19 fragment (CYFRA 21-1), neuron-specific enolase, squamous-cell carcinoma antigen, progastrin-releasing-peptide, CA125, CA 19-9 and CA 15-3 STMs in NSCLC patients published from 2008 until June 2022., Results: Out of 1069 studies, 141 were identified as meeting the inclusion criteria. A considerable heterogeneity regarding design, patient number, analytical and statistical methods was observed. High pretherapeutic CYFRA 21-1 levels and insufficient decreases indicated unfavorable prognosis in many studies on NSCLC patients treated with chemo-, targeted and immunotherapies or their combinations in early and advanced stages. Similar results were seen for CEA in chemotherapy, however, high pretherapeutic levels were sometimes favorable in targeted therapies. CA125 is a promising prognostic marker in patients treated with immunotherapies. Combinations of STMs further increased the prognostic value over single markers., Conclusion: Protein STMs, especially CYFRA 21-1, have prognostic potential in early and advanced stage NSCLC. For future STM investigations, better adherence to comparable study designs, analytical methods, outcome measures and statistical evaluation standards is recommended.

Background: The value of serum tumor markers (STMs) in the current therapeutic landscape of lung cancer is unclear., Objective: This scoping review gathered evidence of the predictive, prognostic, and monitoring value of STMs for patients with advanced lung cancer receiving immunotherapy (IT) or targeted therapy (TT)., Methods: Literature searches were conducted (cut-off: May 2022) using PubMed and Cochrane CENTRAL databases. Medical professionals advised on the search strategies., Results: Study heterogeneity limited the evidence and inferences from the 36 publications reviewed. While increased baseline levels of serum cytokeratin 19 fragment antigen (CYFRA21-1) and carcinoembryonic antigen (CEA) may predict IT response, results for TT were less clear. For monitoring IT-treated patients, STM panels (including CYFRA21-1, CEA, and neuron-specific enolase) may surpass the power of single analyses to predict non-response. CYFRA21-1 measurement could aid in monitoring TT-treated patients, but the value of CEA in this context requires further investigation. Overall, baseline and dynamic changes in individual or combined STM levels have potential utility to predict treatment outcome and for monitoring of patients with advanced lung cancer., Conclusions: In advanced lung cancer, STMs provide additional relevant clinical information by predicting treatment outcome, but further standardization and validation is warranted.