Improved survival of locoregional-advanced larynx and hypopharynx cancer patients treated according to the DeLOS-II protocol.

Introduction: Larynx organ preservation (LOP) in locoregional-advanced laryngeal and hypopharyngeal squamous cell carcinoma (LA-LHSCC) being only R0-resectable (clear margins > 5 mm) by total laryngectomy (TL) is desirable. Based on tumor-specific survival (TSS) and overall survival (OS) data from the RTOG 91-11 trial and meta-analyses of randomized clinical trials (RCTs), cisplatin-based concurrent radiochemotherapy (CRT) is discussed being superior to cisplatin-based induction chemotherapy followed by radiotherapy (IC+RT) and TL followed by postoperative RT (TL+PORT) or radiochemotherapy (TL+PORCT). Outside of RCTs, T4 LHSCC treated with TL+PORCT demonstrated improved OS and TSS compared to CRT alone; comparisons with docetaxel plus cisplatin (TP)-based IC+RT are unpublished. Head-to-head comparisons in RCTs of these four alternatives are missing. Materials and methods: We utilized monocentric registry data to compare the outcome in the LOP trial DeLOS-II (NCT00508664) and propensity score (PS)-matched LHSCC patients. DeLOS-II utilized endoscopic tumor staging after one cycle of TP-based IC for selecting TL+R(C)T for non-responders versus IC+RT for responders. Main risk factors for survival (localization hypopharynx, T4, N+, tobacco smoking >30 pack years, alcohol consumption >60 g/day, age, sex) were used to calculate the individual PS for each DeLOS-II patient and 330 LHSCC patients suitable for DeLOS-II according to eligibility criteria in Leipzig by CRT (78), TL+PORT (148), and TL+PORCT (104). We performed PS matching with caliper width 0.2. Results: The 52 DeLOS-II patients (whole intent-to-treat cohort) and three PS-matched cohorts (52 LHSCC patients each) had equal distribution regarding risk factors including Charlson comorbidity score (CS; all p > 0.05) but differed in outcome. During 12,498.6 months of follow-up, 162 deaths (36/41/43/42 in DeLOS-II/TL+PORCT/TL+PORT/CRT, p = 0.356) occurred; DeLOS-II patients had superior OS and TSS. Compared to DeLOS-II, the HR (95% CI) observed in TL+PORCT, TL+PORT, and CRT for OS and TSS were 1.49 (0.92-2.43), 1.49 (1.15-3.18), and 1.81 (1.11-2.96) for OS; and 2.07 (0.944-4.58), 3.02 (1.32-6.89), and 3.40 (1.58-7.31) for TSS. Conclusion: In addition potential LOP, LA-LHSCC suitable for LOP according the DeLOS-II protocol may achieve improved survival.

Generation of a Realistic Synthetic Laryngeal Cancer Cohort for AI Applications.

BACKGROUND: Obtaining large amounts of real patient data involves great efforts and expenses, and processing this data is fraught with data protection concerns. Consequently, data sharing might not always be possible, particularly when large, open science datasets are needed, as for AI development. For such purposes, the generation of realistic synthetic data may be the solution. Our project aimed to generate realistic cancer data with the use case of laryngeal cancer. METHODS: We used the open-source software Synthea and programmed an additional module for development, treatment and follow-up for laryngeal cancer by using external, real-world (RW) evidence from guidelines and cancer registries from Germany. To generate an incidence-based cohort view, we randomly drew laryngeal cancer cases from the simulated population and deceased persons, stratified by the real-world age and sex distributions at diagnosis. RESULTS: A module with age- and stage-specific treatment and prognosis for laryngeal cancer was successfully implemented. The synthesized population reflects RW prevalence well, extracting a cohort of 50,000 laryngeal cancer patients. Descriptive data on stage-specific and 5-year overall survival were in accordance with published data. CONCLUSIONS: We developed a large cohort of realistic synthetic laryngeal cancer cases with Synthea. Such data can be shared and published open source without data protection issues.

A Treatment Decision Support Model for Laryngeal Cancer Based on Bayesian Networks.

The increase in diagnostic and therapeutic procedures in the treatment of oncological diseases, as well as the limited capacity of experts to provide information, necessitates the development of therapy decision support systems (TDSS). We have developed a treatment decision model that integrates available patient information as well as tumor characteristics. They are assessed according to their relevance in evaluating the optimal therapy option. Our treatment model is based on Bayesian networks (BN) which integrate patient-specific data with expert-based implemented causalities to suggest the optimal therapy option and therefore potentially support the decision-making process for treatment of laryngeal carcinoma. To test the reliability of our model, we compared the calculations of our model with the documented therapy from our data set, which contained information on 97 patients with laryngeal carcinoma. Information on 92 patients was used in our analyses and the model suggested the correct treatment in 419 out of 460 treatment modalities (accuracy of 91%). However, unequally distributed clinical data in the test sets revealed weak spots in the model that require revision for future utilization.

Clinical decision support models for oropharyngeal cancer treatment: design and evaluation of a multi-stage knowledge abstraction and formalization process.

PURPOSE: Treatment decisions in oncology are demanding and affect survival, general health, and quality of life. Expert systems can handle the complexity of the oncological field. We propose the application of a hybrid modeling approach for decision support models consisting of expert-based implementation of a decision model structure and machine-learning (ML) based parameter generation. We demonstrate our approach for the treatment of oropharyngeal cancer. METHODS: We created a clinical decision model based on Bayesian Networks and iteratively optimized its characteristics using structured knowledge engineering approaches. We combined manual adaptation of individual concepts with automatic learning of parameters and causalities. Using data from 94 patient records, we targeted the needed objectivity and clinical significance. RESULTS: In three iteration steps, we assessed the model with cross-validations. The initial aggregated accuracy of 0.529 could be increased to 0.883 in the final version. The predictive rates of the target nodes range from 0.557 to 0.960. CONCLUSION: Combining different methodological approaches requires balancing the complexity of the clinical subject matter with the amount of information available in the dataset for ML application. Our method showed promising results because flaws of one approach can be overcome by the other approach. However, technical integrability as well as clinical acceptance must always be ensured.

Decision Support for Oropharyngeal Cancer Patients Based on Data-Driven Similarity Metrics for Medical Case Comparison.

Making complex medical decisions is becoming an increasingly challenging task due to the growing amount of available evidence to consider and the higher demand for personalized treatment and patient care. IT systems for the provision of clinical decision support (CDS) can provide sustainable relief if decisions are automatically evaluated and processed. In this paper, we propose an approach for quantifying similarity between new and previously recorded medical cases to enable significant knowledge transfer for reasoning tasks on a patient-level. Methodologically, 102 medical cases with oropharyngeal carcinoma were analyzed retrospectively. Based on independent disease characteristics, patient-specific data vectors including relevant information entities for primary and adjuvant treatment decisions were created. Utilizing the ϕK correlation coefficient as the methodological foundation of our approach, we were able to determine the predictive impact of each characteristic, thus enabling significant reduction of the feature space to allow for further analysis of the intra-variable distances between the respective feature states. The results revealed a significant feature-space reduction from initially 19 down to only 6 diagnostic variables (ϕK correlation coefficient ≥ 0.3, ϕK significance test ≥ 2.5) for the primary and 7 variables (from initially 14) for the adjuvant treatment setting. Further investigation on the resulting characteristics showed a non-linear behavior in relation to the corresponding distances on intra-variable level. Through the implementation of a 10-fold cross-validation procedure, we were further able to identify 8 (primary treatment) matching cases with an evaluation score of 1.0 and 9 (adjuvant treatment) matching cases with an evaluation score of 0.957 based on their shared treatment procedure as the endpoint for similarity definition. Based on those promising results, we conclude that our proposed method for using data-driven similarity measures for application in medical decision-making is able to offer valuable assistance for physicians. Furthermore, we consider our approach as universal in regard to other clinical use-cases, which would allow for an easy-to-implement adaptation for a range of further medical decision-making scenarios.

Bayesian Networks to Support Decision-Making for Immune-Checkpoint Blockade in Recurrent/Metastatic (R/M) Head and Neck Squamous Cell Carcinoma (HNSCC).

New diagnostic methods and novel therapeutic agents spawn additional and heterogeneous information, leading to an increasingly complex decision-making process for optimal treatment of cancer. A great amount of information is collected in organ-specific multidisciplinary tumor boards (MDTBs). By considering the patient's tumor properties, molecular pathological test results, and comorbidities, the MDTB has to consent an evidence-based treatment decision. Immunotherapies are increasingly important in today's cancer treatment, resulting in detailed information that influences the decision-making process. Clinical decision support systems can facilitate a better understanding via processing of multiple datasets of oncological cases and molecular genetic information, potentially fostering transparency and comprehensibility of available information, eventually leading to an optimum treatment decision for the individual patient. We constructed a digital patient model based on Bayesian networks to combine the relevant patient-specific and molecular data with depended probabilities derived from pertinent studies and clinical guidelines to calculate treatment decisions in head and neck squamous cell carcinoma (HNSCC). In a validation analysis, the model can provide guidance within the growing subject of immunotherapy in HNSCC and, based on its ability to calculate reliable probabilities, facilitates estimation of suitable therapy options. We compared actual treatment decisions of 25 patients with the calculated recommendations of our model and found significant concordance (Cohen's κ = 0.505, p = 0.009) and 84% accuracy.

Modeling and processing up-to-dateness of patient information in probabilistic therapy decision support.

OBJECTIVES: Probabilistic modeling of a patient's situation with the goal of providing calculated therapy recommendations can improve the decision making of interdisciplinary teams. Relevant information entities and direct causal dependencies, as well as uncertainty, must be formally described. Possible therapy options, tailored to the patient, can be inferred from the clinical data using these descriptions. However, there are several avoidable factors of uncertainty influencing the accuracy of the inference. For instance, inaccuracy may emerge from outdated information. In general, probabilistic models, e.g. Bayesian Networks can depict the causality and relations of individual information entities, but in general cannot evaluate individual entities concerning their up-to-dateness. The goal of the work at hand is to model diagnostic up-to-dateness, which can reasonably adjust the influence of outdated diagnostic information to improve the inference results of clinical decision models. METHODS AND MATERIALS: We analyzed 68 laryngeal cancer cases and modeled the state of up-to-dateness of different diagnostic modalities. All cases were used for cross-validation. 55 cases were used to train the model, 13 for testing. Each diagnostic procedure involved in the decision making process of these cases was associated with a specific threshold for the time the information is considered up-to-date, i.e. reliable. Based on this threshold, outdated findings could be identified and their impact on probabilistic calculations could be reduced. We applied the model for reducing the weight of outdated patient data in the computation of TNM stagings for the 13 test cases and compared the results to the manually derived TNM stagings in the patient files. RESULTS: With the implementation of these weights in the laryngeal cancer model, we increased the accuracy of the TNM calculation from 0.61 (8 out of 13 cases correct) to 0.76 (10 out of 13 cases correct). CONCLUSION: Decision delay may cause specific patient data to be outdated. This can cause contradictory or false information and impair calculations for clinical decision support. Our approach demonstrates that the accuracy of Bayesian Network models can be improved when pre-processing the patient-specific data and evaluating their up-to-dateness with reduced weights on outdated information.

Digital patient models based on Bayesian networks for clinical treatment decision support.

Increasing complexity in the management of oncologic diseases due to advances in diagnostics and individualized treatments demands new techniques of comprehensive decision support. Digital patient models (DPMs) are developed to collect, structure, and evaluate information to improve the decision-making process in tumour boards and surgical procedures in the operating room (OR). Laryngeal cancer (LC) was selected as a prototype to build a clinical decision support system (CDSS) based on Bayesian networks (BN). The model was built in cooperation with a knowledge engineer and a domain expert in head and neck oncology. Once a CDSS is developed, individual patient data can be set to compute a patient-specific BN. The modelling was based on clinical guidelines and analysis of the tumour board decision making. Besides description of the modelling process, recommendations for standardised modelling, new tools, validation and interaction of extensive models are presented. The LC model contains over 1,000 variables with about 1,300 dependencies. A subnetwork representing TNM staging (303 variables) was validated and reached 100% of correct model predictions. Given the new methods and tools, construction of a complex human-readable CDSS is feasible. Interactive platforms with guided modelling may support collaborative model development and extension to other diseases. Appropriate tools may assist decision making in various situations, e.g. the OR.

Validation workflow for a clinical Bayesian network model in multidisciplinary decision making in head and neck oncology treatment.

PURPOSE: Oncological treatment is being increasingly complex, and therefore, decision making in multidisciplinary teams is becoming the key activity in the clinical pathways. The increased complexity is related to the number and variability of possible treatment decisions that may be relevant to a patient. In this paper, we describe validation of a multidisciplinary cancer treatment decision in the clinical domain of head and neck oncology. METHOD: Probabilistic graphical models and corresponding inference algorithms, in the form of Bayesian networks, can support complex decision-making processes by providing a mathematically reproducible and transparent advice. The quality of BN-based advice depends on the quality of the model. Therefore, it is vital to validate the model before it is applied in practice. RESULTS: For an example BN subnetwork of laryngeal cancer with 303 variables, we evaluated 66 patient records. To validate the model on this dataset, a validation workflow was applied in combination with quantitative and qualitative analyses. In the subsequent analyses, we observed four sources of imprecise predictions: incorrect data, incomplete patient data, outvoting relevant observations, and incorrect model. Finally, the four problems were solved by modifying the data and the model. CONCLUSION: The presented validation effort is related to the model complexity. For simpler models, the validation workflow is the same, although it may require fewer validation methods. The validation success is related to the model's well-founded knowledge base. The remaining laryngeal cancer model may disclose additional sources of imprecise predictions.

A Guide for Constructing Bayesian Network Graphs of Cancer Treatment Decisions.

In complex cancer cases, Bayesian networks can support clinical experts in finding the best patient-specific therapeutic decisions. However, the development of decision networks requires teamwork of at least one domain expert and one knowledge engineer making the process expensive, time-consuming, and prone to misunderstandings. We present a novel method for guided modeling. This method enables domain experts to model collaboratively without the need of knowledge engineers, increasing both the development speed and model quality.

Web-tool to Support Medical Experts in Probabilistic Modelling Using Large Bayesian Networks With an Example of Hinosinusitis.

For many complex diseases, finding the best patient-specific treatment decision is difficult for physicians due to limited mental capacity. Clinical decision support systems based on Bayesian networks (BN) can provide a probabilistic graphical model integrating all necessary aspects relevant for decision making. Such models are often manually created by clinical experts. The modeling process consists of graphical modeling conducted by collecting of information entities, and probabilistic modeling achieved through defining the relations of information entities to their direct causes. Such expert-based probabilistic modelling with BNs is very time intensive and requires knowledge about the underlying modeling method. We introduce in this paper an intuitive web-based system for helping medical experts generate decision models based on BNs. Using the tool, no special knowledge about the underlying model or BN is necessary. We tested the tool with an example of modeling treatment decisions of Rhinosinusitis and studied its usability.

Simvastatin suppresses head and neck squamous cell carcinoma ex vivo and enhances the cytostatic effects of chemotherapeutics.

PURPOSE: Simvastatin (Sim) is approved as lipid-controlling drug in patients with cardiovascular risk to reduce hypercholesterolemia. Recent publications indicate possible inhibitory effects of Sim on tumor cell lines, and epidemiological data suggest activity in cancer patients. Still, its therapeutic efficacy, particularly in head and neck squamous cell carcinoma (HNSCC), remains to be elucidated. This study analyzes the effects of Sim on HNSCC cell lines (KB, HN5, FaDu) and on a larger set of primary HNSCC cells by employing a short-time ex vivo colony formation test (FLAVINO assay). Possible additive or synergistic effects of Sim combinations with established chemotherapeutics are determined as well. METHODS: Biopsies of 49 HNSCC were tested in the FLAVINO assay with Sim alone or in combination with cisplatin (Cis) or docetaxel (DTX). Cell lines were studied for reference. Epithelial HNSCC cells were stained by Cy2-labeled anti-cytokeratin antibodies facilitating the detection of colony formation (CF) by immunofluorescence. Drug combinations were analyzed regarding their interaction. RESULTS: Sim alone acted suppressive on tested cell lines and increased the cytostatic efficacy of Cis and DTX. 18/49 HNSCC qualified for FLAVINO-based dose-response analyses, and Sim significantly suppressed CF in 18/18 primary HNSCC. Moreover, Sim increased cytotoxic effects of Cis and DTX, primarily in an additive mode of action. CONCLUSIONS: The ex vivo tumor cell inhibition of Sim and its additive effects upon combination with established cytostatics provide the basis for epidemiological and clinical studies on statins, potentially directed toward co-medication in future treatment regimens.

Hedgehog targeting by cyclopamine suppresses head and neck squamous cell carcinoma and enhances chemotherapeutic effects.

BACKGROUND: The hedgehog signaling pathway (HH) is involved in tumorigenesis in a variety of human malignancies. In head and neck squamous cell carcinomas (HNSCC), Hh overexpression was associated with poor prognosis. Therefore, we analyzed the effect of Hh signaling blockade with cyclopamine on colony formation of cells from HNSCC samples. PATIENTS AND METHODS: HNSCC biopsies were cultured alone for reference or with serial dilutions of cyclopamine (5-5,000 nM), docetaxel (137.5-550 nM), or cisplatin (1,667-6,667 nM) and their binary combinations. Cytokeratin-positive colonies were counted after fluorescent staining. RESULTS: Cyclopamine concentration-dependently inhibited HNSCC ex vivo [(IC50) at about 500 nM]. In binary combinations, cyclopamine additively enhanced the suppressive effects of cisplatin and docetaxel on HNSCC colony formation. CONCLUSION: Our findings define SMO--a Hh component- as a potential target in HNSCC and suggest the utility of Hh targeting in future multimodal treatment regimens for HNSCC.

Overexpression of the Hedgehog signalling pathway in head and neck squamous cell carcinoma.

BACKGROUND: Overexpression of the Hedgehog (HH) signalling pathway has been described in several malignancies and is associated with a poor prognosis. HH signalling blockade reduces tumour growth in vitro and in vivo. We aimed to determine whether head and neck squamous cell carcinomas (HNSCCs) express HH proteins in comparison to healthy mucosa. PATIENTS AND METHODS: Formalin-fixed and paraffin-embedded tissue sections of 10 patients with HNSCC were stained with fluorescence-labelled antibodies for cytokeratin and HH proteins (SHH, PTCH1/2, SMO, Gli1-3) and photographs were taken with a laser scanning microscope. The pixel count and colour intensity were analysed in RGB (red/green/blue) colour mode, and expression levels were compared to healthy mucosa. RESULTS: Image analysis in RGB mode provided objective evidence for the over-expression of HH signalling components in HNSCC, particularly with regard to the transcription factors Gli1 (10-fold) and SHH (5-fold) in comparison with healthy mucosa. The lowest levels were found for Gli3 in HNSCC. CONCLUSIONS: We postulate pivotal roles of Gli1 and SHH expression in the carcinogenesis of HNSCC. HH pathway overexpression appears to be involved in the initiation of tumour growth and spread due to its stem cell-modulating properties. Detection of HH pathway components, and especially Gli1 and SHH, in HNSCC might offer a promising target for further anticancer research in HNSCC.