Time-dependent estimates of recurrence and survival in colon cancer: clinical decision support system tool development for adjuvant therapy and oncological outcome assessment.

Unanswered questions remain in determining which high-risk node-negative colon cancer (CC) cohorts benefit from adjuvant therapy and how it may differ in an equal access population. Machine-learned Bayesian Belief Networks (ml-BBNs) accurately estimate outcomes in CC, providing clinicians with Clinical Decision Support System (CDSS) tools to facilitate treatment planning. We evaluated ml-BBNs ability to estimate survival and recurrence in CC. We performed a retrospective analysis of registry data of patients with CC to train-test-crossvalidate ml-BBNs using the Department of Defense Automated Central Tumor Registry (January 1993 to December 2004). Cases with events or follow-up that passed quality control were stratified into 1-, 2-, 3-, and 5-year survival cohorts. ml-BBNs were trained using machine-learning algorithms and k-fold crossvalidation and receiver operating characteristic curve analysis used for validation. BBNs were comprised of 5301 patients and areas under the curve ranged from 0.85 to 0.90. Positive predictive values for recurrence and mortality ranged from 78 to 84 per cent and negative predictive values from 74 to 90 per cent by survival cohort. In the 12-month model alone, 1,132,462,080 unique rule sets allow physicians to predict individual recurrence/mortality estimates. Patients with Stage II (N0M0) CC benefit from chemotherapy at different rates. At one year, all patients older than 73 years of age with T2-4 tumors and abnormal carcinoembryonic antigen levels benefited, whereas at five years, all had relative reduction in mortality with the largest benefit amongst elderly, highest T-stage patients. ml-BBN can readily predict which high-risk patients benefit from adjuvant therapy. CDSS tools yield individualized, clinically relevant estimates of outcomes to assist clinicians in treatment planning.

Evidence-based Guidelines for Precision Risk Stratification-Based Screening (PRSBS) for Colorectal Cancer: Lessons learned from the US Armed Forces: Consensus and Future Directions.

Colorectal cancer (CRC) is the third most common cause of cancer-related death in the United States (U.S.), with estimates of 143,460 new cases and 51,690 deaths for the year 2012. Numerous organizations have published guidelines for CRC screening; however, these numerical estimates of incidence and disease-specific mortality have remained stable from years prior. Technological, genetic profiling, molecular and surgical advances in our modern era should allow us to improve risk stratification of patients with CRC and identify those who may benefit from preventive measures, early aggressive treatment, alternative treatment strategies, and/or frequent surveillance for the early detection of disease recurrence. To better negotiate future economic constraints and enhance patient outcomes, ultimately, we propose to apply the principals of personalized and precise cancer care to risk-stratify patients for CRC screening (Precision Risk Stratification-Based Screening, PRSBS). We believe that genetic, molecular, ethnic and socioeconomic disparities impact oncological outcomes in general, those related to CRC, in particular. This document highlights evidence-based screening recommendations and risk stratification methods in response to our CRC working group private-public consensus meeting held in March 2012. Our aim was to address how we could improve CRC risk stratification-based screening, and to provide a vision for the future to achieving superior survival rates for patients diagnosed with CRC.

Clinical decision support and individualized prediction of survival in colon cancer: bayesian belief network model.

BACKGROUND: We used a large population-based data set to create a clinical decision support system (CDSS) for real-time estimation of overall survival (OS) among colon cancer (CC) patients. Patients with CC diagnosed between 1969 and 2006 were identified from the Surveillance Epidemiology and End Results (SEER) registry. Low- and high-risk cohorts were defined. The tenfold cross-validation assessed predictive utility of the machine-learned Bayesian belief network (ml-BBN) model for clinical decision support (CDS). METHODS: A data set consisting of 146,248 records was analyzed using ml-BBN models to provide CDS in estimating OS based on prognostic factors at 12-, 24-, 36-, and 60-month post-treatment follow-up. RESULTS: Independent prognostic factors in the ml-BBN model included age, race; primary tumor histology, grade and location; Number of primaries, AJCC T stage, N stage, and M stage. The ml-BBN model accurately estimated OS with area under the receiver-operating-characteristic curve of 0.85, thereby improving significantly upon existing AJCC stage-specific OS estimates. Significant differences in OS were found between low- and high-risk cohorts (odds ratios for mortality: 17.1, 16.3, 13.9, and 8.8 for 12-, 24-, 36-, and 60-month cohorts, respectively). CONCLUSIONS: A CDSS was developed to provide individualized estimates of survival in CC. This ml-BBN model provides insights as to how disease-specific factors influence outcome. Time-dependent, individualized mortality risk assessments may inform treatment decisions and facilitate clinical trial design.

A novel nomogram for peritoneal mesothelioma predicts survival.

BACKGROUND: Malignant peritoneal mesothelioma (MPM) is a rare disease treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC). Estimation of personalized survival times can potentially guide treatment and surveillance. METHODS: We analyzed 104 patients who underwent CRS and cisplatin-based HIPEC for MPM. By means of 25 demographic, laboratory, operative, and histopathological variables, we developed a novel nomogram using machine-learned Bayesian belief networks with stepwise training, testing, and cross-validation. RESULTS: The mean peritoneal carcinomatosis index (PCI) was 15, and 66 % of patients had a completeness of cytoreduction (CC) score of 0 or 1. Eighty-seven percent of patients had epithelioid histology. The median follow-up time was 49 (1-195) months. The 3- and 5-year overall survivals (OS) were 58 and 46 %, respectively. The histological subtype, pre-CRS PCI, and preoperative serum CA-125 had the greatest impact on OS and were included in the nomogram. The mean areas under the receiver operating characteristic curve for the 10-fold cross-validation of the 3- and 5-year models were 0.77 and 0.74, respectively. The graphical calculator or nomogram uses color coding to assist the clinician in quickly estimating individualized patient-specific survival before surgery. CONCLUSIONS: Machine-learned Bayesian belief network analysis generated a novel nomogram predicting 3- and 5-year OS in patients treated with CRS and HIPEC for MPM. Pre-CRS estimation of survival times may potentially individualize patient care by influencing the use of systemic therapy and frequency of diagnostic imaging, and might prevent CRS in patients unlikely to achieve favorable outcomes despite surgical intervention.

Clinical decision support systems: potential with pitfalls.

Clinical Decision Support Systems (CDSS), an important part of clinical practice, are comprised of a: knowledge base; program for integrating patient-specific information with the knowledge-base; and, user-interface to allow clinicians to interact with the system and get the right information needed to make the right decision for the right patient at the right time. We review the common approaches to CDSS, their strengths and weaknesses and how they are evaluated and developed for clinical use.

Using machine-learned bayesian belief networks to predict perioperative risk of clostridium difficile infection following colon surgery.

BACKGROUND: Clostridium difficile (C-Diff) infection following colorectal resection is an increasing source of morbidity and mortality. OBJECTIVE: We sought to determine if machine-learned Bayesian belief networks (ml-BBNs) could preoperatively provide clinicians with postoperative estimates of C-Diff risk. METHODS: We performed a retrospective modeling of the Nationwide Inpatient Sample (NIS) national registry dataset with independent set validation. The NIS registries for 2005 and 2006 were used for initial model training, and the data from 2007 were used for testing and validation. International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) codes were used to identify subjects undergoing colon resection and postoperative C-Diff development. The ml-BBNs were trained using a stepwise process. Receiver operating characteristic (ROC) curve analysis was conducted and area under the curve (AUC), positive predictive value (PPV), and negative predictive value (NPV) were calculated. RESULTS: From over 24 million admissions, 170,363 undergoing colon resection met the inclusion criteria. Overall, 1.7% developed postoperative C-Diff. Using the ml-BBN to estimate C-Diff risk, model AUC is 0.75. Using only known a priori features, AUC is 0.74. The model has two configurations: a high sensitivity and a high specificity configuration. Sensitivity, specificity, PPV, and NPV are 81.0%, 50.1%, 2.6%, and 99.4% for high sensitivity and 55.4%, 81.3%, 3.5%, and 99.1% for high specificity. C-Diff has 4 first-degree associates that influence the probability of C-Diff development: weight loss, tumor metastases, inflammation/infections, and disease severity. CONCLUSIONS: Machine-learned BBNs can produce robust estimates of postoperative C-Diff infection, allowing clinicians to identify high-risk patients and potentially implement measures to reduce its incidence or morbidity.

Estimating survival in patients with operable skeletal metastases: an application of a bayesian belief network.

BACKGROUND: Accurate estimations of life expectancy are important in the management of patients with metastatic cancer affecting the extremities, and help set patient, family, and physician expectations. Clinically, the decision whether to operate on patients with skeletal metastases, as well as the choice of surgical procedure, are predicated on an individual patient's estimated survival. Currently, there are no reliable methods for estimating survival in this patient population. Bayesian classification, which includes bayesian belief network (BBN) modeling, is a statistical method that explores conditional, probabilistic relationships between variables to estimate the likelihood of an outcome using observed data. Thus, BBN models are being used with increasing frequency in a variety of diagnoses to codify complex clinical data into prognostic models. The purpose of this study was to determine the feasibility of developing bayesian classifiers to estimate survival in patients undergoing surgery for metastases of the axial and appendicular skeleton. METHODS: We searched an institution-owned patient management database for all patients who underwent surgery for skeletal metastases between 1999 and 2003. We then developed and trained a machine-learned BBN model to estimate survival in months using candidate features based on historical data. Ten-fold cross-validation and receiver operating characteristic (ROC) curve analysis were performed to evaluate the BNN model's accuracy and robustness. RESULTS: A total of 189 consecutive patients were included. First-degree predictors of survival differed between the 3-month and 12-month models. Following cross validation, the area under the ROC curve was 0.85 (95% CI: 0.80-0.93) for 3-month probability of survival and 0.83 (95% CI: 0.77-0.90) for 12-month probability of survival. CONCLUSIONS: A robust, accurate, probabilistic naïve BBN model was successfully developed using observed clinical data to estimate individualized survival in patients with operable skeletal metastases. This method warrants further development and must be externally validated in other patient populations.

Consensus recommendations for advancing breast cancer: risk identification and screening in ethnically diverse younger women.

A need exists for a breast cancer risk identification paradigm that utilizes relevant demographic, clinical, and other readily obtainable patient-specific data in order to provide individualized cancer risk assessment, direct screening efforts, and detect breast cancer at an early disease stage in historically underserved populations, such as younger women (under age 40) and minority populations, who represent a disproportionate number of military beneficiaries. Recognizing this unique need for military beneficiaries, a consensus panel was convened by the USA TATRC to review available evidence for individualized breast cancer risk assessment and screening in young (< 40), ethnically diverse women with an overall goal of improving care for military beneficiaries. In the process of review and discussion, it was determined to publish our findings as the panel believes that our recommendations have the potential to reduce health disparities in risk assessment, health promotion, disease prevention, and early cancer detection within and in other underserved populations outside of the military. This paper aims to provide clinicians with an overview of the clinical factors, evidence and recommendations that are being used to advance risk assessment and screening for breast cancer in the military.

Development of a Bayesian Belief Network Model for personalized prognostic risk assessment in colon carcinomatosis.

Multimodality therapy in selected patients with peritoneal carcinomatosis is gaining acceptance. Treatment-directing decision support tools are needed to individualize care and select patients best suited for cytoreductive surgery +/- hyperthermic intraperitoneal chemotherapy (CRS +/- HIPEC). The purpose of this study is to develop a predictive model that could support surgical decisions in patients with colon carcinomatosis. Fifty-three patients were enrolled in a prospective study collecting 31 clinical-pathological, treatment-related, and outcome data. The population was characterized by disease presentation, performance status, extent of peritoneal cancer (Peritoneal Cancer Index, PCI), primary tumor histology, and nodal staging. These preoperative parameters were analyzed using step-wise machine-learned Bayesian Belief Networks (BBN) to develop a predictive model for overall survival (OS) in patients considered for CRS +/- HIPEC. Area-under-the-curve from receiver-operating-characteristics curves of OS predictions was calculated to determine the model's positive and negative predictive value. Model structure defined three predictors of OS: severity of symptoms (performance status), PCI, and ability to undergo CRS +/- HIPEC. Patients with PCI < 10, resectable disease, and excellent performance status who underwent CRS +/- HIPEC had 89 per cent probability of survival compared with 4 per cent for those with poor performance status, PCI > 20, who were not considered surgical candidates. Cross validation of the BBN model robustly classified OS (area-under-the-curve = 0.71). The model's positive predictive value and negative predictive value are 63.3 per cent and 68.3 per cent, respectively. This exploratory study supports the utility of Bayesian classification for developing decision support tools, which assess case-specific relative risk for a given patient for oncological outcomes based on clinically relevant classifiers of survival. Further prospective studies to validate the BBN model-derived prognostic assessment tool are warranted.

Development of a prognostic naive bayesian classifier for successful treatment of nonunions.

BACKGROUND: predictive models permitting individualized prognostication for patients with fracture nonunion are lacking. The objective of this study was to train, test, and cross-validate a Bayesian classifier for predicting fracture-nonunion healing in a population treated with extracorporeal shock wave therapy. METHODS: prospectively collected data from 349 patients with delayed fracture union or a nonunion were utilized to develop a naïve Bayesian belief network model to estimate site-specific fracture-nonunion healing in patients treated with extracorporeal shock wave therapy. Receiver operating characteristic curve analysis and tenfold cross-validation of the model were used to determine the clinical utility of the approach. RESULTS: predictors of fracture-healing at six months following shock wave treatment were the time between the fracture and the first shock wave treatment, the time between the fracture and the surgery, intramedullary stabilization, the number of bone-grafting procedures, the number of extracorporeal shock wave therapy treatments, work-related injury, and the bone involved (p < 0.05 for all comparisons). These variables were all included in the naïve Bayesian belief network model. CONCLUSIONS: a clinically relevant Bayesian classifier was developed to predict the outcome after extracorporeal shock wave therapy for fracture nonunions. The time to treatment and the anatomic site of the fracture nonunion significantly impacted healing outcomes. Although this study population was restricted to patients treated with shock wave therapy, Bayesian-derived predictive models may be developed for application to other fracture populations at risk for nonunion. LEVEL OF EVIDENCE: prognostic Level II. See Instructions to Authors for a complete description of levels of evidence.

IgG responses to tissue-associated antigens as biomarkers of immunological treatment efficacy.

We previously demonstrated that IgG responses to a panel of 126 prostate tissue-associated antigens are common in patients with prostate cancer. In the current report we questioned whether changes in IgG responses to this panel might be used as a measure of immune response, and potentially antigen spread, following prostate cancer-directed immune-active therapies. Sera were obtained from prostate cancer patients prior to and three months following treatment with androgen deprivation therapy (n = 34), a poxviral vaccine (n = 31), and a DNA vaccine (n = 21). Changes in IgG responses to individual antigens were identified by phage immunoblot. Patterns of IgG recognition following three months of treatment were evaluated using a machine-learned Bayesian Belief Network (ML-BBN). We found that different antigens were recognized following androgen deprivation compared with vaccine therapies. While the number of clinical responders was low in the vaccine-treated populations, we demonstrate that ML-BBN can be used to develop potentially predictive models.

Assessing differences between physicians' realized and anticipated gains from electronic health record adoption.

Return on investment (ROI) concerns related to Electronic Health Records (EHRs) are a major barrier to the technology's adoption. Physicians generally rely upon early adopters to vet new technologies prior to putting them into widespread use. Therefore, early adopters' experiences with EHRs play a major role in determining future adoption patterns. The paper's purposes are: (1) to map the EHR value streams that define the ROI calculation; and (2) to compare Current Users' and Intended Adopters' perceived value streams to identify similarities, differences and governing constructs. Primary data was collected by the Texas Medical Association, which surveyed 1,772 physicians on their use and perceptions of practice gains from EHR adoption. Using Bayesian Belief Network Modeling, value streams are constructed for both current EHR users and Intended Adopters. Current Users and Intended Adopters differ significantly in their perceptions of the EHR value stream. Intended Adopters' value stream displays complex relationships among the potential gains compared to the simpler, linear relationship that Current Users identified. The Current Users identify "Reduced Medical Records Costs" as the gain that governs the value stream while Intended Adopters believe "Reduced Charge Capture Costs" define the value stream's starting point. Current Users' versus Intended Adopters' assessments of EHR benefits differ significantly and qualitatively from one another.

Lymph node ratio as a quality and prognostic indicator in stage III colon cancer.

BACKGROUND: The presence and number of nodal metastasis significantly impact colon cancer prognosis. Similarly, the number of resected/evaluated nodes impacts staging accuracy. This ratio of metastatic to examined nodes or lymph node ratio (LNR) may have independent prognostic value in colon carcinoma. PURPOSE: : To evaluate the impact of LNR on overall survival in colon cancer patients with fewer than 12 or 12 examined nodes or more. METHODS: Patients (n = 36,712) with node-positive nonmetastatic colon cancer diagnosed between 1992 and 2004 were identified from the Surveillance, Epidemiology, and End Results database and stratified according to LNR and number of nodes examined. Survival was estimated by Kaplan-Meier method, and differences analyzed by log-rank test. A Cox proportional hazards model was used for multivariate analysis. RESULTS: Patients with fewer than 12 nodes were older and male and had lower primary tumor stage, grade, and N stage (P < 0.01). Survival appeared greater with 12 total nodes examined or more (median 53 vs. 66 months, P < 0.001). Within each LNR stratum, survival with 12 nodes or more was improved for those with less than 10% of nodes positive for cancer, but was worse with higher LNRs (P < 0.01). Lymph node ratio was significantly associated with survival independent of total nodes (HR 1.24-5.12, P < 0.001). Other significant factors included age, race, tumor grade, stage, location, and N stage. CONCLUSION: Metastatic LNR independently estimates survival in Stage III colon cancer, irrespective of number of nodes examined. However, statistically significant differences in each LNR stratum between those with resection of fewer than 12 or 12 nodes or more would indicate that a 12-node minimum may still be necessary for accurate staging.

Probabilistic (Bayesian) modeling of gene expression in transplant glomerulopathy.

Transplant glomerulopathy (TG) is associated with rapid decline in glomerular filtration rate and poor outcome. We used low-density arrays with a novel probabilistic analysis to characterize relationships between gene transcripts and the development of TG in allograft recipients. Retrospective review identified TG in 10.8% of 963 core biopsies from 166 patients; patients with stable function were studied for comparison. The biopsies were analyzed for expression of 87 genes related to immune function and fibrosis by using real-time PCR, and a Bayesian model was generated and validated to predict histopathology based on gene expression. A total of 57 individual genes were increased in TG compared with stable function biopsies (P < 0.05). The Bayesian analysis identified critical relationships between ICAM-1, IL-10, CCL3, CD86, VCAM-1, MMP-9, MMP-7, and LAMC2 and allograft pathology. Moreover, Bayesian models predicted TG when derived from either immune function (area under the curve [95% confidence interval] of 0.875 [0.675 to 0.999], P = 0.004) or fibrosis (area under the curve [95% confidence interval] of 0.859 [0.754 to 0.963], P < 0.001) gene networks. Critical pathways in the Bayesian models were also analyzed by using the Fisher exact test and had P values <0.005. This study demonstrates that evaluating quantitative gene expression profiles with Bayesian modeling can identify significant transcriptional associations that have the potential to support the diagnostic capability of allograft histology. This integrated approach has broad implications in the field of transplant diagnostics.

Development of a Bayesian classifier for breast cancer risk stratification: a feasibility study.

BACKGROUND: Lifetime risk assessment tools are relatively limited in identifying breast cancer risk in younger women. The predictive value of mathematical models to estimate risk varies according to age, menopausal status, race/ethnicity, and family history. Current risk prediction models estimate population, not individual, levels of breast cancer risk; hence, individualized risk prediction models are needed to identify younger at-risk women who could benefit from timely risk reduction interventions. Clinical data collected as part of breast cancer screening studies may be modeled using Bayesian classification. PURPOSE: To train a proof-of-concept Bayesian classifier for breast cancer risk stratification. PATIENTS AND METHODS: We trained a Bayesian belief network (BBN) model on cohort data (including risk factors, demographic, electrical impedance scanning (EIS), breast imaging, and biopsy data) from a prospective pilot screening trial in younger women (N = 591). Receiver operating characteristic curve analysis and cross-validation of the model were used to derive preliminary guidance on the robustness of this approach and to gain insights into what a cross-validation exercise could provide in terms of risk stratification in a larger population. RESULTS: Independent predictors of biopsy outcome in the BBN model included personal breast disease history, breast size, EIS (low vs high risk) and imaging results, and Gail cutoff (5-year risk: <1.66% vs > or =1.66%). Area under the receiver operating characteristic curve and positive predictive value for benign and malignant biopsy outcomes were 0.88 and 97% and 0.97 and 42%, respectively. Patient-specific probability of biopsy outcome given positive EIS result and Gail model 5-year risk > or =1.66% indicated that the combined effect of these predictors on likelihood that a biopsy would prove malignant exceeded the sum of the individual effects; breast cancer likelihood is as follows: 3% (EIS negative and Gail model 5-year risk <1.66%) versus 9% (EIS positive and Gail model 5-year risk <1.66%) versus 27% (EIS negative and Gail model 5-year risk > or =1.66%) versus 45% (EIS positive and Gail model 5-year risk > or =1.66%). CONCLUSION: Clinical data collected as part of breast cancer screening studies can be modeled using Bayesian classification. The BBN model may be predictive and may provide clinically useful incremental risk information for individualized breast cancer risk assessment in younger women.

Translational research in surgical disease.

OBJECTIVE: To review cutting-edge, novel, implemented and potential translational research and to provide a glimpse into rich, innovative, and brilliant approaches to everyday surgical problems. DATA SOURCES: Scientific literature and unpublished results. STUDY SELECTION: Articles reviewed were chosen based on innovation and application to surgical diseases. DATA EXTRACTION: Each section was written by a surgeon familiar with cutting-edge and novel research in their field of expertise and interest. DATA SYNTHESIS: Articles that met criteria were summarized in the manuscript. CONCLUSIONS: Multiple avenues have been used for the discovery of improved means of diagnosis, treatment, and overall management of patients with surgical diseases. These avenues have incorporated the use of genomics, electrical impedence, statistical and mathematical modeling, and immunology.

Predictive model of outcome of targeted nodal assessment in colorectal cancer.

BACKGROUND: Improvement in staging accuracy is the principal aim of targeted nodal assessment in colorectal carcinoma. Technical factors independently predictive of false negative (FN) sentinel lymph node (SLN) mapping should be identified to facilitate operative decision making. PURPOSE: To define independent predictors of FN SLN mapping and to develop a predictive model that could support surgical decisions. PATIENTS AND METHODS: Data was analyzed from 2 completed prospective clinical trials involving 278 patients with colorectal carcinoma undergoing SLN mapping. Clinical outcome of interest was FN SLN(s), defined as one(s) with no apparent tumor cells in the presence of non-SLN metastases. To assess the independent predictive effect of a covariate for a nominal response (FN SLN), a logistic regression model was constructed and parameters estimated using maximum likelihood. A probabilistic Bayesian model was also trained and cross validated using 10-fold train-and-test sets to predict FN SLN mapping. Area under the curve (AUC) from receiver operating characteristics curves of these predictions was calculated to determine the predictive value of the model. RESULTS: Number of SLNs (<3; P = 0.03) and tumor-replaced nodes (P < 0.01) independently predicted FN SLN. Cross validation of the model created with Bayesian Network Analysis effectively predicted FN SLN (area under the curve = 0.84-0.86). The positive and negative predictive values of the model are 83% and 97%, respectively. CONCLUSION: This study supports a minimum threshold of 3 nodes for targeted nodal assessment in colorectal cancer, and establishes sufficient basis to conclude that SLN mapping and biopsy cannot be justified in the presence of clinically apparent tumor-replaced nodes.

Development of a Bayesian model to estimate health care outcomes in the severely wounded.

BACKGROUND: Graphical probabilistic models have the ability to provide insights as to how clinical factors are conditionally related. These models can be used to help us understand factors influencing health care outcomes and resource utilization, and to estimate morbidity and clinical outcomes in trauma patient populations. STUDY DESIGN: Thirty-two combat casualties with severe extremity injuries enrolled in a prospective observational study were analyzed using step-wise machine-learned Bayesian belief network (BBN) and step-wise logistic regression (LR). Models were evaluated using 10-fold cross-validation to calculate area-under-the-curve (AUC) from receiver operating characteristics (ROC) curves. RESULTS: Our BBN showed important associations between various factors in our data set that could not be developed using standard regression methods. Cross-validated ROC curve analysis showed that our BBN model was a robust representation of our data domain and that LR models trained on these findings were also robust: hospital-acquired infection (AUC: LR, 0.81; BBN, 0.79), intensive care unit length of stay (AUC: LR, 0.97; BBN, 0.81), and wound healing (AUC: LR, 0.91; BBN, 0.72) showed strong AUC. CONCLUSIONS: A BBN model can effectively represent clinical outcomes and biomarkers in patients hospitalized after severe wounding, and is confirmed by 10-fold cross-validation and further confirmed through logistic regression modeling. The method warrants further development and independent validation in other, more diverse patient populations.

Combat Wound Initiative program.

The Combat Wound Initiative (CWI) program is a collaborative, multidisciplinary, and interservice public-private partnership that provides personalized, state-of-the-art, and complex wound care via targeted clinical and translational research. The CWI uses a bench-to-bedside approach to translational research, including the rapid development of a human extracorporeal shock wave therapy (ESWT) study in complex wounds after establishing the potential efficacy, biologic mechanisms, and safety of this treatment modality in a murine model. Additional clinical trials include the prospective use of clinical data, serum and wound biomarkers, and wound gene expression profiles to predict wound healing/failure and additional clinical patient outcomes following combat-related trauma. These clinical research data are analyzed using machine-based learning algorithms to develop predictive treatment models to guide clinical decision-making. Future CWI directions include additional clinical trials and study centers and the refinement and deployment of our genetically driven, personalized medicine initiative to provide patient-specific care across multiple medical disciplines, with an emphasis on combat casualty care.