Supporting the decision to perform molecular profiling for cancer patients based on routinely collected data through the use of machine learning.

BACKGROUND: Personalized medicine offers targeted therapy options for cancer treatment. However, the decision whether to include a patient into next-generation sequencing (NGS) testing is not standardized. This may result in some patients receiving unnecessary testing while others who could benefit from it are not tested. Typically, patients who have exhausted conventional treatment options are of interest for consideration in molecularly targeted therapy. To assist clinicians in decision-making, we developed a decision support tool using routine data from a precision oncology program. METHODS: We trained a machine learning model on clinical data to determine whether molecular profiling should be performed for a patient. To validate the model, the model's predictions were compared with decisions made by a molecular tumor board (MTB) using multiple patient case vignettes with their characteristics. RESULTS: The prediction model included 440 patients with molecular profiling and 13,587 patients without testing. High area under the curve (AUC) scores indicated the importance of engineered features in deciding on molecular profiling. Patient age, physical condition, tumor type, metastases, and previous therapies were the most important features. During the validation MTB experts made the same decision of recommending a patient for molecular profiling only in 10 out of 15 of their previous cases but there was agreement between the experts and the model in 9 out of 15 cases. CONCLUSION: Based on a historical cohort, our predictive model has the potential to assist clinicians in deciding whether to perform molecular profiling.

Integrating the 40-Gene Expression Profile (40-GEP) Test Improves Metastatic Risk-Stratification Within Clinically Relevant Subgroups of High-Risk Cutaneous Squamous Cell Carcinoma (cSCC) Patients.

INTRODUCTION: The validated 40-gene expression profile (40-GEP) test independently stratifies risk of regional or distant metastasis for cutaneous squamous cell carcinoma (cSCC) tumors with high-risk clinicopathologic features. This study evaluated the stratification of risk by the 40-GEP test in a large cohort of tumors with one or more high-risk factors and in clinically relevant subgroups, including tumors within National Comprehensive Cancer Network (NCCN) high- and very-high-risk groups, lower-stage BWH T1 and T2a tumors, and patients > 65 years old. METHODS: This multicenter (n = 58) performance study of the 40-GEP included 897 patients. Kaplan-Meier analyses were performed to assess risk stratification profiles for 40-GEP Class 1 (low), Class 2A (higher) and Class 2B (highest) risk groups, while nested Cox regression models were used to compare risk prediction of clinicopathologic risk classification systems versus risk classification systems in combination with 40-GEP. RESULTS: Patients classified as 40-GEP Class 1, Class 2A, or Class 2B had significantly different metastatic risk profiles (p < 0.0001). Integrating 40-GEP results into models with individual clinicopathologic risk factors or risk classification systems (Brigham and Women's Hospital, American Joint Committee on Cancer Staging Manual, 8th Edition) and NCCN demonstrated significant improvement in accuracy for prediction of metastatic events (ANOVA for model deviance, p < 0.0001 for all models). CONCLUSION: The 40-GEP test demonstrates accurate, independent, clinically actionable stratification of metastatic risk and improves predictive accuracy when integrated into risk classification systems. The improved accuracy of risk assessment when including tumor biology via the 40-GEP test ensures more risk-aligned, personalized patient management decisions.

Tumor-specific T cells in head and neck cancer have rescuable functionality and can be identified through single-cell co-culture.

BACKGROUND: Human papillomavirus (HPV)-negative head and neck squamous cell carcinoma (HNSCC) remains a treatment-resistance disease with limited response to immunotherapy. While T cells in HNSCC are known to display phenotypic dysfunction, whether they retain rescuable functional capacity and tumor-killing capability remains unclear. METHODS: To investigate the functionality and tumor-specificity of tumor-infiltrating lymphocytes (TILs) across HNSCCs, malignant cell lines and TILs were derived from 31 HPV-negative HNSCCs at the time of standard surgical resection. T cell functional capacity was evaluated through ex vivo expansion, immunophenotyping, and IsoLight single-cell proteomics. Tumor-specificity was investigated through both bulk and single-cell tumor-TIL co-culture. RESULTS: TILs could be successfully generated from 24 patients (77%), including both previously untreated and radiation recurrent HNSCCs. We demonstrate that across HNSCCs, TILs express multiple exhaustion markers but maintain a predominantly effector memory phenotype. After ex vivo expansion, TILs retain immunogenic functionality even from radiation-resistant, exhausted, and T cell-depleted disease. We further demonstrate tumor-specificity of T cells across HNSCC patients through patient-matched malignant cell-T cell co-culture. Finally, we use optofluidic technology to establish an autologous single tumor cell-single T cell co-culture platform for HNSCC. Cells derived from three HNSCC patients underwent single-cell co-culture which enabled identification and visualization of individual tumor-killing TILs in real-time in all patients. CONCLUSIONS: These studies show that cancer-specific T cells exist across HNSCC patients with rescuable immunogenicity and can be identified on a single-cell level. These data lay the foundation for development of patient-specific T cell immunotherapies in HNSCC.

Swapping data: A pragmatic approach for enabling academic-industrial partnerships.

Objectives: Academic institutions have access to comprehensive sets of real-world data. However, their potential for secondary use-for example, in medical outcomes research or health care quality management-is often limited due to data privacy concerns. External partners could help achieve this potential, yet documented frameworks for such cooperation are lacking. Therefore, this work presents a pragmatic approach for enabling academic-industrial data partnerships in a health care environment. Methods: We employ a value-swapping strategy to facilitate data sharing. Using tumor documentation and molecular pathology data, we define a data-altering process as well as rules for an organizational pipeline that includes the technical anonymization process. Results: The resulting dataset was fully anonymized while still retaining the critical properties of the original data to allow for external development and the training of analytical algorithms. Conclusion: Value swapping is a pragmatic, yet powerful method to balance data privacy and requirements for algorithm development; therefore, it is well suited to enable academic-industrial data partnerships.

Clinical Impact and Accuracy of Shave Biopsy for Initial Diagnosis of Cutaneous Melanoma.

INTRODUCTION: Effective treatment of malignant melanomas is dependent upon accurate histopathological staging of preoperative biopsy specimens. While narrow excision is the gold standard for melanoma diagnosis, superficial shave biopsies have become the preferred method by dermatologists but may transect the lesion and result in inaccurate Breslow thickness assessment. This is a retrospective cohort study evaluating an initial method of biopsy for diagnosis of cutaneous melanoma and indication for reoperation based on inaccurate initial T-staging. METHODS: We retrospectively analyzed consecutive patients referred to the Medical College of Wisconsin, a tertiary cancer center, with a diagnosis of primary cutaneous melanoma. Adult patients seen between 2015 and 2018 were included. Fisher's exact test was used to assess the association between method of initial biopsy and need for unplanned reoperation. RESULTS: Three hundred twenty three patients with cutaneous melanoma from the head and neck (H&N, n = 101, 31%), trunk (n = 90, 15%), upper extremity (n = 84, 26%), and lower extremity (n = 48, 28%) were analyzed. Median Breslow thickness was 0.54 mm (interquartile range = 0.65). Shave biopsy was the method of initial biopsy in 244 (76%), excision in 23 (7%), and punch biopsy in 56 (17%). Thirty nine (33%) shave biopsies had a positive deep margin, as did seven (23%) punch biopsies and 0 excisional biopsies. Residual melanoma at definitive excision was found in 131 (42.5%) of all surgical specimens: 95 (40.6%) shave biopsy patients, 32 (60.4%) punch biopsy patients, and four (19.0%) excision biopsy patients. Recommendations for excision margin or sentinel lymph node biopsy changed in 15 (6%) shave biopsy patients and five (9%) punch biopsy patients. CONCLUSIONS: Shave biopsy is the most frequent method of diagnosis of cutaneous melanoma in the modern era. While shave and punch biopsies may underestimate true T-stage, there was no difference in need for reoperation due to T-upstaging based on initial biopsy type, supporting current diagnostic practices. Partial biopsies can thus be used to guide appropriate treatment and definitive wide local excision when adjusting for understaging.

Gene expression profiling for metastatic risk in head and neck cutaneous squamous cell carcinoma.

OBJECTIVE: Over 50% of newly diagnosed cutaneous squamous cell carcinoma (cSCC) lesions occur in the head and neck (cSCC-HN), and metastasis to nodal basins in this region further complicates surgical and adjuvant treatment. The current study addressed whether the 40-gene expression profile (40-GEP) test can predict metastatic risk in cSCC-HN with improved accuracy and provide independent prognostic value to complement current risk assessment methods. STUDY DESIGN: Multicenter, retrospective cohort study. METHODS: Formalin-fixed paraffin-embedded primary tumor tissue and associated clinical data from patients with cSCC-HN (n = 278) were collected from 33 independent centers. Samples were analyzed via the 40-GEP test. Cases were staged per American Joint Committee on Cancer, Eighth Edition (AJCC8) and Brigham and Women's Hospital (BWH) criteria after comprehensive medical record and pathology report review. Metastasis-free survival (MFS) rates were determined, and risk factors were analyzed via Cox regression. RESULTS: The 40-GEP test classified the cohort into low (Class 1, n = 126; 45.3%), moderate (Class 2A, n = 134; 48.2%), and high (Class 2B, n = 18; 6.5%) metastatic risk at 3 years postdiagnosis. Regional/distant metastasis occurred in 54 patients (19.4%). MFS rates were 92.1% (Class 1), 76.1% (Class 2A), and 44.4% (Class 2B; p < .0001). Multivariate analysis of 40-GEP results with AJCC8 or BWH tumor stage, or clinicopathologic risk factors, demonstrated independent prognostic value of the 40-GEP test (p < .03). Accuracy of predicting metastatic risk was also improved using 40-GEP classification (p < .02). CONCLUSIONS: Improved metastatic risk stratification through the 40-GEP test could complement cSCC-HN risk assessment for better-informed decision-making for treatment and surveillance and ultimately improve patient outcomes. LEVEL OF EVIDENCE: 3.

Enhanced metastatic risk assessment in cutaneous squamous cell carcinoma with the 40-gene expression profile test.

Aim: To clinically validate the 40-gene expression profile (40-GEP) test for cutaneous squamous cell carcinoma patients and evaluate coupling the test with individual clinicopathologic risk factor-based assessment methods. Patients & methods: In a 33-site study, primary tumors with known patient outcomes were assessed under clinical testing conditions (n = 420). The 40-GEP results were integrated with clinicopathologic risk factors. Kaplan-Meier and Cox regression analyses were performed for metastasis. Results: The 40-GEP test demonstrated significant prognostic value. Risk classification was improved via integration of 40-GEP results with clinicopathologic risk factor-based assessment, with metastasis rates near the general cutaneous squamous cell carcinoma population for class 1 and ≥50% for class 2B. Conclusion: Combining molecular profiling with clinicopathologic risk factor assessment enhances stratification of cutaneous squamous cell carcinoma patients and may inform decision-making for risk-appropriate management strategies.

Plain language summary Cutaneous squamous cell carcinoma is a common skin cancer, with approximately 2 million cases diagnosed each year in the USA. Because substantial numbers of patients experience metastasis, which can result in death, accurate metastatic risk assessment is important. Clinicians use clinicopathologic factors to determine risk for disease progression. However, traditional methods miss pinpointing many patients who experience metastasis and sometimes categorize patients as at risk who do not develop metastasis, indicating that additional tools are needed. A molecular test, the 40-gene expression profile (40-GEP), was developed to predict metastatic risk based on the biology of the tumor. This study demonstrates that the 40-GEP, either as an independent tool or together with traditional methods, accurately identifies patients' risk of metastasis. Using the 40-GEP could improve patient management to improve patient outcomes.

Diagnosis and management of lentigo maligna: a review.

Lentigo maligna is a melanocytic neoplasm occurring on sun-exposed skin, usually on the head and neck, of middle-aged and elderly patients. It is thought to represent the in situ phase of lentigo maligna melanoma. The ill-defined nature and potentially large size of lesions can pose significant diagnostic and treatment challenges. The goal of therapy is to cure the lesions in order to prevent development of invasive disease, and surgical excision is the treatment of choice to achieve clear histological margins. Nonsurgical treatment modalities have been reported; however, evidence is lacking to support their use. Age, general health, and comorbidities need to be taken into account when deciding the right treatment modality for each individual patient.

A Bax-induced pro-oxidant state is critical for cytochrome c release during programmed neuronal death.

Bax is required for the apoptotic death of sympathetic neurons deprived of nerve growth factor (NGF). After NGF withdrawal, Bax translocates from the cytoplasm to the mitochondria of these cells and induces release of the proapoptotic protein cytochrome c. Here, we report that withdrawing NGF from mouse sympathetic neurons caused an increase of mitochondria-derived reactive oxygen species (ROS). Suppressing these ROS inhibited apoptosis. Bax deletion blocked death and prevented the ROS burst. Inducing a pro-oxidant state similar to that in NGF-deprived, wild-type cells caused cytochrome c release even in neurons lacking Bax. A similar ROS burst in cerebellar granule neurons undergoing apoptosis was also blocked by Bax deletion. These findings indicate that Bax lies upstream from increased ROS in NGF-deprived neurons and suggest that the Bax-induced ROS burst is both necessary and sufficient for cytochrome c redistribution in these cells.