A Machine Learning Method for Identifying Lung Cancer Based on Routine Blood Indices: Qualitative Feasibility Study

Background

Liquid biopsies based on blood samples have been widely accepted as a diagnostic and monitoring tool for cancers, but extremely high sensitivity is frequently needed due to the very low levels of the specially selected DNA, RNA, or protein biomarkers that are released into blood. However, routine blood indices tests are frequently ordered by physicians, as they are easy to perform and are cost effective. In addition, machine learning is broadly accepted for its ability to decipher complicated connections between multiple sets of test data and diseases.

Objective

The aim of this study is to discover the potential association between lung cancer and routine blood indices and thereby help clinicians and patients to identify lung cancer based on these routine tests.

Methods

The machine learning method known as Random Forest was adopted to build an identification model between routine blood indices and lung cancer that would determine if they were potentially linked. Ten-fold cross-validation and further tests were utilized to evaluate the reliability of the identification model.

Results

In total, 277 patients with 49 types of routine blood indices were included in this study, including 183 patients with lung cancer and 94 patients without lung cancer. Throughout the course of the study, there was correlation found between the combination of 19 types of routine blood indices and lung cancer. Lung cancer patients could be identified from other patients, especially those with tuberculosis (which usually has similar clinical symptoms to lung cancer), with a sensitivity, specificity and total accuracy of 96.3%, 94.97% and 95.7% for the cross-validation results, respectively. This identification method is called the routine blood indices model for lung cancer, and it promises to be of help as a tool for both clinicians and patients for the identification of lung cancer based on routine blood indices.

Conclusions

Lung cancer can be identified based on the combination of 19 types of routine blood indices, which implies that artificial intelligence can find the connections between a disease and the fundamental indices of blood, which could reduce the necessity of costly, elaborate blood test techniques for this purpose. It may also be possible that the combination of multiple indices obtained from routine blood tests may be connected to other diseases as well.

Stereotactic image-guided neoadjuvant ablative single-dose radiation, then lumpectomy, for early breast cancer: the SIGNAL prospective single-arm trial of single-dose radiation therapy

Background and Purpose

Adjuvant whole-breast irradiation after breast-conserving surgery, typically delivered over several weeks, is the traditional standard of care for low-risk breast cancer. More recently, hypofractionated, partial-breast irradiation has increasingly become established. Neoadjuvant single-fraction radiotherapy (rt) is an uncommon approach wherein the unresected lesion is irradiated preoperatively in a single fraction. We developed the signal (Stereotactic Image-Guided Neoadjuvant Ablative Radiation Then Lumpectomy) trial, a prospective single-arm trial to test our hypothesis that, for low-risk carcinoma of the breast, the preoperative single-fraction approach would be feasible and safe.

Methods

Patients presenting with early-stage (T < 3 cm), estrogen-positive, clinically node-negative invasive carcinoma of the breast with tumours at least 2 cm away from skin and chest wall were enrolled. All patients received prone breast magnetic resonance imaging (mri) and prone computed tomography simulation. Treatable patients received a single 21 Gy fraction of external-beam rt (as volumetric-modulated arc therapy) to the primary lesion in the breast, followed by definitive surgery 1 week later. The primary endpoints at 3 weeks, 6 months, and 1 year were toxicity and cosmesis (that is, safety) and feasibility (defined as the proportion of mri-appropriate patients receiving rt).

Results

Of 52 patients accrued, 27 were successfully treated. The initial dosimetric constraints resulted in a feasibility failure, because only 57% of eligible patients were successfully treated. Revised dosimetric constraints were developed, after which 100% of patients meeting mri criteria were treated according to protocol. At 3 weeks, 6 months, and 1 year after the operation, toxicity, patient- and physician-rated cosmesis, and quality of life were not significantly different from baseline.

Conclusions

The signal trial presents a feasible method of implementing single-dose preoperative rt in early-stage breast cancer. This pilot study did not identify any significant toxicity and demonstrated excellent cosmetic and quality-of-life outcomes. Future randomized multi-arm studies are required to corroborate these findings.

Continuous Temperature-Monitoring Socks for Home Use in Patients With Diabetes: Observational Study

Background

Over 30 million people in the United States (over 9%) have been diagnosed with diabetes. About 25% of people with diabetes will experience a diabetic foot ulcer (DFU) in their lifetime. Unresolved DFUs may lead to sepsis and are the leading cause of lower-limb amputations. DFU rates can be reduced by screening patients with diabetes to enable risk-based interventions. Skin temperature assessment has been shown to reduce the risk of foot ulceration. While several tools have been developed to measure plantar temperatures, they only measure temperature once a day or are designed for clinic use only. In this report, wireless sensor-embedded socks designed for daily wear are introduced, which perform continuous temperature monitoring of the feet of persons with diabetes in the home environment. Combined with a mobile app, this wearable device informs the wearer about temperature increases in one foot relative to the other, to facilitate early detection of ulcers and timely intervention.

Objective

A pilot study was conducted to assess the accuracy of sensors used in daily wear socks, obtain user feedback on how comfortable sensor-embedded socks were for home use, and examine whether observed temperatures correlated with clinical observations.

Methods

Temperature accuracy of sensors was assessed both prior to incorporation in the socks, as well as in the completed design. The measured temperatures were compared to the reference standard, a high-precision thermostatic water bath in the range 20°C-40°C. A total of 35 patients, 18 years of age and older, with diabetic peripheral neuropathy were enrolled in a single-site study conducted under an Institutional Review Board–approved protocol. This study evaluated the usability of the sensor-embedded socks and correlated the observed temperatures with clinical findings.

Results

The temperatures measured by the stand-alone sensors were within 0.2°C of the reference standard. In the sensor-embedded socks, across multiple measurements for each of the six sensors, a high agreement (R²=1) between temperatures measured and the reference standard was observed. Patients reported that the socks were easy to use and comfortable, ranking them at a median score of 9 or 10 for comfort and ease of use on a 10-point scale. Case studies are presented showing that the temperature differences observed between the feet were consistent with clinical observations.

Conclusions

We report the first use of wireless continuous temperature monitoring for daily wear and home use in patients with diabetes and neuropathy. The wearers found the socks to be no different from standard socks. The temperature studies conducted show that the sensors used in the socks are reliable and accurate at detecting temperature and the findings matched clinical observations. Continuous temperature monitoring is a promising approach as an early warning system for foot ulcers, Charcot foot, and reulceration.

Radiologic-Pathologic Correlation of Tumor Thickness and Its Prognostic Importance in Squamous Cell Carcinoma of the Oral Cavity: Implications for the Eighth Edition Tumor, Node, Metastasis Classification

BACKGROUND AND PURPOSE

Addressing the performance of an imaging-based parameter compared to a "gold standard" pathologic measurement is essential to achieve accurate clinical T-classification. Our aim was to determine the radiologic-pathologic tumor thickness correlation and its prognostic value in oral squamous cell carcinoma.

MATERIALS AND METHODS

All pathologic T1-T3 (seventh edition of the Cancer Staging Manual of the American Joint Committee on Cancer) oral squamous cell carcinomas diagnosed between 2010 and 2015 were reviewed. Radiologic tumor thickness was measured on preoperative CT or MR imaging blinded to pathology. The radiologic-pathologic tumor thickness correlation was calculated. The impact of the imaging-to-surgery time interval and imaging technique on the correlation was explored. Intra-/interrater reliability on radiologic tumor thickness was calculated. The correlation of radiologic-versus-pathologic tumor thickness and its performance as the seventh edition T-category modifier was evaluated. Multivariable analysis assessed the prognostic value of the radiologic tumor thickness for overall survival adjusted for age, seventh edition T-category, and performance status.

RESULTS

For 354 consecutive patients, the radiologic-pathologic tumor thickness correlation was similar for the image-to-surgery interval of ≤4.0 weeks (ρ = 0.76) versus 4-8 weeks (ρ = 0.80) but lower in those with more than an 8-week interval (ρ = 0.62). CT and MR imaging had similar correlations (0.76 and 0.80). Intrarater and interrater reliability was excellent (0.88 and 0.84). Excluding 19 cases with an imaging-to-surgery interval of >8 weeks, 335 patients were eligible for further analysis. The radiologic-pathologic tumor thickness correlation was 0.78. The accuracy for upstaging the T-classification based on radiologic tumor thickness was 83% for pathologic T1 and 74% for pathologic T2 tumors. Multivariable analysis confirmed the prognostic value of radiologic tumor thickness (hazard ratio = 1.5, P = .02) for overall survival.

CONCLUSIONS

This study demonstrates a good radiologic-pathologic tumor thickness correlation. Intrarater and interrater reliability for radiologic tumor thickness was excellent. Radiologically thicker tumor was predictive of inferior survival.

Phase I study of concurrent and consolidation cisplatin and docetaxel chemotherapy with thoracic radiotherapy in non-small cell lung cancer

Background

We designed a phase i study of concurrent chemoradiotherapy (ccrt) with docetaxel (D) and cisplatin (C), followed by consolidation dc, for unresectable stage iii non-small cell lung cancer (nsclc).

Methods

Patients with histologically proven and unresectable stage iii nsclc were eligible. During ccrt, C was given every 3 weeks (75 mg/m²) and D given weekly. The starting dose of D was 20 mg/m², escalated in cohorts of 3 to define the maximum tolerated dose (mtd). Radiotherapy was prescribed to a dose of 60 Gy in 30 fractions. This was followed by 2 cycles of consolidation dc, which were dose escalated if ccrt was tolerated.

Results

Twenty-six patients were enrolled, with 1 excluded following evidence of metastatic disease. Nineteen patients completed both phases of treatment. There were 7 grade 3 events during ccrt (5 esophagitis, 2 nausea), and 8 grade 3 events during consolidation (2 neutropenia, 2 leukopenia, 1 esophagitis, 2 nausea, and 1 pneumonitis). Three patients had grade 4 neutropenia. No patients died due to toxicities. The mtd of concurrent weekly D was 20 mg/m². Consolidation D and C were each dose escalated to 75 mg/m² in 8 patients. The median overall survival (os) and progression-free survival (pfs) of all patients were 33.6 months and 17.2 months, respectively, with median follow-up of 26.6 months (range 0.43-110.8).

Conclusions

The use of docetaxel 20 mg/m² weekly and cisplatin 75 mg/m² every 3 weeks concurrent with thoracic radiotherapy, followed by consolidation docetaxel and cisplatin, both given at 75 mg/m² every 3 weeks, appears to be safe in this phase i trial.

Phase I Study of Concurrent and Consolidation Cisplatin and Docetaxel Chemotherapy with Thoracic Radiotherapy in Non-Small Cell Lung Cancer

Background: We designed a phase I study of concurrent chemoradiotherapy (CCRT) with docetaxel (D) and cisplatin (C), followed by consolidation DC, for unresectable stage III non-small cell lung cancer (NSCLC). Methods: Patients with histologically proven and unresectable stage III NSCLC were eligible. During CCRT, C was given every 3 weeks (75 mg/m2) and D given weekly. The starting dose of D was 20 mg/m2, escalated in cohorts of 3 to define the maximum tolerated dose (MTD). Radiotherapy was prescribed to a dose of 60 Gy in 30 fractions. This was followed by 2 cycles of consolidation DC, which were dose escalated if CCRT was tolerated. Results: Twenty-six patients were enrolled, with 1 excluded following evidence of metastatic disease. Nineteen patients completed both phases of treatment. There were 7 grade 3 events during CCRT (5 esophagitis, 2 nausea), and 8 grade 3 events during consolidation (2 neutropenia, 2 leukopenia, 1 esophagitis, 2 nausea, and 1 pneumonitis). Three patients had grade 4 neutropenia. No patients died due to toxicities. The MTD of concurrent weekly D was 20 mg/m2. Consolidation D and C were each dose escalated to 75 mg/m2 in 8 patients. The median overall survival (OS) and progression-free survival (pfs) of all patients were 33.6 months and 17.2 months, respectively, with median follow-up of 26.6 months (range 0.43–110.8). Conclusions: The use of docetaxel 20 mg/m2 weekly and cisplatin 75 mg/m2 every 3 weeks concurrent with thoracic radiotherapy, followed by consolidation docetaxel and cisplatin, both given at 75 mg/m2 every 3 weeks, appears to be safe in this phase I trial.

Upregulation of MARCKS in kidney cancer and its potential as a therapeutic target

Targeted therapeutics, such as those abrogating hypoxia inducible factor (HIF)/vascular endothelial growth factor signaling, are initially effective against kidney cancer (or renal cell carcinoma, RCC); however, drug resistance frequently occurs via subsequent activation of alternative pathways. Through genome-scale integrated analysis of the HIF-α network, we identified the major protein kinase C substrate MARCKS (myristoylated alanine-rich C kinase substrate) as a potential target molecule for kidney cancer. In a screen of nephrectomy samples from 56 patients with RCC, we found that MARCKS expression and its phosphorylation are increased and positively correlate with tumor grade. Genetic and pharmacologic suppression of MARCKS in high-grade RCC cell lines in vitro led to a decrease in cell proliferation and migration. We further demonstrated that higher MARCKS expression promotes growth and angiogenesis in vivo in an RCC xenograft tumor. MARCKS acted upstream of the AKT/mTOR pathway, activating HIF-target genes, notably vascular endothelial growth factor-A. Following knockdown of MARCKS in RCC cells, the IC50 of the multikinase inhibitor regorafenib was reduced. Surprisingly, attenuation of MARCKS using the MPS (MARCKS phosphorylation site domain) peptide synergistically interacted with regorafenib treatment and decreased survival of kidney cancer cells through inactivation of AKT and mTOR. Our data suggest a major contribution of MARCKS to kidney cancer growth and provide an alternative therapeutic strategy of improving the efficacy of multikinase inhibitors.

Graft-Versus-Host Disease Following Liver Transplantation: Development of a High-Incidence Rat Model and a Selective Prevention Method

Graft-versus-host disease (GvHD) following liver transplantation (LT) is a rare but serious complication with no presently available animal model and no preventive measures. To develop a rat model of GvHD after LT (LT-GvHD), we preconditioned hosts with sublethal irradiation plus reduction of natural killer (NK) cells with anti-CD8α mAb treatment, which invariably resulted in acute LT-GvHD. Compared with those in the peripheral counterpart, graft CD4⁺ CD25^- passenger T cells showed lower alloreactivities in mixed leukocyte culture. Immunohistology revealed that donor CD4⁺ T cells migrated and formed clusters with host dendritic cells in secondary lymphoid organs, with early expansion and subsequent accumulation in target organs. For selectively preventing GvHD, donor livers were perfused ex vivo with organ preservation media containing anti-TCRαβ mAb. T cell-depleted livers almost completely suppressed clinical GvHD such that host rats survived for >100 days. Our results showed that passenger T cells could develop typical LT-GvHD if resistant cells such as host radiosensitive cells and host radioresistant NK cells were suppressed. Selective ex vivo T cell depletion prevented LT-GvHD without affecting host immunity or graft function. This method might be applicable to clinical LT in prediagnosed high-risk donor-recipient combinations and for analyzing immunoregulatory mechanisms of the liver.

Guideline for radiotherapy with curative intent in patients with early-stage medically inoperable non-small-cell lung cancer

OBJECTIVES

For this guideline, we investigated the effectiveness of radiotherapy with curative intent in medically inoperable patients with early-stage non-small-cell lung cancer (nsclc).

METHODS

The guideline was developed by Cancer Care Ontario's Program in Evidence-Based Care and by the Lung Cancer Disease Site Group through a systematic review of mainly retrospective studies, expert consensus, and formal internal and external reviews.

RECOMMENDATIONS

■ Stereotactic body radiation therapy (sbrt) with curative intent is an option that should be considered for patients with early-stage, node-negative, medically inoperable nsclc. Qualifying Statements■ Because of the high dose per fraction, the planning process and treatment delivery for sbrt require the use of advanced technology to maintain an appropriate level of safety. Consistent patient positioning and 4-dimensional analysis of tumour and critical structure motion during simulation and treatment delivery are essential.■ Preliminary results for proton-beam therapy have been promising, but the technique requires further clinical study.■ Recommended fractionation schemes for sbrt should result in a biologically effective dose of 100 or greater by the linear quadric model, choosing an α/β value of 10 [bed_10(LQ) ≥ 100]. Qualifying Statements■ Because of the increased risk of treatment-related adverse events associated with centrally located tumours, consideration of tumour size and proximity to critical central structures is required when determining the dose and fractionation.■ Examples of dose-fractionation schemes used in the included studies have been provided.■ Based on the current evidence and the opinion of the authors, radiation doses at bed_10(LQ) greater than 146 might significantly increase toxicity and should be avoided.■ Determination of the radiation bed by the linear quadratic model has limitations for the extreme hypofractionated schemes used in sbrt.

Abstract P3-13-10: A comparison of the micro-impulse radar SAVI SCOUT to the radioactive I125 seed in localization of non-palpable breast cancer for breast conserving therapy

Breast conservation and primary radiation (BCT) is a widely used treatment for early stage breast cancer patients. Studies report a 20-40 percent re-excision rate to obtain clear margins. Current localization practices include needle, radioactive seed and intraoperative U/S. Seed localization has been found to decrease tissue volume excision and improve patient satisfaction. However, radioactive seed programs are difficult to implement due to cumbersome regulations by the Nuclear Regulatory Commission (NRC). SAVI SCOUT® is a new technology cleared by the FDA for tumor localization. This device utilizes non-radioactive, micro-impulse radar (radar) to provide surgical guidance. The aim of this study was to evaluate the SCOUT® and determine its equivalence to seed localization by comparing re-excision rates and specimen volume.

70 patients with clinical stage 0, I, or II breast cancer who were treated with BCT were included in this IRB approved review. 35 patients were compared using the SCOUT radar localization technique with 35 patients using the radioactive iodine 125 seed localization technique. All patients received a wide segmental resection. The tissue was oriented and assessed clinically (visualization and palpation) and radiographically (Kubtec's XPERT 40 Digital Specimen Radiography System) in the operating room. Additional margins were excised if deemed to be suspicious by the surgeon (unless the anterior margin was skin or the posterior margin was the pectoral muscle fascia). Final margin status for both groups was compared. A positive margin was any margin with tumor on ink. The total volume of the excised specimen plus additional margins was recorded by the pathologist.

In all 70 patients, the targeted lesions, seed and/or reflectors were successfully removed. There were 420 margins assessed (6 for each specimen), using the additional margins excised as the final margin for evaluation of tumor on ink. Of the 210 final margins in the specimens excised using the seed, 5 margins (2.38%) in 4 patients were positive. 5 margins (2.38%) were also positive in 4 patients using the SCOUT. Nine patients in total returned to the operating room for re-excision. [One re-excision was performed as physician preference for close (&lt;2mm) margins for DCIS.] 5/9 patients requiring re-excision were found to have residual disease. A total of 119 additional margins were excised from 51 patients at the initial operation. 68 margins from 26 patients (SCOUT) and 51 margins from 25 patients (seed). Of the 119, 5 margins were found to be positive. 3 margins 4.41% (3/68) in the SCOUT group and 2 margins 3.92% (2/51) in the seed group. The average volume resected from the SCOUT averaged 81.28 cm3 while the volume of the seed averaged 100.39 cm3 (p-value 0.209).

The use of SCOUT for non-palpable tumor localization was equivalent to seed localization when comparing margin re-excision rate and tissue volumes. We conclude that SCOUT is an excellent alternative in breast cancer localization and can be easily implemented in most hospitals for breast conservation therapy.

Citation Format: Nolano SE, Thalhiemer LO, Yu E, Grujic E, Carter WB, Frazier TG. A comparison of the micro-impulse radar SAVI SCOUT to the radioactive I125 seed in localization of non-palpable breast cancer for breast conserving therapy [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P3-13-10.

Fabrication and Characterization of Electrospun Thermoplastic Polyurethane/Fibroin Small-Diameter Vascular Grafts for Vascular Tissue Engineering

The demand for small-diameter blood vessel substitutes has been increasing due to a shortage of autograft vessels and problems with thrombosis and intimal hyperplasia with synthetic grafts. In this study, hybrid small-diameter vascular grafts made of thermoplastic polyurethane (TPU) and silk fibroin, which possessed a hybrid fibrous structure of an aligned inner layer and a random outer layer, were fabricated by the electrospinning technique using a customized striated collector that generated both aligned and random fibers simultaneously. A methanol post-treatment process induced the transition of fibroin protein conformation from the water-soluble, amorphous, and less ordered structures to the water-insoluble β-sheet structures that possessed robust mechanical properties and relatively slow proteolytic degradation. The methanol post-treatment also created crimped fibers that mimicked the wavy structure of collagen fibers in natural blood vessels. Ultrafine nanofibers and nanowebs were found on the electrospun TPU/fibroin samples, which effectively increased the surface area for cell adhesion and migration. Cyclic circumferential tensile test results showed compatible mechanical properties for grafts made of a soft TPU/fibroin blend compared to human coronary arteries. In addition, cell culture tests with endothelial cells after 6 and 60 days of culture exhibited high cell viability and good biocompatibility of TPU/fibroin grafts, suggesting the potential of applying electrospun TPU/fibroin grafts in vascular tissue engineering.