Development of a clinical decision model for thyroid nodules

Differences in the dielectric properties of various benign and malignant thyroid nodules

PURPOSE

This experiment was conducted to investigate the dielectric properties of different types of thyroid nodules. Our goal was to find a simple and fast method to detect thyroid diseases at different stages from the dielectric properties of thyroid nodules.

METHODS

We used the open-ended coaxial line method to measure the dielectric permittivities of thyroid tissues from 155 patients at frequencies ranging from 1 to 4000 MHz. Tissues that were investigated included normal thyroid tissue and benign and malignant thyroid nodules (nodular goiter, follicular adenoma, papillary carcinoma, and follicular carcinoma), as determined from pathological reports. Differences in dielectric properties were measured between each nodule and the surrounding 1 cm of tissue.

RESULTS

The analysis results revealed that the dielectric permittivity and conductivity values were positively correlated with the degree of malignancy of the nodule (normal < benign < malignant; all differences P < 0.05). This was more obvious at frequencies within 20~70 MHz, following the order normal tissue < nodular goiter < follicular adenoma < papillary carcinoma < follicular carcinoma. A significant difference (P < 0.05) in dielectric permittivity and conductivity was found when comparing these nodules with the surrounding 1 cm of tissue.

CONCLUSIONS

Normal, benign, and malignant nodules were successfully distinguished from one another, and dielectric permittivity was found to be a more sensitive parameter than conductivity. In particular, different disease types can be distinguished at a stimulation frequency of 20~70 MHz, which shows that dielectric properties have application prospects for the detection and diagnosis of cancer. At the same time, the dielectric parameter differences between the surrounding 1 cm of tissue and the diseased nodule can distinguish the tumor and its surrounding tissues in real time during surgery to determine the tumor boundary.

Total Thyroidectomy Versus Lobectomy in Small Nodules Suspicious for Papillary Thyroid Cancer: Cost-Effectiveness Analysis

OBJECTIVES/HYPOTHESIS

Recent American Thyroid Association Guidelines recommend either near-total/total thyroidectomy or lobectomy for patients with a thyroid nodule suspicious for papillary thyroid cancer (PTC) on fine-needle aspiration (FNA) biopsy (Bethesda V). In this analysis, we aim to assess the cost-effectiveness of lobectomy in comparison to total thyroidectomy.

STUDY DESIGN

Cost-effectiveness analysis.

METHODS

A Markov model cost-effectiveness analysis was performed for a base case followed for 20 years postoperatively. Cost and probabilities data were retrieved from the current literature. Effectiveness was represented by quality-adjusted life year (QALY).

RESULTS

Total thyroidectomy protocol produced an incremental cost of $2,681.36 and incremental effectiveness of -0.24 QALY as compared to lobectomy protocol (incremental cost-effectiveness ratio [ICER] = -$11,188.85/QALY). Sensitivity analysis demonstrated that total thyroidectomy becomes a cost-effective strategy only if the risk of stages III and IV PTC is 82.4% among patients with suspicious PTC on preoperative FNA. Lobectomy is cost effective and preferred over total thyroidectomy as long as lobectomy complications are less than 50%.

CONCLUSIONS

Total thyroidectomy is not just cost prohibitive but also associated with a lower effectiveness compared to lobectomy.

LEVEL OF EVIDENCE

2c Laryngoscope, 2020.

Diagnostic Accuracy of Ultrasonography in Classifying Thyroid Nodules Compared with Fine-Needle Aspiration

Background

Classifying thyroid lesions is challenging; nonetheless, using ultrasonography may allow for accurate diagnosis, differentiation and management of thyroid lesions and help avoid unnecessary biopsy.

Objectives

The main objective of the study is to determine the diagnostic accuracy of ultrasonography in classifying thyroid nodules compared with fine-needle aspiration.

Materials and Methods

This retrospective study included all 68 patients diagnosed with thyroid nodules at King Fahd Hospital of the University, Al Khobar, Saudi Arabia, between June 1, 2014, and November 30, 2016. Parameters were selected based on the Society of Radiologists in Ultrasound criteria. Ultrasonographic features, namely, nodule margins, echotexture, vascularity and calcifications, and fine-needle aspiration cytology (FNAC) results were reviewed by two radiologists blinded to each other's findings and validated by another experienced interventional radiologist. Ultrasonography results were compared against that of FNAC to calculate sensitivity and positive- and negative-likelihood ratios, and the nodule types were compared using Fisher's exact test.

Results

Of the 68 nodules analyzed, 59 were reported as benign using FNAC (specificity = 95%; P < 0.001). Of these 59, 56 were also reported as benign using ultrasonography. The specificity of ultrasonography in determining benign nodules was 94.9%, and the positive- and negative-likelihood ratios were 13.0 and 0.35, respectively. Six of the nine suspicious nodules were confirmed as malignant using FNAC, and the ultrasonography and FNAC findings were strongly associated (P = 0.001). According to the Society of Radiologists in Ultrasound criteria, FNAC and ultrasonography findings were significantly associated for nodule calcification (P = 0.001) and echogenicity (P = 0.001).

Conclusion

The diagnostic specificity of ultrasonography and FNAC in this study are consistent with those reported previously, indicating that ultrasonography reliably classifies thyroid nodules, and thus can assist in the decision-making regarding need for biopsy.

A predictive model of thyroid malignancy using clinical, biochemical and sonographic parameters for patients in a multi-center setting

BACKGROUND

Thyroid nodules are highly prevalent, but a robust, feasible method for malignancy differentiation has not yet been well documented. This study aimed to establish a practical model for thyroid nodule discrimination.

METHODS

Records for 2984 patients who underwent thyroidectomy were analyzed. Clinical, laboratory, and US variables were assessed retrospectively. Multivariate logistic regression analysis was performed and a mathematical model was established for malignancy prediction.

RESULTS

The results showed that the malignant group was younger and had smaller nodules than the benign group (43.5 ± 11.6 vs. 48.5 ± 11.5 y, p < 0.001; 1.96 ± 1.16 vs. 2.75 ± 1.70 cm, p < 0.001, respectively). The serum thyrotropin (TSH) level (median = 1.63 mIU/L, IQR (0.89-2.66) vs. 1.19 (0.59-2.10), p < 0.001) was higher in the malignant group than in the benign group. Patients with malignancies tested positive for anti-thyroglobulin antibody (TGAb) and anti-thyroid peroxidase antibody (TPOAb) more frequently than those with benign nodules (TGAb, 30.3% vs. 15.0%, p < 0.001; TPOAb, 25.6% vs. 18.0%, p = 0.028). The prevalence of ultrasound (US) features (irregular shape, ill-defined margin, solid structure, hypoechogenicity, microcalcifications, macrocalcifications and central intranodular flow) was significantly higher in the malignant group. Multivariate logistic regression analysis confirmed that age (OR = 0.963, 95% CI = 0.934-0.993, p = 0.017), TGAb (OR = 4.435, 95% CI = 1.902-10.345, p = 0.001), hypoechogenicity (OR = 2.830, 95% CI = 1.113-7.195, p = 0.029), microcalcifications (OR = 4.624, 95% CI = 2.008-10.646, p < 0.001), and central intranodular flow (OR = 2.155, 95% CI = 1.011-4.594, p < 0.05) were independent predictors of thyroid malignancy. A predictive model including four variables (age, TGAb, hypoechogenicity and microcalcification) showed an optimal discriminatory accuracy (area under the curve, AUC) of 0.808 (95% CI = 0.761-0.855). The best cut-off value for prediction was 0.52, achieving sensitivity and specificity of 84.6% and 76.3%, respectively.

CONCLUSION

A predictive model of malignancy that combines clinical, laboratory and sonographic characteristics would aid clinicians in avoiding unnecessary procedures and making better clinical decisions.

Dielectric Properties for Differentiating Normal and Malignant Thyroid Tissues

Background

The incidence rate of thyroid cancer has increased greatly during the last few decades, and highly sensitive and specific methods for early diagnosis and prognostic evaluation remain lacking. In this study, we investigated a novel approach based on microwave theory to detect thyroid cancer.

Material/Methods

Freshly excised thyroid tissues (n=236) from 48 patients were identified as normal or malignant using histology. Each sample was measured for effective dielectric permittivity and effective conductivity (0.5–8 GHz). The means of each of these parameters of the normal and malignant groups were compared.

Results

The effective dielectric permittivities of normal and malignant thyroid tissues were 24.026±1.951 to 17.950±1.648 and 69.782±2.734 to 57.356±1.802, respectively. Also, as a function of frequency, the effective conductivities of normal and malignant thyroid cancer were 0.8395±0.2013 to 1.8730±0.0979 and 1.8960±0.5024 to 9.7461±0.9349 (S/m), respectively. The mean effective dielectric permittivities and effective conductivities of normal thyroid tissues were significantly lower than that of thyroid cancer tissues.

Conclusions

Measuring the effective dielectric permittivity and effective conductivity of excised thyroid tissues may be a new and viable method to determine malignancy in thyroid cancer.

Can a Bayesian Belief Network Be Used to Estimate 1-year Survival in Patients With Bone Sarcomas?

BACKGROUND

Extremity sarcoma has a preponderance to present late with advanced stage at diagnosis. It is important to know why these patients die early from sarcoma and to predict those at high risk. Currently we have mid- to long-term outcome data on which to counsel patients and support treatment decisions, but in contrast to other cancer groups, very little on short-term mortality. Bayesian belief network modeling has been used to develop decision-support tools in various oncologic diagnoses, but to our knowledge, this approach has not been applied to patients with extremity sarcoma.

QUESTIONS/PURPOSES

We sought to (1) determine whether a Bayesian belief network could be used to estimate the likelihood of 1-year mortality using receiver operator characteristic analysis; (2) describe the hierarchal relationships between prognostic and outcome variables; and (3) determine whether the model was suitable for clinical use using decision curve analysis.

METHODS

We considered all patients treated for primary bone sarcoma between 1970 and 2012, and excluded secondary metastasis, presentation with local recurrence, and benign tumors. The institution's database yielded 3499 patients, of which six (0.2%) were excluded. Data extracted for analysis focused on patient demographics (age, sex), tumor characteristics at diagnosis (size, metastasis, pathologic fracture), survival, and cause of death. A Bayesian belief network generated conditional probabilities of variables and survival outcome at 1 year. A lift analysis determined the hierarchal relationship of variables. Internal validation of 699 test patients (20% dataset) determined model accuracy. Decision curve analysis was performed comparing net benefit (capped at 85.5%) for all threshold probabilities (survival output from model).

RESULTS

We successfully generated a Bayesian belief network with five first-degree associates and describe their conditional relationship with survival after the diagnosis of primary bone sarcoma. On internal validation, the resultant model showed good predictive accuracy (area under the curve [AUC] = 0.767; 95% CI, 0.72-0.83). The factors that predict the outcome of interest, 1-year mortality, in order of relative importance are synchronous metastasis (6.4), patient's age (3), tumor size (2.1), histologic grade (1.8), and presentation with a pathologic fracture (1). Patient's sex, tumor location, and inadvertent excision were second-degree associates and not directly related to the outcome of interest. Decision curve analysis shows that clinicians can accurately base treatment decisions on the 1-year model rather than assuming all patients, or no patients, will survive greater than 1 year. For threshold probabilities less than approximately 0.5, the model is no better or no worse than assuming all patients will survive.

CONCLUSIONS

We showed that a Bayesian belief network can be used to predict 1-year mortality in patients presenting with a primary malignancy of bone and quantified the primary factors responsible for an increased risk of death. Synchronous metastasis, patient's age, and the size of the tumor had the largest prognostic effect. We believe models such as these can be useful as clinical decision-support tools and, when properly externally validated, provide clinicians and patients with information germane to the treatment of bone sarcomas.

CLINICAL RELEVANCE

Bone sarcomas are difficult to treat requiring multidisciplinary input to strategize management. An evidence-based survival prediction can be a powerful adjunctive to clinicians in this scenario. We believe the short-term predictions can be used to evaluate services, with 1-year mortality already being a quality indicator. Mortality predictors also can be incorporated in clinical trials, for example, to identify patients who are least likely to experience the side effects of experimental toxic chemotherapeutic agents.

Predicting malignancy in thyroid nodules: feasibility of a predictive model integrating clinical, biochemical, and ultrasound characteristics

Background

Although the majority of thyroid nodules are benign the process of excluding malignancy is challenging and sometimes involves unnecessary surgical procedures. We explored the development of a predictive model for malignancy in thyroid nodules by integrating a combination of simple demographic, biochemical, and ultrasound characteristics.

Methods

Retrospective case-record review.

We reviewed records of patients with thyroid nodules referred to our institution from 2004 to 2011 (n = 536; female 84 %, mean age 51 years). All malignancy was proven histologically while benign disease was either confirmed histologically, or on cytology with minimum 36-month observation period. We focused on the following predictors: age, sex, smoking status, thyroid hormones (FT4 and TSH) and nodule characteristics on ultrasound. Variables were included in a multivariate logistic regression and bootstrap analyses were used to confirm results.

Results

Independent predictors of malignancy in the fully adjusted model were TSH (OR 1.53, 95 % CI 1.10, 2.12, p = 0.01), male gender (OR 3.45, 95 % CI 1.33, 8.92, p = 0.01), microcalcifications (OR 6.32, 95 % CI 2.82, 14.1, p < 0.001), and irregular nodule margins (OR 5.45, 95 % CI 1.61, 18.6, p = 0.006) Bootstrap analyses strengthened these associations and a parsimonious analysis consisting of these variables and age-group demonstrated an area under the curve of 0.77. A predictive score was sensitive (86.9 %) at low scores and highly specific (94.87 %) at higher scores for distinguishing benign from malignant disease.

Conclusions

A predictive model for malignancy using a combination of clinical, biochemical, and radiological characteristics may support clinicians in reducing unnecessary invasive procedures in patients with thyroid nodules.

Electronic supplementary material

The online version of this article (doi:10.1186/s13044-016-0033-y) contains supplementary material, which is available to authorized users.

2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer

BACKGROUND

Thyroid nodules are a common clinical problem, and differentiated thyroid cancer is becoming increasingly prevalent. Since the American Thyroid Association's (ATA's) guidelines for the management of these disorders were revised in 2009, significant scientific advances have occurred in the field. The aim of these guidelines is to inform clinicians, patients, researchers, and health policy makers on published evidence relating to the diagnosis and management of thyroid nodules and differentiated thyroid cancer.

METHODS

The specific clinical questions addressed in these guidelines were based on prior versions of the guidelines, stakeholder input, and input of task force members. Task force panel members were educated on knowledge synthesis methods, including electronic database searching, review and selection of relevant citations, and critical appraisal of selected studies. Published English language articles on adults were eligible for inclusion. The American College of Physicians Guideline Grading System was used for critical appraisal of evidence and grading strength of recommendations for therapeutic interventions. We developed a similarly formatted system to appraise the quality of such studies and resultant recommendations. The guideline panel had complete editorial independence from the ATA. Competing interests of guideline task force members were regularly updated, managed, and communicated to the ATA and task force members.

RESULTS

The revised guidelines for the management of thyroid nodules include recommendations regarding initial evaluation, clinical and ultrasound criteria for fine-needle aspiration biopsy, interpretation of fine-needle aspiration biopsy results, use of molecular markers, and management of benign thyroid nodules. Recommendations regarding the initial management of thyroid cancer include those relating to screening for thyroid cancer, staging and risk assessment, surgical management, radioiodine remnant ablation and therapy, and thyrotropin suppression therapy using levothyroxine. Recommendations related to long-term management of differentiated thyroid cancer include those related to surveillance for recurrent disease using imaging and serum thyroglobulin, thyroid hormone therapy, management of recurrent and metastatic disease, consideration for clinical trials and targeted therapy, as well as directions for future research.

CONCLUSIONS

We have developed evidence-based recommendations to inform clinical decision-making in the management of thyroid nodules and differentiated thyroid cancer. They represent, in our opinion, contemporary optimal care for patients with these disorders.

Bayesian belief network analysis applied to determine the progression of temporomandibular disorders using MRI

OBJECTIVES

This study investigated the applicability of a Bayesian belief network (BBN) to MR images to diagnose temporomandibular disorders (TMDs). Our aim was to determine the progression of TMDs, focusing on how each finding affects the other.

METHODS

We selected 1.5-T MRI findings (33 variables) and diagnoses (bone changes and disc displacement) of patients with TMD from 2007 to 2008. There were a total of 295 cases with 590 sides of temporomandibular joints (TMJs). The data were modified according to the research diagnostic criteria of TMD. We compared the accuracy of the BBN using 11 algorithms (necessary path condition, path condition, greedy search-and-score with Bayesian information criterion, Chow-Liu tree, Rebane-Pearl poly tree, tree augmented naïve Bayes model, maximum log likelihood, Akaike information criterion, minimum description length, K2 and C4.5), a multiple regression analysis and an artificial neural network using resubstitution validation and 10-fold cross-validation.

RESULTS

There were 191 TMJs (32.4%) with bone changes and 340 (57.6%) with articular disc displacement. The BBN path condition algorithm using resubstitution validation and 10-fold cross-validation was >99% accurate. However, the main advantage of a BBN is that it can represent the causal relationships between different findings and assign conditional probabilities, which can then be used to interpret the progression of TMD.

CONCLUSIONS

Osteoarthritic bone changes progressed from condyle to articular fossa and finally to mandibular bone contours. Disc displacement was directly related to severe bone changes. Early bone changes were not directly related to disc displacement. TMJ functional factors (condylar translation, bony space and disc form) and age mediated between bone changes and disc displacement.

Future directions for the early detection of colorectal cancer recurrence

Surgical resection remains a mainstay of treatment and is highly effective for localized colorectal cancer. However, ~30-40% of patients develop recurrence following surgery and 40-50% of recurrences are apparent within the first few years after initial surgical resection. Several variables factor into the ultimate outcome of these patients, including the extent of disease, tumor biology, and patient co-morbidities. Additionally, the time from initial treatment to the development of recurrence is strongly associated with overall survival, particularly in patients who recur within one year of their surgical resection. Current post-resection surveillance strategies involve physical examination, laboratory, endoscopic and imaging studies utilizing various high and low-intensity protocols. Ultimately, the goal is to detect recurrence as early as possible, and ideally in the asymptomatic localized phase, to allow initiation of treatment that may still result in cure. While current strategies have been effective, several efforts are evolving to improve our ability to identify recurrent disease at its earliest phase. Our aim with this article is to briefly review the options available and, more importantly, examine emerging and future options to assist in the early detection of colon and rectal cancer recurrence.

Bayesian networks for clinical decision support in lung cancer care

Survival prediction and treatment selection in lung cancer care are characterised by high levels of uncertainty. Bayesian Networks (BNs), which naturally reason with uncertain domain knowledge, can be applied to aid lung cancer experts by providing personalised survival estimates and treatment selection recommendations. Based on the English Lung Cancer Database (LUCADA), we evaluate the feasibility of BNs for these two tasks, while comparing the performances of various causal discovery approaches to uncover the most feasible network structure from expert knowledge and data. We show first that the BN structure elicited from clinicians achieves a disappointing area under the ROC curve of 0.75 (± 0.03), whereas a structure learned by the CAMML hybrid causal discovery algorithm, which adheres with the temporal restrictions, achieves 0.81 (± 0.03). Second, our causal intervention results reveal that BN treatment recommendations, based on prescribing the treatment plan that maximises survival, can only predict the recorded treatment plan 29% of the time. However, this percentage rises to 76% when partial matches are included.

Helicobacter pylori infection is associated with the presence of thyroid nodules in the euthyroid population

Helicobacter pylori infection is associated with extragastric diseases. The thyroid may be one of the targets of chronic inflammation. Here, we sought to investigate whether H. pylori infections were associated with the presence of thyroid nodules. A total of 988 euthyroid subjects from China were included in this cross-sectional study. Four hundred thirty-five (44.0%) subjects were diagnosed as having thyroid nodules, and 486 (49.2%) were diagnosed with H. pylori infections. The thyroid nodules group had a higher proportion of H. pylori infections than the control group (P = 0.002). Free thyroxine (FT4) levels were lower and the prevalence of thyroid nodules was higher in patients with H. pylori infection compared to those without infection, even after adjustment for age, gender, and body mass index (BMI; all P < 0.05). The prevalence of H. pylori infection showed a decreasing trend as serum FT4 level increased (P_trend = 0.020). Stepwise logistic regression analysis showed that H. pylori infection was significantly associated with the risk of thyroid nodules (odds ratio: 1.390, 95% confidence interval: 1.059–1.824, P = 0.018). Our results suggested that H. pylori infections were positively associated with the presence of thyroid nodules in the euthyroid population, whose thyroid functions were in the reference range.

Risk of thyroid cancer based on thyroid ultrasound imaging characteristics: results of a population-based study

IMPORTANCE

There is wide variation in the management of thyroid nodules identified on ultrasound imaging.

OBJECTIVE

To quantify the risk of thyroid cancer associated with thyroid nodules based on ultrasound imaging characteristics.

METHODS

Retrospective case-control study of patients who underwent thyroid ultrasound imaging from January 1, 2000, through March 30, 2005. Thyroid cancers were identified through linkage with the California Cancer Registry.

RESULTS

A total of 8806 patients underwent 11,618 thyroid ultrasound examinations during the study period, including 105 subsequently diagnosed as having thyroid cancer. Thyroid nodules were common in patients diagnosed as having cancer (96.9%) and patients not diagnosed as having thyroid cancer (56.4%). Three ultrasound nodule characteristics--microcalcifications (odds ratio [OR], 8.1; 95% CI, 3.8-17.3), size greater than 2 cm (OR, 3.6; 95% CI, 1.7-7.6), and an entirely solid composition (OR, 4.0; 95% CI, 1.7-9.2)--were the only findings associated with the risk of thyroid cancer. If 1 characteristic is used as an indication for biopsy, most cases of thyroid cancer would be detected (sensitivity, 0.88; 95% CI, 0.80-0.94), with a high false-positive rate (0.44; 95% CI, 0.43-0.45) and a low positive likelihood ratio (2.0; 95% CI, 1.8-2.2), and 56 biopsies will be performed per cancer diagnosed. If 2 characteristics were required for biopsy, the sensitivity and false-positive rates would be lower (sensitivity, 0.52; 95% CI, 0.42-0.62; false-positive rate, 0.07; 95% CI, 0.07-0.08), the positive likelihood ratio would be higher (7.1; 95% CI, 6.2-8.2), and only 16 biopsies will be performed per cancer diagnosed. Compared with performing biopsy of all thyroid nodules larger than 5 mm, adoption of this more stringent rule requiring 2 abnormal nodule characteristics to prompt biopsy would reduce unnecessary biopsies by 90% while maintaining a low risk of cancer (5 per 1000 patients for whom biopsy is deferred).

CONCLUSIONS AND RELEVANCE

Thyroid ultrasound imaging could be used to identify patients who have a low risk of cancer for whom biopsy could be deferred. On the basis of these results, these findings should be validated in a large prospective cohort.

Malignancy risk assessment in patients with thyroid nodules using classification and regression trees

Purpose. We sought to investigate the utility of classification and regression trees (CART) classifier to differentiate benign from malignant nodules in patients referred for thyroid surgery. Methods. Clinical and demographic data of 271 patients referred to the Sadoughi Hospital during 2006–2011 were collected. In a two-step approach, a CART classifier was employed to differentiate patients with a high versus low risk of thyroid malignancy. The first step served as the screening procedure and was tailored to produce as few false negatives as possible. The second step identified those with the lowest risk of malignancy, chosen from a high risk population. Sensitivity, specificity, positive and negative predictive values (PPV and NPV) of the optimal tree were calculated. Results. In the first step, age, sex, and nodule size contributed to the optimal tree. Ultrasonographic features were employed in the second step with hypoechogenicity and/or microcalcifications yielding the highest discriminatory ability. The combined tree produced a sensitivity and specificity of 80.0% (95% CI: 29.9–98.9) and 94.1% (95% CI: 78.9–99.0), respectively. NPV and PPV were 66.7% (41.1–85.6) and 97.0% (82.5–99.8), respectively. Conclusion. CART classifier reliably identifies patients with a low risk of malignancy who can avoid unnecessary surgery.

Classification of thyroid nodules using a resonance-frequency-based electrical impedance spectroscopy: a preliminary assessment

BACKGROUND

Ultrasound and ultrasound-guided fine-needle aspiration biopsy are considered the most effective approaches for both identifying and classifying thyroid nodules. However, despite continuing improvements in scanner technology and refinements in ultrasound/cytological classification guidelines, indeterminate findings still lead to diagnostic lobectomy under general anesthesia. This study aims to investigate the feasibility of applying a modified noninvasive electrical impedance spectroscopy (EIS) approach to classifying thyroid nodules.

METHOD

To increase nodule classification sensitivity, we developed a new EIS-based model that introduces an optimized inductance component, which increases the measured signal-to-noise ratio of capacitance variation in and about thyroid nodules. Our model then measures the change of resonance frequency when the positive reactance of the system inductor cancels out the negative reactance of the nodule capacitance in a multi-frequency electrical signal scan. The system is termed "resonance-frequency-based electrical impedance spectroscopy" (REIS). A portable REIS system with multiple probes was assembled and preliminarily tested in our clinical facility. From an ongoing prospective study, an initial data set of 160 REIS examinations including 27 verified cancer cases was used. From the data set, a number of EIS signal features was extracted and analyzed. A multi-feature-based Bayesian Belief Network was built to classify the detected thyroid nodules. A receiver operating characteristic data analysis method was applied to evaluate classification performance.

RESULTS

The results showed that (i) the median resonance frequency measured by the probe nearest to malignant nodules was in general lower than that measured in benign cases, and (ii) the median descending slope of EIS signal sweep curves computed from cancer cases was larger than that computed from benign cases. The Bayesian Belief Network yielded a classification performance as measured by the area under the receiver operating characteristic curve of 0.794 [with a 95% confidence interval of 0.709-0.863].

CONCLUSIONS

The study demonstrates that noninvasive measurement of REIS signal features may potentially provide useful supplementary information to assist in classifying between malignant and benign thyroid nodules. Such an approach may ultimately lead to a reduction in the number of unnecessary thyroid surgeries.

External validation of a nomogram that predicts the pathological diagnosis of thyroid nodules in a Chinese population

INTRODUCTION

Nomograms are statistical predictive models that can provide the probability of a clinical event. Nomograms have better performance for the estimation of individual risks because of their increased accuracy and objectivity relative to physicians' personal experiences. Recently, a nomogram for predicting the likelihood that a thyroid nodule is malignant was introduced by Nixon. The aim of this study was to determine whether Nixon's nomogram can be validated in a Chinese population.

MATERIALS AND METHODS

All consecutive patients with thyroid nodules who underwent surgery between January and June 2012 in our hospital were enrolled to validate Nixon's nomogram. Univariate and multivariate analyses were used to identify the risk factors for thyroid carcinoma. Discrimination and calibration were employed to evaluate the performance of Nixon's model in our population.

RESULTS

A total of 348 consecutive patients with 409 thyroid nodules were enrolled. Thyroid ultrasonographic characteristics, including shape, echo texture, calcification, margins, vascularity and number (solitary vs. multiple nodules), were associated with malignance in the multivariate analysis. The discrimination of all nodules group, the group with a low risk of malignancy (predictive proportion <50%) and the group with a high risk of malignancy (predictive proportion ≥50%) using Nixon's nomogram was satisfactory, and the area under the receiver operating characteristic curve of the three groups were 0.87, 0.75 and 0.72, respectively. However, the calibration was significant (p = 0.55) only in the high-risk group.

CONCLUSION

Nixon's nomogram is a valuable predictive model for the Chinese population and has been externally validated. It has good performance for patients with a high risk of malignancy and may be more suitable for use with these patients in China.

Surgical management of appendicular skeletal metastases in thyroid carcinoma

Background. Bone is a frequent site of metastasis from thyroid carcinoma, but prognostic factors for patients who have surgery for thyroid carcinoma bone metastases are poorly understood. Methods. A retrospective review at a single institution identified 41 patients that underwent surgery in the appendicular skeleton for thyroid carcinoma bone metastasis from 1988 to 2011. Results. Overall patient survival probability by Kaplan-Meier analysis after surgery for bone metastasis was 72% at 1 year, 29% at 5 years, and 20% at 8 years. Patients who had their tumor excised (P = 0.001) or presented with solitary bone involvement had a lower risk of death following surgery adjusting for age and gender. Disease progression at the surgery site occurred more frequently with a histological diagnosis of follicular carcinoma compared with other subtypes (P = 0.023). Multivariate analysis showed that tumor subtype, chemotherapy, and preoperative radiation treatment had no effect on survival after surgery. Patients treated with radioactive iodine had better survival following thyroidectomy, but not following surgery for bone metastases. Conclusions. For patients undergoing surgery for thyroid cancer bone metastasis, resection of the bone metastasis, if possible, has a survival benefit.

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.

Thyroid nodule management: clinical, ultrasound and cytopathological parameters for predicting malignancy

Although fine-needle aspiration cytology is considered to be the reference method for evaluating thyroid nodules, the results are inaccurate in approximately 10-30% of cases. Several studies have attempted to predict the risk of malignancy in thyroid nodules based on age, nodularity, thyrotropin values, thyroid autoimmune disease, hot/cold nodule status, and ultrasound parameters. However, no consensus has been found, and none of these parameters has significantly affected patient management. The management of indeterminate thyroid nodules and re-biopsies of nodules with initially benign cytological results remain important and controversial topics of discussion. The Bethesda cytological system and several studies on the use of molecular markers to predict malignancy from cytological samples of thyroid nodules need further clarification. More in-depth discussions among and continuous education of the specialists involved in treating thyroid disease are necessary to improve the management of these patients. This review aims to examine the clinical, laboratory, ultrasound, and scintigraphic parameters that can be used for thyroid nodule management.

Transcutaneous computed bioconductance measurement in lung cancer: a treatment enabling technology useful for adjunctive risk stratification in the evaluation of suspicious pulmonary lesions

Lung cancer is the number one cause of cancer deaths in North America and is rapidly increasing worldwide. Although there are advances being made in the multidisciplinary management and combined-modality therapies of lung cancers, most cases are still diagnosed in later noncurable stages. Early detection has hinged on clinical risk assessment and on the future possibility of screening by low-dose computed tomography of the chest; however, this will only vastly increase the number of indeterminate pulmonary lesions (IPLs) being detected. Given that the majority of radiographically detected lung lesions are benign, and tissue confirmation by various invasive biopsy tests has increased risks and costs, a noninvasive adjunctive test that can stratify likelihood of an indeterminate lung lesion as malignant or benign will be a useful treatment-enabling technology to speed up diagnosis and treatment of lung cancers at a more curable stage and defer unnecessary invasive procedures that have potential for harm. Measurement of transcutaneous bioconductance using the differential conductivity properties of cancerous versus benign tissue has been previously demonstrated on nonlung lesions. Thus, it has the potential of being a noninvasive, simple-to-perform and repeatable test that may be valuable in assessing lung lesions. In this prospective study of subjects with known thoracic malignancies, computed bioconductance measurements discriminated between malignant lesions (29 primary lung cancers) from benign pathology (12) across a range of IPL sizes (0.8 cm and greater) with a sensitivity of 89.7% (positive predictive value 96.3%) and specificity of 91.7% (negative predictive value 78.5%). The technology seems to be effective across a range of tumor thoracic locations, cell types, and stages. Additional cohorts of subjects will be used to validate testing and for refinement of the current algorithm, which at present has a test performance with a receiver operating characteristic of 90.7%. Noninvasive transcutaneous computed bioconductance measurement can become a standard risk assessment and therapy-enabling tool in the evaluation of IPLs.

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.

Avoiding unnecessary fine-needle aspiration cytology by accuractely predicting the benign nature of thyroid nodules using ultrasound

Objective:

The objective of this study was to describe a reliable ultrasound based index scoring system based on ultraound characteristics to identify benign thyroid nodules and avoid unnecessary fine needle aspiration cytology.

Materials and Methods:

Patients undergoing ultrasound-guided fine-needle aspiration cytology (FNAC) for thyroid nodules were evaluated prospectively. A total of 284 patients were evaluated from November 2005 to November 2011. There were 284 nodules. Any solid or partly solid focal nodule in the thyroid gland was included in the study. Cysts with no solid component were excluded. We used LOGIQ 9 (GE Healthcare) scanner equipped with a 10--14 MHz linear matrix transducer with color and power Doppler capability. Four US characteristics were evaluated, i.e., nodule margins, echo texture, vascularity, and calcification. Fine needle aspiration (FNA) was performed on all nodules. The nodules were labeled benign or suspicious using an ultrasound index score and the results compared with FNAC. Follicular neoplasms on fine-needle aspiration cytology were further assessed by excision biopsy and histology. Cytology/histology was used as the final diagnosis.

Results:

In total 284 nodules were analyzed. All the 234 nodules in US labeled benign category were proven to be benign on cytology/histology. Therefore the specificity of ultrasound in labeling a nodule benign was 100%. Twenty of the 50 nodules that were suspicious on US were malignant. The most significant US differentiating characteristics were nodule margins, vascularity, and microcalcification.

Conclusion:

Our results show that US can accurately characterize benign thyroid nodules using an index scoring system and therefore preclude FNAC in these patients.

A probabilistic analysis of completely excised high-grade soft tissue sarcomas of the extremity: an application of a Bayesian belief network

BACKGROUND

It is important to understand the relative importance of prognostic variables in patients with soft tissue sarcomas. The purpose of this study was to describe the hierarchical relationships between features inherent to completely excised, localized high-grade soft tissue sarcomas of the extremity and compare the associations to those previously reported.

METHODS

Data were collected from the Memorial Sloan-Kettering Cancer Center Sarcoma Database. All adult patients with high-grade extremity soft tissue sarcomas who underwent complete excision (R0 margins) at our institution between 1982 and 2010 were included in the analysis. Bayesian belief network (BBN) modeling software was used to develop a hierarchical network of features trained to estimate the likelihood of disease-specific survival. Important relationships depicted by the BBN model were compared to those previously reported.

RESULTS

The records of 1318 consecutive patients met the inclusion criteria, and all were included in the analysis. First-degree associates of disease-specific survival were the primary tumor size; presence of and time to distant recurrence; and presence of and time to local recurrence. On cross-validation, the BBN model was sufficiently robust, with an area under the curve of 0.94 (95 % confidence interval 0.93-0.96).

CONCLUSIONS

We successfully described the hierarchical relationships between features inherent to patients with completely excised high-grade soft tissue sarcomas of the extremity. The relationships defined by the BBN model were similar to those previously reported. Cross-validation results were encouraging, demonstrating that BBN modeling can be used to graphically illustrate the complex hierarchical relationships between prognostic features in this setting.

A multidisciplinary survey on controversies in the use of EUS-guided FNA: assessing perspectives of surgeons, oncologists and gastroenterologists

BACKGROUND

EUS-guided FNA can help diagnose and differentiate between various pancreatic and other lesions.The aim of this study was to compare approaches among involved/relevant physicians to the controversies surrounding the use of FNA in EUS.

METHODS

A five-case survey was developed, piloted, and validated. It was collected from a total of 101 physicians, who were all either gastroenterologists (GIs), surgeons or oncologists. The survey compared the management strategies chosen by members of these relevant disciplines regarding EUS-guided FNA.

RESULTS

For CT operable T2NOM0 pancreatic tumors the research demonstrated variance as to whether to undertake EUS-guided FNA, at p < 0.05. For inoperable pancreatic tumors 66.7% of oncologists, 62.2% of surgeons and 79.1% of GIs opted for FNA (p < 0.05). For cystic pancreatic lesions, oncologists were more likely to send patients to surgery without FNA. For stable simple pancreatic cysts (23 mm), most physicians (66.67%) did not recommend FNA. For a submucosal gastric 19 mm lesion, 63.2% of surgeons recommended FNA, vs. 90.0% of oncologists (p < 0.05).

CONCLUSIONS

Controversies as to ideal application of EUS-FNA persist. Optimal guidelines should reflect the needs and concerns of the multidisciplinary team who treat patients who need EUS-FNA. Multi-specialty meetings assembled to manage patients with these disorders may be enlightening and may help develop consensus.

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.

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.

Application of Bayesian classifier for the diagnosis of dental pain

Toothache is the most common symptom encountered in dental practice. It is subjective and hence, there is a possibility of under or over diagnosis of oral pathologies where patients present with only toothache. Addressing the issue, the paper proposes a methodology to develop a Bayesian classifier for diagnosing some common dental diseases (D = 10) using a set of 14 pain parameters (P = 14). A questionnaire is developed using these variables and filled up by ten dentists (n = 10) with various levels of expertise. Each questionnaire is consisted of 40 real-world cases. Total 14*10*10 combinations of data are hence collected. The reliability of the data (P and D sets) has been tested by measuring (Cronbach's alpha). One-way ANOVA has been used to note the intra and intergroup mean differences. Multiple linear regressions are used for extracting the significant predictors among P and D sets as well as finding the goodness of the model fit. A naïve Bayesian classifier (NBC) is then designed initially that predicts either presence/absence of diseases given a set of pain parameters. The most informative and highest quality datasheet is used for training of NBC and the remaining sheets are used for testing the performance of the classifier. Hill climbing algorithm is used to design a Learned Bayes' classifier (LBC), which learns the conditional probability table (CPT) entries optimally. The developed LBC showed an average accuracy of 72%, which is clinically encouraging to the dentists.