Assuntos
Humanos , Masculino , Feminino , Neoplasias Retais/cirurgia , Procedimentos Cirúrgicos do Sistema Digestório/métodos , Recidiva Local de Neoplasia/diagnóstico , Recidiva Local de Neoplasia/terapia , Equipe de Assistência ao Paciente , Radioterapia/métodos , Diagnóstico por Imagem , Colostomia/métodos , Biomarcadores Tumorais , Análise de Sobrevida , Diafragma da Pelve/cirurgia , Intervalo Livre de Doença , Procedimentos Cirúrgicos Minimamente Invasivos/métodos , Tratamento Farmacológico/métodos , Liberação de Cirurgia , Analgesia/métodos , Cuidados Intraoperatórios , Recidiva Local de Neoplasia/classificação , Antineoplásicos/uso terapêuticoRESUMO
BACKGROUND: The proper estimate of the risk of recurrences in early-stage oral tongue squamous cell carcinoma (OTSCC) is mandatory for individual treatment-decision making. However, this remains a challenge even for experienced multidisciplinary centers. OBJECTIVES: We compared the performance of four machine learning (ML) algorithms for predicting the risk of locoregional recurrences in patients with OTSCC. These algorithms were Support Vector Machine (SVM), Naive Bayes (NB), Boosted Decision Tree (BDT), and Decision Forest (DF). MATERIALS AND METHODS: The study cohort comprised 311 cases from the five University Hospitals in Finland and A.C. Camargo Cancer Center, São Paulo, Brazil. For comparison of the algorithms, we used the harmonic mean of precision and recall called F1 score, specificity, and accuracy values. These algorithms and their corresponding permutation feature importance (PFI) with the input parameters were externally tested on 59 new cases. Furthermore, we compared the performance of the algorithm that showed the highest prediction accuracy with the prognostic significance of depth of invasion (DOI). RESULTS: The results showed that the average specificity of all the algorithms was 71% . The SVM showed an accuracy of 68% and F1 score of 0.63, NB an accuracy of 70% and F1 score of 0.64, BDT an accuracy of 81% and F1 score of 0.78, and DF an accuracy of 78% and F1 score of 0.70. Additionally, these algorithms outperformed the DOI-based approach, which gave an accuracy of 63%. With PFI-analysis, there was no significant difference in the overall accuracies of three of the algorithms; PFI-BDT accuracy increased to 83.1%, PFI-DF increased to 80%, PFI-SVM decreased to 64.4%, while PFI-NB accuracy increased significantly to 81.4%. CONCLUSIONS: Our findings show that the best classification accuracy was achieved with the boosted decision tree algorithm. Additionally, these algorithms outperformed the DOI-based approach. Furthermore, with few parameters identified in the PFI analysis, ML technique still showed the ability to predict locoregional recurrence. The application of boosted decision tree machine learning algorithm can stratify OTSCC patients and thus aid in their individual treatment planning.
Assuntos
Algoritmos , Árvores de Decisões , Neoplasias Bucais/terapia , Recidiva Local de Neoplasia/diagnóstico , Recidiva Local de Neoplasia/epidemiologia , Aprendizado de Máquina Supervisionado , Neoplasias da Língua/terapia , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Teorema de Bayes , Brasil/epidemiologia , Quimiorradioterapia , Criança , Estudos de Coortes , Terapia Combinada , Feminino , Finlândia/epidemiologia , Humanos , Incidência , Masculino , Pessoa de Meia-Idade , Neoplasias Bucais/patologia , Recidiva Local de Neoplasia/classificação , Prognóstico , Máquina de Vetores de Suporte , Neoplasias da Língua/patologia , Adulto JovemRESUMO
OBJECTIVE: To compare the historic risk of recurrence (RR) and response to therapy to risk stratification estimated with historical pathology reports (HPRs) and contemporary re-review of the pathological slides in patients with differentiated thyroid cancer (DTC). SUBJECTS AND METHODS: Out of 210 DTC patients with low and intermediate RR who underwent total thyroidectomy and remnant ablation in our hospital, 63 available historic pathologic samples (HPS) were reviewed. The RR and the response to therapy were evaluated considering historical histological features (histological type, tumor size, capsular invasion, number of lymph node metastases) and then, reassessed after observing additional histological features (vascular invasion, extrathyroidal extension, size of lymph node metastases, presence of extranodal extension, and/or status of the resection margins). RESULTS: A change in the RR category was observed in 16 of 63 cases (25.4%). Out of 46 patients initially classified as low RR, 2 patients were reclassified as intermediate RR, 4 as high RR, and 1 as noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP). Out of 17 patients initially classified as intermediate RR, 3 were reassigned to the low RR group, 5 as high RR, and 1 as NIFTP. The percentages of structural incomplete response at final follow-up changed from 2.2 to 0% (p = 1) in patients with low RR and from 6.3 to 20% (p = 0.53) in patients with intermediate RR. CONCLUSION: A detailed report of specific features in the HPR of patients with DTC might give a more accurate RR classification and a better estimation of the response to treatment.
Assuntos
Carcinoma/patologia , Carcinoma/terapia , Recidiva Local de Neoplasia/patologia , Medição de Risco/métodos , Neoplasias da Glândula Tireoide/patologia , Neoplasias da Glândula Tireoide/terapia , Adulto , Idoso , Feminino , Humanos , Metástase Linfática , Masculino , Pessoa de Meia-Idade , Invasividade Neoplásica , Recidiva Local de Neoplasia/classificação , Valor Preditivo dos Testes , Valores de Referência , Reprodutibilidade dos Testes , Fatores de Risco , Tireoidectomia , Resultado do Tratamento , Adulto JovemRESUMO
ABSTRACT Objective To compare the historic risk of recurrence (RR) and response to therapy to risk stratification estimated with historical pathology reports (HPRs) and contemporary re-review of the pathological slides in patients with differentiated thyroid cancer (DTC). Subjects and methods Out of 210 DTC patients with low and intermediate RR who underwent total thyroidectomy and remnant ablation in our hospital, 63 available historic pathologic samples (HPS) were reviewed. The RR and the response to therapy were evaluated considering historical histological features (histological type, tumor size, capsular invasion, number of lymph node metastases) and then, reassessed after observing additional histological features (vascular invasion, extrathyroidal extension, size of lymph node metastases, presence of extranodal extension, and/or status of the resection margins). Results A change in the RR category was observed in 16 of 63 cases (25.4%). Out of 46 patients initially classified as low RR, 2 patients were reclassified as intermediate RR, 4 as high RR, and 1 as noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP). Out of 17 patients initially classified as intermediate RR, 3 were reassigned to the low RR group, 5 as high RR, and 1 as NIFTP. The percentages of structural incomplete response at final follow-up changed from 2.2 to 0% (p = 1) in patients with low RR and from 6.3 to 20% (p = 0.53) in patients with intermediate RR. Conclusion A detailed report of specific features in the HPR of patients with DTC might give a more accurate RR classification and a better estimation of the response to treatment.
Assuntos
Humanos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Idoso , Adulto Jovem , Neoplasias da Glândula Tireoide/patologia , Neoplasias da Glândula Tireoide/terapia , Carcinoma/patologia , Carcinoma/terapia , Medição de Risco/métodos , Recidiva Local de Neoplasia/patologia , Valores de Referência , Tireoidectomia , Valor Preditivo dos Testes , Reprodutibilidade dos Testes , Fatores de Risco , Resultado do Tratamento , Metástase Linfática , Invasividade Neoplásica , Recidiva Local de Neoplasia/classificaçãoRESUMO
En la actualidad, el enfoque terapéutico y el seguimiento de los pacientes con carcinoma diferenciado de tiroides (CDT) es individualizado de acuerdo con el riesgo de recurrencia de la enfermedad, con una menor tendencia a ablacionar a pacientes de bajo riesgo de recurrencia. Por otro lado, la evaluación de las respuestas al tratamiento se validó en pacientes tratados con tiroidectomía total (TT) y ablación con radioyodo (RAI), pero son escasos los estudios en pacientes no ablacionados. Los objetivos de este estudio fueron describir las características de una población de pacientes con CDT no ablacionados y validar las respuestas al tratamiento durante el seguimiento. Se incluyó a 88 pacientes con un seguimiento mínimo de 12 meses. El 87,6% eran mujeres y la edad promedio en el momento del diagnóstico fue de 47,5 años. Basados en el Consenso Intersocietario Argentino, el 97,7% de la cohorte fue clasificada como de bajo riesgo y el 2,3% como de riesgo intermedio de recurrencia. Los pacientes presentaron una respuesta inicial excelente en el 73% de los casos, con un estado sin evidencia de enfermedad al final del seguimiento en el 85,5%. Una minoría de los pacientes (1%) presentó una respuesta inicial estructural incompleta, la cual fue similar al final del seguimiento (1%). Por otro lado, el 26% de los pacientes presentó una respuesta inicial indeterminada, aunque solo el 13,5% permaneció con esta respuesta al final del seguimiento. Nuestros datos validan las respuestas al tratamiento en pacientes con CDT que recibieron TT no ablacionados como una herramienta efectiva para la estratificación del riesgo dinámico. Los pacientes apropiadamente seleccionados tratados sin RAI tienen un excelente pronóstico, con una baja frecuencia de respuesta estructural incompleta en el seguimiento, inclusive menor que la de los pacientes de bajo riesgo ablacionados.
The therapeutic approach and the follow-up of patients with differentiated thyroid cancer (DTC) is currently individualised according to the risk of recurrence, with a lower tendency to perform remnant ablation (RA) in patients with low risk of recurrence. While response to therapy assessment has been validated for DTC patients treated by total thyroidectomy (TT) and RA, it has not been widely confirmed in patients treated with TT without RA. The aims of this study were to describe the characteristics of the population of patients treated with TT without RA, and to validate the response to therapy. The study included 88 patients followed-up for at least 12 months after surgery. In the entire cohort, 87.9% were female and the mean age was 47.5 years old. Based on the Argentine Intersociety Consensus, 97.7% and 2.3% were classified as low risk and intermediate risk of recurrence, respectively. Patients had an initial excellent response to treatment in 73% of cases, with a disease-free status at the end of follow-up of 85.5%. A minority of patients (1%) presented with an initial structural incomplete response, which was similar at the end of follow-up (1%). On the other hand, 26% of the patients had an initial indeterminate response, although only 13.5% remained with this response at the end of follow-up. These results validate the responses to treatment in DTC patients treated with TT without RA as an effective tool for the dynamic risk stratification. Patients appropriately selected who did not receive RA have an excellent outcome, with a low frequency of structural incomplete response, even lower than that observed in low risk ablated patients.
Assuntos
Humanos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Idoso , Idoso de 80 Anos ou mais , Neoplasias da Glândula Tireoide/terapia , Avaliação de Resultado de Intervenções Terapêuticas , Comportamento de Redução do Risco , Neoplasias da Glândula Tireoide/cirurgia , Resultado do Tratamento , Tempo para o Tratamento/estatística & dados numéricos , Recidiva Local de Neoplasia/classificaçãoRESUMO
Introdução: Classificações de risco baseadas em fatores preditivos de recorrência e progressão são essenciais para condutas no câncer de bexiga. Tabelas de risco combinam essas variáveis para uso clínico. As tabelas de risco da Organização Europeia para Pesquisa e Tratamento do Câncer (EORTC) são aceitas para esse propósito, mas nunca foram validadas no Brasil. Objetivos: Validar as tabelas de risco EORTC e criar uma classificação de risco baseada na população de pacientes acompanhados em um centro terciário de câncer. Métodos: Estudo retrospectivo de 561 pacientes submetidos a ressecção transuretral (RTU) de câncer de bexiga superficial de fevereiro de 2005 a junho de 2011. As variáveis analisadas foram as mesmas das tabelas de risco EORTC. A regressão logística foi realizada usando SPSS. A análise da curva COR determinou o limite de tamanho do tumor. Resultados: As tabelas de risco EORTC não conseguiram prever recorrência nem progressão. Na análise para prever recorrência isoladamente, estadio T e tamanho do tumor previram o desfecho. O limite de tamanho do tumor foi definido em <4cm vs ≥4cm (AUC=0,61; p=0,001). Criamos uma classificação: Ta/CIS=0 pontos, T1=4 pontos, tamanho do tumor=0 ou 3 pontos. A classificação de risco foi obtida somando os pontos. A taxa de recorrência em 2 anos foi: escore 0=11,2%; escore 3=20,7%; escore 4=29,2%; escore 7=37,9%. Para prever recorrência e progressão, estadio T e tamanho do tumor previram significativamente o desfecho. A classificação em escores foi: Ta/CIS=0 pontos, T1=2 pontos, tamanho do tumor = 0 ou 2 pontos. A classificação de risco foi obtida somando os pontos. A taxa de recorrência em 2 anos foi: escore 0=17%; escore 2=28,6%; escore 4=40,7%. Conclusões: Constatamos que as tabelas de risco EORTC não conseguiram prever recorrência ou progressão do câncer de bexiga na nossa população. Portanto, desenvolvemos uma classificação de risco para auxiliar urologistas a individualizar as condutas por paciente.
Introduction: Risk classification based on predictive factors of bladder cancer recurrence and progression is essential for management decision. Risk tables combine these variables for clinical practice use. European Organization for Research and Treatment of Cancer (EORTC) risk tables are widely accepted for this purpose, however they were never validated in Brazil. Our aim was to validate the EORTC risk tables and create a risk classification based on our population. Methods: Retrospective study of 561 patients who underwent transurethral resection of superficial bladder from February 2005 to June 2011. Variables analyzed were the same as EORTC risk tables. Logistic regression was performed using SPSS. ROC curve analysis was used for determining the cut-off for tumor size. Results: EORTC risk tables were not able to predict neither disease recurrence nor progression. In our analysis for predicting bladder cancer recurrence alone, we found that T stage and tumor size predicted outcome. Tumor size cut-off was defined as < 4 cm vs ≥ 4 (AUC=0.61; p=0.001). We created a scoring classification: Ta/CIS=0 points, T1=4 points, tumor size=0 or 3 points. Risk classification was obtained by adding the points accordingly and the following recurrence rate at 2 yrs by group: score 0=11.2%; score 3=20.7%; score 4=29.2%; score 7=37.9%. The statistical model for bladder cancer recurrence or progression found that T stage and tumor size predicted the outcome. The scoring classification was: Ta/CIS=0 points, T1=2 points, tumor size=0 or 2 points. Risk classification was obtained by adding the points accordingly and the following recurrence rate at 2 yrs by group: score 0=17%; score 2=28.6%; score 4=40.7%. Conclusions: We found that EORTC risk tables could not predict bladder cancer recurrence or progression in our patient population, possibly due to differences in patient characteristics. Therefore, we developed a new risk classification to aid urologists to individualize the management decision per patient.
Assuntos
Humanos , Masculino , Feminino , Adulto , Idoso , Institutos de Câncer , Recidiva Local de Neoplasia/classificação , Neoplasias da Bexiga Urinária , Estudo de Validação , Brasil/epidemiologia , Progressão da Doença , RecidivaRESUMO
Breast cancer is the most frequent malignancy in women worldwide. Distinct intrinsic subtypes of breast cancer have different prognoses, and their relative prevalence varies significantly among ethnic groups. Little is known about the prevalence of breast cancer intrinsic subtypes and their association with clinicopathological data and genetic ancestry in Latin Americans. Immunohistochemistry surrogates from the 2013 St. Gallen International Expert Consensus were used to classify breast cancers in 301 patients from Colombia into intrinsic subtypes. We analyzed the distribution of subtypes by clinicopathological variables. Genetic ancestry was estimated from a panel of 80 ancestry informative markers. Luminal B breast cancer subtype was the most prevalent in our population (37.2%) followed by luminal A (26.3%), non-basal triple negative (NBTN) (11.6%), basal like (9%), human epidermal growth factor receptor 2 (HER2) enriched (8.6%) and unknown (7.3%). We found statistical significant differences in distribution between Colombian region (P = 0.007), age at diagnosis (P = 0.0139), grade (P < 0.001) and recurrence (P < 0.001) according to intrinsic subtype. Patients diagnosed with HER2-enriched, basal-like and NBTN breast cancer had the highest African ancestry. Future studies analyzing the molecular profiles of breast cancer in Colombian women will help us understand the molecular basis of this subtype distribution and compare the molecular characteristics of the different intrinsic subtypes in Colombian patients.
Assuntos
Biomarcadores Tumorais/genética , Neoplasias da Mama/epidemiologia , Recidiva Local de Neoplasia/epidemiologia , Prognóstico , Adulto , Idoso , População Negra/genética , Neoplasias da Mama/classificação , Neoplasias da Mama/genética , Colômbia/epidemiologia , Feminino , Humanos , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/classificação , Recidiva Local de Neoplasia/genética , Receptor ErbB-2/genética , Receptores de Estrogênio/genética , Receptores de Progesterona/genéticaAssuntos
Carcinoma Basocelular/classificação , Carcinoma Basocelular/patologia , Dermoscopia , Neoplasias Cutâneas/classificação , Neoplasias Cutâneas/patologia , Adulto , Idoso , Idoso de 80 Anos ou mais , Carcinoma Basocelular/epidemiologia , Estudos Transversais , Feminino , Humanos , Masculino , México/epidemiologia , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/classificação , Recidiva Local de Neoplasia/epidemiologia , Recidiva Local de Neoplasia/patologia , Fatores de Risco , Sensibilidade e Especificidade , Neoplasias Cutâneas/epidemiologiaRESUMO
OBJECTIVES: The aims of this study were to validate the proposed Latin American Thyroid Society (LATS) risk of recurrence stratification system and to compare the findings with those of the American Thyroid Association (ATA) risk of recurrence stratification system. SUBJECTS AND METHODS: This study is a retrospective review of papillary thyroid cancer patients treated with total thyroidectomy and radioactive iodine at a single experienced thyroid cancer center and followed according to the LATS management guidelines. Each patient was risk-stratified using both the LATS and ATA staging systems. The primary endpoints were (i) the best response to initial therapy defined as either remission (stimulated thyroglobulin [Tg] <1 ng/mL, negative ultrasonography) or persistent disease (biochemical and/or structural), and (ii) clinical status at final follow-up defined as no evidence of disease (suppressed Tg <1 ng/mL, negative ultrasonography), biochemical persistent disease (suppressed Tg >1 ng/mL in the absence of structural disease), structural persistent disease (locoregional or distant metastases), or recurrence (biochemical or structural disease identified after a period of no evidence of disease). RESULTS: One hundred seventy-one papillary thyroid cancer patients were included (mean age 45 ± 16 years, followed for a median of 4 years after initial treatment). Both the ATA and LATS risk stratification systems provided clinically meaningful graded estimates with regard to (i) the likelihood of achieving remission in response to initial therapy, (ii) the likelihood of having persistent structural disease in response to initial therapy and at final follow-up, (iii) the likely locations of the persistent structural disease (locoregional vs. distant metastases), (iv) the likelihood of recurrence, and (v) the likelihood of being no evidence of disease at final follow-up. The likelihood of having persistent biochemical evidence of disease was not significantly different across the staging categories. CONCLUSIONS: Both the ATA and LATS risk of recurrence systems effectively risk-stratify patients with regard to multiple important clinical outcomes. When used in conjunction with a staging system that predicts disease-specific mortality, either of these systems can be used to guide risk-adapted individualized initial management recommendations.
Assuntos
Carcinoma/diagnóstico , Carcinoma/patologia , Recidiva Local de Neoplasia/prevenção & controle , Glândula Tireoide/patologia , Neoplasias da Glândula Tireoide/diagnóstico , Neoplasias da Glândula Tireoide/patologia , Adulto , Idoso , Carcinoma/classificação , Carcinoma Papilar , Bases de Dados Factuais , Feminino , Humanos , Radioisótopos do Iodo/uso terapêutico , América Latina , Masculino , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/classificação , Indução de Remissão , Estudos Retrospectivos , Risco , Sociedades Médicas , Tireoglobulina/uso terapêutico , Câncer Papilífero da Tireoide , Neoplasias da Glândula Tireoide/classificação , Tireoidectomia , Resultado do Tratamento , Estados UnidosRESUMO
PURPOSE: To evaluate 20 cases of nonmetastatic synovial sarcoma of the extremities regarding prognostic factors, and to propose a histologic grading system with prognostic significance. METHODS: The cases of 20 patients (14 females and 6 males) with nonmetastatic synovial sarcomas of the extremities treated between 1985 and 1998, were retrospectively evaluated regarding prognostic factors. A histologic grading system with prognostic significance is proposed. RESULTS: The mean follow-up period was 48.4 months (range, 16-116 months). There was local recurrence in 3 cases (15%), microscopic surgical margin being the only prognostic factor identified. Seven patients (35%) died of the disease in a mean postoperative period of 31.7 months (range, 16-53 months), all with pulmonary or brain metastasis. The survival rate was 65% in 48.4 months of follow-up. CONCLUSION: The unfavorable prognostic factors identified regarding survival were high histologic grade, tumors proximal to the knee or elbow, and spontaneous tumor necrosis over 25%. Local recurrence did not have influence on survival in this study. The presence of mast cells appears to have a positive influence on survival, although statistical significance was not reached (P = 0.07). The oncologic and functional result was good in 6 cases (30%), regular in 7 (35%), and poor in 7 cases (35%).