RESUMO
BACKGROUND: Up to 30% of thyroid nodules are classified as indeterminate after fine needle aspiration biopsy. These indeterminate thyroid nodules (ITNs) require surgical pathology for definitive diagnosis. Molecular testing provides additional pre-operative cancer risk stratification but adds expense and invasive testing. The purpose of this study is to utilize a machine learning (ML) algorithm to predict malignancy of ITNs using data available from less invasive tests. MATERIALS AND METHODS: We conducted a retrospective study using medical records from one academic and one community center. Thyroid nodules with an indeterminate diagnosis on fine needle aspiration biopsy and completed diagnostic pathology were included. Linear, non-linear, and non-linear-ensemble ML methods were tested for accuracy when predicting malignancy using 10-fold cross-validation. Classifiers were evaluated using area under the receiver operating characteristics curve (AUROC). RESULTS: A total of 355 nodules met inclusion criteria. Of these, 171 (48.2%) were diagnosed with cancer. A Random Forest classifier performed the best, producing an accuracy of 79.1%, a sensitivity of 75.5%, specificity of 82.4%, positive predicative value of 80.3%, negative predictive value of 79.0%, and an AUROC of 0.859. CONCLUSIONS: ML methods accurately risk stratify ITNs using data gathered from existing, non-invasive, and inexpensive diagnostic tests. Applying an ML model with existing data can become a cost-effective alternative to molecular testing. Future studies will prospectively evaluate the performance of this ML approach when combined with expert judgment.
Assuntos
Neoplasias da Glândula Tireoide , Nódulo da Glândula Tireoide , Biópsia por Agulha Fina , Humanos , Aprendizado de Máquina , Estudos Retrospectivos , Sensibilidade e Especificidade , Neoplasias da Glândula Tireoide/diagnóstico , Neoplasias da Glândula Tireoide/patologia , Nódulo da Glândula Tireoide/patologiaRESUMO
BACKGROUND: Thyroid nodules are common; up to 67% of adults will show nodules on high-quality ultrasound, and 95% of these nodules are benign. FNA cytology is a crucial step in determining the risk of malignancy, and a false negative diagnosis at this stage delays cancer treatment. The purpose of this study is to develop a predictive model using machine learning which can identify false negative FNA results based on less-invasive clinical data. MATERIALS AND METHODS: We conducted a retrospective medical record review at one academic and one community center. Inclusion criteria were thyroid nodules evaluated by ultrasound and FNA with a Bethesda II (benign) result or malignancy detected on pathology or FNA. Linear, non-linear, and ensemble models were generated with scikit-learn using 10-fold cross validation with repetition and compared with AUROC. The classification task was the prediction of malignancy using information acquired from less-invasive ultrasound and FNA. RESULTS: A total of 604 subjects met inclusion criteria; 38 were diagnosed with malignancy. Of all algorithms tested, a Random Forest method achieved the best AUROC (0.64) in separating benign and malignant nodules, though the improvement over other tested algorithms was not statistically significant. CONCLUSIONS: A Random Forest model performed better than random chance using readily available data obtained via standard evaluation of thyroid nodules. The diagnostic probability threshold of this model can be varied to minimize false positives at the cost of increasing the number of false negatives. Future studies will prospectively evaluate the model's performance.
Assuntos
Neoplasias da Glândula Tireoide , Nódulo da Glândula Tireoide , Adulto , Biópsia por Agulha Fina , Humanos , Aprendizado de Máquina , Estudos Retrospectivos , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Neoplasias da Glândula Tireoide/patologia , Nódulo da Glândula Tireoide/diagnóstico por imagem , Nódulo da Glândula Tireoide/patologiaRESUMO
HYPOTHESIS: We hypothesized that players in the National Basketball Association (NBA) who sustained a shoulder destabilizing injury could return to play (RTP) successfully at a high rate regardless of treatment type. METHODS: We used publicly available data to identify and evaluate 50 players who sustained an in-season shoulder instability event (subluxation/dislocation) while playing in the NBA. Demographic variables, return to NBA gameplay, incidence of surgery, time to RTP, recurrent instability events, and player efficiency rating (PER) were collected. Overall RTP was determined, and players were compared by type of injury and mode of treatment. RESULTS: All players (50/50) returned to game play after sustaining a shoulder instability event. In those treated nonoperatively, athletes who sustained shoulder subluxations returned after an average of 3.6 weeks, compared with 7.6 weeks in those who sustained a shoulder dislocation (P = .037). Players who underwent operative management returned after an average of 19 weeks. Athletes treated operatively were found to have a longer time interval between a recurrent instability event (70 weeks vs. 28.5 weeks, P = .001). CONCLUSION: We found 100% rate of RTP after a shoulder instability event in an NBA athlete. Players who experience shoulder dislocations were found to miss more time before RTP and were more likely to undergo surgical intervention compared with those who experienced a subluxation. Surgical repair maintained a longer interval between recurrent instability. Future investigations should aim to evaluate outcomes based on surgical procedures and identify possible risk factors predictive of recurrent instability or failure to RTP.
Assuntos
Basquetebol/lesões , Tratamento Conservador , Instabilidade Articular/cirurgia , Volta ao Esporte , Luxação do Ombro/cirurgia , Lesões do Ombro/cirurgia , Adulto , Desempenho Atlético , Humanos , Instabilidade Articular/terapia , Masculino , Recidiva , Luxação do Ombro/terapia , Lesões do Ombro/terapia , Fatores de Tempo , Adulto JovemRESUMO
BACKGROUND: The rate of wound complications following traditional open Achilles tendon repair is reported at 7.6%. The purpose of this study is to characterize the rate of wound and other early complications following a specific minimally invasive Achilles tendon repair technique, and to identify any factors associated with increased risk. METHODS: The postoperative courses of 99 patients who underwent minimally invasive Achilles tendon repair by 2 surgeons at separate academic medical centers were retrospectively reviewed. Mean follow-up was 8.1 months (range 3.0-24.6 months). Repair technique was similar in all cases with the exception that 71 procedures used a longitudinal incision and a tourniquet, while 28 procedures used a transverse incision and no tourniquet (surgeon preference). The rates of complications were compared between patients with differing baseline and procedural characteristics. RESULTS: Of the 99 patients included in the study, 2 (2.0%) developed wound complications. There was no statistical difference in the rate of wound complications between patients in the longitudinal incision/tourniquet group and patients in the transverse incision/no tourniquet group (2.8% vs 0%; P = 1.000). Four patients (4.0%) developed sural neuropraxia. One patient developed deep venous thrombosis. There were no cases of rerupture. At final follow-up, all 99 patients had intact Thompson tests and well-healed wounds. CONCLUSIONS: The rate of wound complications following minimally invasive Achilles tendon repair is low at 2.0%. Patients should be counseled that although risk for wound complications may be lower with this minimally invasive technique, there are risks for sural neuropraxia and deep suture reaction. LEVELS OF EVIDENCE: Level III, Retrospective study.
Assuntos
Tendão do Calcâneo , Traumatismos dos Tendões , Tendão do Calcâneo/lesões , Tendão do Calcâneo/cirurgia , Humanos , Procedimentos Cirúrgicos Minimamente Invasivos/efeitos adversos , Procedimentos Cirúrgicos Minimamente Invasivos/métodos , Estudos Retrospectivos , Ruptura/cirurgia , Técnicas de Sutura/efeitos adversos , Traumatismos dos Tendões/etiologia , Traumatismos dos Tendões/cirurgia , Resultado do TratamentoRESUMO
Introduction: There is increasing interest in the early identification and treatment of adverse medical events following orthopaedic procedures. The purpose of this study is to characterize the timing of 8 early adverse events following open reduction and internal fixation of closed fractures of the ankle. Methods: A retrospective cohort study was conducted using the American College of Surgeons National Surgical Quality Improvement Program. A total of 17 318 patients undergoing open reduction and internal fixation of closed ankle fractures were identified. 48.4% of patients were discharged on the day of surgery. For each of 8 different early adverse events, the median postoperative day of diagnosis, interquartile range for day of diagnosis, and middle 80% for day of diagnosis were determined. Timing was compared between unimalleolar and bi-/trimalleolar fractures and between inpatient and outpatient procedures. Results: The median day of diagnosis (and interquartile range; middle 80%) for myocardial infarction was 2 (1-5; 0-17), pneumonia 3 (2-7; 1-19), acute kidney injury 6.5 (2-18; 2-20), urinary tract infection 7 (2-14; 0-24), pulmonary embolism 10 (3-21; 0-27), sepsis 15 (4-22; 1-28), deep vein thrombosis 17 (10-22; 3-27), and surgical site infection 19 (14-25; 8-28). Patients with bi-/trimalleolar fractures had earlier occurrence of myocardial infarction (day 2 vs 10), urinary tract infection (day 6.5 vs 9.5), and sepsis (day 10 vs 20.5). Inpatients had later occurrence of acute kidney injury (day 7 vs 3), but earlier occurrence of urinary tract infection (day 6 vs 15). Conclusions: These precisely described time periods for occurrence of specific adverse events enable heightened awareness among orthopaedic surgeons during the first month following open reduction and internal fixation of the ankle. Orthopaedic surgeons should have the lowest threshold for testing for each adverse event during the time period of greatest risk.Levels of Evidence: Therapeutic, Level III: Retrospective cohort study.
Assuntos
Fraturas do Tornozelo/cirurgia , Tornozelo/cirurgia , Fixação Interna de Fraturas/efeitos adversos , Fixação Interna de Fraturas/métodos , Redução Aberta/efeitos adversos , Redução Aberta/métodos , Complicações Pós-Operatórias/epidemiologia , Complicações Pós-Operatórias/etiologia , Adolescente , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pneumonia/epidemiologia , Pneumonia/etiologia , Embolia Pulmonar/epidemiologia , Embolia Pulmonar/etiologia , Melhoria de Qualidade , Qualidade da Assistência à Saúde , Estudos Retrospectivos , Infecção da Ferida Cirúrgica/epidemiologia , Infecção da Ferida Cirúrgica/etiologia , Fatores de Tempo , Adulto JovemRESUMO
BACKGROUND: The sudden and debilitating nature of lower extremity injuries can trigger mood disturbances, including major depressive disorder. METHODS: This prospective study enrolled patients undergoing operative repair of ankle fractures and Achilles ruptures and followed them for 1 year postoperatively. The validated Patient Health Questionnaire (PHQ-9) for depressive symptoms was administered at the preoperative visit and at postoperative weeks 1, 2, 4, 8, 16, 24, 32, 40, and 52. PHQ-9 is scored 0 to 27, with higher values indicating greater depression symptoms. RESULTS: Fifty-eight patients completed 1 year of follow-up. The mean PHQ-9 score was 2.7 (range, 0-20) at the preoperative visit, peaked at postoperative week 1 (4.9; range, 0-16), and reached its low at postoperative week 52 (0.8; range, 0-7). Cumulative incidences of depressive symptoms during the first year following surgery were 51.7% for at least mild depression, 22.4% for at least moderate depression, and 6.9% for severe depression. A history of mental health disorder and the inability to work during the period of postoperative immobilization were independently associated with greater depressive symptoms. CONCLUSION: The majority of patients undergoing operative treatment of Achilles ruptures and ankle fractures develop postoperative symptoms of mild to moderate depression that normalize after several months. Patients with a history of mental health disorder or who cannot work while immobilized postoperatively are at greatest risk. LEVEL OF EVIDENCE: Level II, prospective cohort study.
Assuntos
Tendão do Calcâneo , Fraturas do Tornozelo , Transtorno Depressivo Maior , Tendão do Calcâneo/cirurgia , Fraturas do Tornozelo/cirurgia , Depressão/epidemiologia , Humanos , Estudos Prospectivos , Ruptura , Resultado do TratamentoRESUMO
BACKGROUND: Total hip and knee arthroplasty (THA and TKA) are performed more commonly than total ankle arthroplasty (TAA), so patients and the orthopaedic community are more familiar with the likelihood of complications after THA and TKA than after TAA. The present study places early complication rates after TAA in the context of those after THA and TKA. METHODS: Patients who underwent TAA, THA, or TKA during 2006 to 2016 as part of the National Surgical Quality Improvement Program were identified. Multivariate regression was used to compare procedures with adjustment for baseline and anesthesia characteristics. RESULTS: One hundred thirty-eight thousand three hundred twenty-five patients underwent THA, 223,587 TKA, and 839 TAA. The total complication rate was lower for TAA (2.98%) compared with THA (4.92%, P = 0.011) and TKA (4.56%, P = 0.049). Similarly, the rate of blood transfusion was lower for TAA (0.48%) compared with THA (9.66%) and TKA (6.44%, P < 0.001 for each). The rate of additional surgery was lower for TAA compared with THA (0.48% versus 1.79%, P = 0.007). Finally, the rate of readmission was lower for TAA (1.45%) compared with THA (3.66%, P = 0.002) and TKA (3.40%, P = 0.005). DISCUSSION: Patients can be counseled that relative to THA and TKA, TAA is safer in the perioperative period, with lower rates of adverse events, blood transfusion, additional surgery, and hospital readmission.
Assuntos
Artroplastia de Substituição do Tornozelo , Artroplastia de Quadril , Artroplastia do Joelho , Complicações Pós-Operatórias/epidemiologia , Idoso de 80 Anos ou mais , Artroplastia de Substituição do Tornozelo/efeitos adversos , Artroplastia de Quadril/efeitos adversos , Artroplastia do Joelho/efeitos adversos , Transfusão de Sangue/estatística & dados numéricos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Readmissão do Paciente/estatística & dados numéricos , Complicações Pós-Operatórias/etiologia , Período Pós-Operatório , Reoperação/estatística & dados numéricos , SegurançaRESUMO
Foot and ankle surgeons routinely prescribe diagnostic imaging that exposes patients to potentially harmful ionizing radiation. It is unclear how well patients understand the radiation to which they are exposed. In this study, 946 consecutive new patients were surveyed regarding medical imaging and radiation exposure prior to their first appointment. Respondents compared the amount of radiation associated with chest X-rays (CXRs) with various types of foot and ankle imaging. Results were compared with actual values of radiation exposure from the published literature. Of 946 patients surveyed, 841 (88.9%) participated. Most had private insurance (82.8%) and a bachelor's degree or higher (60.6%). Most believed that foot X-ray, ankle X-ray, "low dose" foot and ankle computed tomography (CT) scan (alluding to cone-beam CT), and traditional foot and ankle CT scan contain similar amounts of ionizing radiation to CXR. This contradicts the published literature that suggests that the actual exposure to patients is 0.006, 0.006, 0.127, and 0.833 CXR equivalents of radiation, respectively. Of patients who had undergone an X-ray, 55.9% thought about the issue of radiation prior to the study, whereas 46.1% of those undergoing a CT scan considered radiation prior to the exam. Similarly, 35.2% and 27.6% reported their doctor having discussed radiation with them prior to obtaining an X-ray and CT scan, respectively. Patients greatly overestimate the radiation exposure associated with plain film X-rays and cone-beam CT scans of the foot and ankle, and may benefit from increased counseling regarding the relatively low radiation exposure associated with these imaging modalities.Level of Evidence: Level III: Prospective questionnaire.
Assuntos
Tornozelo/diagnóstico por imagem , Pé/diagnóstico por imagem , Conhecimento , Educação de Pacientes como Assunto , Pacientes/psicologia , Exposição à Radiação , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Exposição à Radiação/efeitos adversos , Exposição à Radiação/prevenção & controle , Inquéritos e QuestionáriosRESUMO
BACKGROUND: Patients are often made weightbearing as tolerated (WBAT) in a controlled ankle motion (CAM) boot for the management of various foot and ankle conditions. The CAM boot causes a leg length discrepancy (LLD) between the booted (longer) and contralateral (shorter) lower extremities. This discrepancy can potentially cause balance problems, undue strain on joints, and discomfort in patients. We hypothesized that a leg length-evening orthotic placed on the plantar aspect of the contralateral shoe improves balance among patients who are WBAT in a CAM boot. METHODS: Patients made WBAT in a CAM boot were randomized to either the leg length-evening orthotic intervention group or to a control group in which patients wore a normal shoe of their choice. Patients were followed for 2 weeks and asked a series of questions pertaining to balance and pain experienced at their knees, hips, and back. Balance was the primary outcome and was scored from 0 (no difficulty with balance) to 10 (great difficulty with balance). Of 107 subjects enrolled and randomized, 95 (88.8%) completed the study, satisfying the a priori sample size requirement of 94 patients. There were no differences in baseline characteristics between groups (P > .05 for each). RESULTS: Intervention patients reported less difficulty with balance than control patients (intention-to-treat analysis: 2.0±1.5 vs 3.2±1.8, P = .001; as-treated analysis: 2.1±1.7 vs 3.0±1.7, P = .009). Intervention and control patients did not differ with respect to pain experienced at their knees, hips, or back, or in a composite total pain score (P > .05 for each). CONCLUSION: This multicenter randomized controlled trial found that adding a limb length-evening orthotic to the plantar aspect of the contralateral shoe in a patient that is WBAT in a CAM boot improved patient-reported self-assessment of balance. The trial was powered to identify a difference in the primary outcome measure of balance and may have been insufficiently powered to identify differences in knee, hip, back, or total pain. LEVEL OF EVIDENCE: Level II, prospective comparative study.
RESUMO
BACKGROUND: As orthopaedic surgery moves toward bundled payments, there is growing interest in identifying patients at high risk of early postoperative adverse events. The purpose of this study was to develop and validate a risk-stratification system for the occurrence of early adverse events among patients treated with open reduction and internal fixation (ORIF) for a closed fracture of the ankle. METHODS: Patients undergoing ORIF for a closed ankle fracture during the period of 2006 to 2017, as documented by the American College of Surgeons National Surgical Quality Improvement Program, were identified. For the 60% of patients randomly selected as the development cohort, multivariate Cox proportional hazards modeling was used to identify factors that were independently associated with the occurrence of adverse events (including events such as reoperation, surgical site infection, and pulmonary embolism). On the basis of these results, a nomogram analysis was used to generate a point-based risk-stratification system. To evaluate the validity of the point-based system, the system was applied to the remaining 40% of patients constituting the validation cohort and tested for its ability to predict adverse events. RESULTS: Of the 7,582 patients in the development cohort, 455 developed an adverse event (estimated adverse event risk of 6%). On the basis of Cox proportional-hazards regression, patients were assigned points for each of the following significant risk factors: +1 point for age of 40 to 59 years, +3 points for age of 60 to 79 years, +5 points for age of ≥80 years, +1 point for female sex, +2 points for chronic obstructive pulmonary disease (COPD), +2 points for insulin-dependent diabetes, +3 points for anemia, and +4 points for end-stage renal disease. The validation cohort included 5,263 patients. Among this second cohort, the risk-stratification system predicted the risk of early adverse events (p < 0.001; Harrell C = 0.697). CONCLUSIONS: The occurrence of early adverse events following ORIF for closed ankle fractures was associated with greater age, female sex, COPD, insulin-dependent diabetes, anemia, and end-stage renal disease. We present and validate a simple point-based risk-stratification system to predict the risk of early adverse events. LEVEL OF EVIDENCE: Therapeutic Level IV. See Instructions for Authors for a complete description of levels of evidence.
Assuntos
Fraturas do Tornozelo/terapia , Fixação Interna de Fraturas/métodos , Redução Aberta/métodos , Adulto , Distribuição por Idade , Idoso , Idoso de 80 Anos ou mais , Procedimentos Cirúrgicos Ambulatórios/estatística & dados numéricos , Anemia/complicações , Fraturas do Tornozelo/complicações , Diabetes Mellitus Tipo 1/complicações , Feminino , Humanos , Falência Renal Crônica/complicações , Masculino , Pessoa de Meia-Idade , Complicações Pós-Operatórias/etiologia , Estudos Prospectivos , Doença Pulmonar Obstrutiva Crônica/complicações , Estudos Retrospectivos , Medição de Risco , Fatores de Risco , Fatores SexuaisRESUMO
BACKGROUND: The functional capacity evaluation (FCE) is used to determine physical ability after treatment of a workplace-related injury. This evaluation is a determinant in the administration of benefits and the decision to return to work (RTW). The purpose of this study was to characterize FCE results and ability to RTW after treatment for workplace-related orthopedic injuries to the foot or ankle. METHODS: A retrospective medical record review from the practices of 4 orthopedic foot and ankle surgeons was conducted. Inclusion criteria were a workplace-related injury to the foot or ankle, at least 2 years of follow-up, and an associated FCE. The FCE report and clinic notes were used to determine the patient's preinjury job requirement, postinjury FCE-determined ability, specific FCE- or physician-imposed work restrictions, and clearance to RTW. A total of 188 patients met inclusion criteria. RESULTS: In total, 74.4% of patients had FCE-determined work abilities at or above their preinjury job requirements, and 63.3% of patients were cleared to RTW. The mean time from injury to FCE was 1.9 ± 1.5 years, and the mean time to clearance for RTW was 2.0 ± 1.3 years. A less strenuous preinjury job requirement was positively associated with both the FCE-determined ability meeting the preinjury job requirement (P < .001) and clearance to RTW (P = .034). CONCLUSION: Two in 3 patients were cleared to RTW following workplace-related injuries to the foot or ankle culminating in an FCE. However, it took a mean of 2 years to achieve this clearance. Patients with more strenuous jobs were less likely to be able to RTW after injury. LEVEL OF EVIDENCE: Level III, retrospective comparative study.
Assuntos
Traumatismos do Tornozelo/fisiopatologia , Traumatismos do Pé/fisiopatologia , Ferimentos e Lesões/fisiopatologia , Avaliação da Deficiência , Humanos , Médicos , Estudos Retrospectivos , Avaliação da Capacidade de Trabalho , Ferimentos e Lesões/prevenção & controleRESUMO
BACKGROUND: The effect of concussions on professional athletes has been investigated in many sports. However, few studies have evaluated concussions in National Basketball Association (NBA) players. HYPOTHESIS: We hypothesized that concussion incidence has increased, yet the return-to-play (RTP) rate will remain high following the institution of the NBA concussion policy (NBACP). We also hypothesized that the incidence of repeat concussions will be similar to first occurrences and that player performance and game availability will not be significantly affected by sustaining a concussion. STUDY DESIGN: Descriptive epidemiology study. METHODS: Publicly available records were searched to identify all concussions from NBA seasons 1999-2000 to 2017-2018. Player demographics and information regarding career history were tabulated. Incidence of concussion and RTP timing were evaluated before and after institution of the NBACP (2011). Minutes per game and game score per minute were evaluated pre- versus postconcussion. Player availability and performance were also compared with an age-, body mass index-, position-, and experience-matched control group of players who did not sustain a concussion. RESULTS: A total of 189 concussions were reported in the NBA from 1999 to 2018, with a mean ± SD incidence of 9.7 ± 7.3 concussions per season. Following implementation of the NBACP, incidence significantly increased from 5.7 ± 2.8 to 16.7 ± 7.5 concussions per season (P = .007). All players returned to play following first-time concussion after missing 7.7 ± 8.6 days and 3.5 ± 4.1 games. RTP time was not significantly different after implementation of the NBACP (games missed, P = .24; days missed, P = .27), and there was no difference in concussion-free time interval (P = .29). Game score per minute and minutes per game were not significantly affected by sustaining a concussion (both P > .05). CONCLUSION: Concussion incidence in NBA players is approximately 17 instances per season since the 2011 institution of a league-wide concussion policy. The number of reported concussions significantly increased following the policy, in line with trends seen in other professional sports leagues. Players have retained a high rate of RTP after 3 to 4 missed games. Player performance and availability are not affected by sustaining a concussion following successful RTP.