RESUMEN
BACKGROUND/PURPOSE: Pressure ulcers are a common problem in hospital care and long-term care. Pressure ulcers are caused by prolonged compression of soft tissues, which can cause local tissue damage and even lead to serious infections. This study uses a deep learning algorithm to construct a system that diagnoses pressure ulcers and assists in making treatment decisions, thus providing additional reference for first-line caregivers. METHODS: We performed a retrospective research of medical records to find photos of patients with pressure ulcers at National Taiwan University Hospital from 2016 to 2020. We used photos from 2016 to 2019 for training and after removing the photos which were vague, underexposed, or overexposed, 327 photos were obtained. The photos were then labeled as "erythema" or "non-erythema" for the first classification task and "extensive necrosis", "moderate necrosis" or "limited necrosis" for the second, by consensus of three recruited physicians. An Inception-ResNet-v2 model, a kind of Convolutional Neural Network (CNN), was applied for training these two classification tasks to construct an assessment system. Finally, we tested the model with the photos of pressure ulcers taken from 2019 to 2020 to verify its accuracy. RESULTS: For the task of classification of erythema and non-erythema wounds, our CNN model achieved an accuracy of about 98.5%. For the task of classification of necrotic tissue, our model achieved accuracy of about 97%. CONCLUSION: Our CNN model, which was based on Inception-ResNet-v2, achieved high accuracy when classifying different types of pressure ulcers, making it applicable in clinical circumstances.
Asunto(s)
Úlcera por Presión , Toma de Decisiones , Humanos , Necrosis , Redes Neurales de la Computación , Úlcera por Presión/diagnóstico , Estudios RetrospectivosRESUMEN
BACKGROUND: Necrotizing fasciitis (NF) is a life-threatening soft tissue infection with low incidence that requires prompt surgery. In the initial stage, it is difficult to distinguish NF and cellulitis, and limited population-based reports are available. METHODS: We queried inpatient data sets of National Health Institute Research Database in Taiwan from 2002 to 2011 for all patients with diagnoses of NF. Of them, only patients who underwent surgeries and had been admitted to intensive care units were included as the study group. Age and gender-matched patients with admission diagnoses of cellulitis were enrolled in a ratio of 1:4 as the control group. We calculated annual incidence, mortality rate, risk factors and predictors of mortality of NF. RESULTS: The study group consisted of 7391 NF patients. Among them, 4715 patients (64%) were man and 2676 (36%) were women. The overall annual incidence of NF was 3.26 hospitalizations per 100,000 person-years, which rose with age with male predominance. The in-hospital mortality rate, which also rose with age, was 32.2%. Diabetes mellitus (adjusted odds ratio, 2.93; 95% confidence interval, 2.77-3.11; P value < 0.0001), alcoholism (2.64; 2.27-3.08; P < .0001), and chronic kidney disease (1.98; 1.84-2.14; P < .001) were identified as risk factors. Chronic kidney disease (1.86; 1.64-2.10; P < .001) and liver cirrhosis (1.68; 1.50-1.88; P < .001) were identified as predictors of in-hospital mortality. CONCLUSION: Age and the presence of chronic diseases are major risk factors as well as prognostic factors of NF in Taiwan. Diabetes mellitus increases the risk of NF, but does not adversely affect the outcome.
Asunto(s)
Fascitis Necrotizante/diagnóstico , Fascitis Necrotizante/mortalidad , Mortalidad Hospitalaria/tendencias , Hospitalización/estadística & datos numéricos , Adolescente , Adulto , Distribución por Edad , Anciano , Anciano de 80 o más Años , Alcoholismo/epidemiología , Estudios de Casos y Controles , Celulitis (Flemón)/diagnóstico , Celulitis (Flemón)/mortalidad , Niño , Preescolar , Comorbilidad , Bases de Datos Factuales , Diabetes Mellitus/epidemiología , Diagnóstico Diferencial , Femenino , Humanos , Incidencia , Lactante , Recién Nacido , Modelos Logísticos , Masculino , Persona de Mediana Edad , Insuficiencia Renal Crónica , Factores de Riesgo , Distribución por Sexo , Taiwán/epidemiología , Adulto JovenRESUMEN
BACKGROUND: Intraoperative navigation is a tool that provides surgeons with real-time guidance based on patients' preoperative imaging studies. The application of intraoperative navigation to neurosurgery and otolaryngology has been well documented; however, only isolated reports have analyzed its potential in the field of craniomaxillofacial surgery. METHODS: From November 2010 to July 2014, 15 patients were operated on for complex craniomaxillofacial surgery with assistance by 3 different navigation systems, which used either infrared or electromagnetic technologies. We imported fine-cut (0.625-mm) computed tomographic scan images of the patients to the navigation systems whose software processed them into multisurface 3-dimentional models used as guiding material for the surgical navigation. We also developed a simple "2-plane reference system" to ensure that the final results were symmetric to the normal half of the face. Appearance outcome was evaluated by questionnaire. RESULTS: Of these 15 cases, 3 cases were performed with infrared-based navigation, and the remaining 12 cases were accomplished by electromagnetic technology. Most of these cases resulted in satisfactory outcomes after tumor resection, posttraumatic reconstruction, and postablative reconstruction. CONCLUSION: Navigation systems offer highly valuable intraoperative assistance in complex craniomaxillofacial surgery. Not only can these systems pinpoint deep-seated lesions as neurosurgeons or otolaryngologists do, but they can also use a simple 2-plane reference system for accurate bone alignment. Moreover, advancements in multisurface 3-D models provide us more reliable intuitive image guidance. The application of electromagnetic technology, with its smaller reference obviation of the line-of-sight problem, makes the manipulation of craniomaxillofacial surgery more comfortable.
Asunto(s)
Imagenología Tridimensional/métodos , Procedimientos Ortopédicos/métodos , Cráneo/cirugía , Cirugía Asistida por Computador/métodos , Tomografía Computarizada Espiral , Adolescente , Adulto , Anciano , Niño , Preescolar , Femenino , Estudios de Seguimiento , Humanos , Masculino , Persona de Mediana Edad , Evaluación de Resultado en la Atención de Salud , Cráneo/diagnóstico por imagen , Adulto JovenRESUMEN
BACKGROUND: For thymoma, the feasibility of resection via video-assisted thoracoscopic surgery (VATS) remains controversial. The objective of our study was to compare the outcomes of VATS and transsternal thymectomy in order to evaluate the efficacy of the VATS method for treatment of early stage thymoma. METHODS: This study is a retrospective study of 120 patients who underwent thymectomy of early stage thymoma (Masaoka stage I and II) in a single medical center from 1991 to 2010. Of these patients, 76 patients underwent VATS thymectomy (VATS group) and 44 patients underwent the conventional transsternal approach (sternotomy group). We applied the Kaplan-Meier method to estimate overall survival (OS), recurrence-free survival (RFS), and time to tumor recurrence (TTR) of these two groups. RESULTS: The mean follow-up time was 61.9 months in the VATS group and 69.7 months in the sternotomy group. There was no surgery-related mortality or major complication. The VATS group had smaller specimen size (p < 0.05) and tumor size (p < 0.01), shorter length of stay (LOS) in the hospital (p < 0.01), and shorter duration of chest tube drainage (p < 0.05) than the sternotomy group. There were no significant differences between the two groups for OS, RFS, and TTR. CONCLUSIONS: In early stage thymoma, VATS thymectomy associated with shorter hospital LOS and shorter duration of pleural drainage compared with the conventional transsternal approach. Otherwise, the two approaches had similar oncologic outcomes during the mean 60-month follow-up period.
Asunto(s)
Recurrencia Local de Neoplasia/cirugía , Esternotomía , Cirugía Torácica Asistida por Video , Timectomía , Timoma/cirugía , Neoplasias del Timo/cirugía , Adulto , Anciano , Drenaje , Femenino , Estudios de Seguimiento , Humanos , Masculino , Persona de Mediana Edad , Recurrencia Local de Neoplasia/mortalidad , Recurrencia Local de Neoplasia/patología , Estadificación de Neoplasias , Complicaciones Posoperatorias , Pronóstico , Estudios Retrospectivos , Tasa de Supervivencia , Toracoscopía , Timoma/mortalidad , Timoma/patología , Neoplasias del Timo/mortalidad , Neoplasias del Timo/patología , Adulto JovenRESUMEN
Pressure injuries are a common problem resulting in poor prognosis, long-term hospitalization, and increased medical costs in an aging society. This study developed a method to do automatic segmentation and area measurement of pressure injuries using deep learning models and a light detection and ranging (LiDAR) camera. We selected the finest photos of patients with pressure injuries, 528 in total, at National Taiwan University Hospital from 2016 to 2020. The margins of the pressure injuries were labeled by three board-certified plastic surgeons. The labeled photos were trained by Mask R-CNN and U-Net for segmentation. After the segmentation model was constructed, we made an automatic wound area measurement via a LiDAR camera. We conducted a prospective clinical study to test the accuracy of this system. For automatic wound segmentation, the performance of the U-Net (Dice coefficient (DC): 0.8448) was better than Mask R-CNN (DC: 0.5006) in the external validation. In the prospective clinical study, we incorporated the U-Net in our automatic wound area measurement system and got 26.2% mean relative error compared with the traditional manual method. Our segmentation model, U-Net, and area measurement system achieved acceptable accuracy, making them applicable in clinical circumstances.
Asunto(s)
Aprendizaje Profundo , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Estudios Prospectivos , Taiwán , Úlcera por PresiónRESUMEN
Necrotizing fasciitis is a relatively rare and serious fatal soft-tissue infection that is characterized by a rapidly spreading bacterial infection located in the subcutaneous tissues. We report a 59-year-old man who was diagnosed with acute necrotizing fasciitis, following a primary total knee replacement. He received primary total knee replacement that was uneventful and smooth intraoperatively. An immediate high fever was reported in the next few days, with several complications, confirming a diagnosis of necrotizing fasciitis. The most effective treatment for this disease is a rapid primary diagnosis and surgical debridement. Gold standard treatment includes intravenous therapy, such as antibiotics, surgical debridement, and intensive care. As a result of possible GI complications that triggered necrotizing fasciitis, the patient underwent flap reconstruction. This report's aim is to review the comprehensive treatment, management, and experience of necrotizing fasciitis, highlighting the roles with a multidisciplinary care team for improving the condition of this patient.
RESUMEN
A pressure ulcer is an injury of the skin and underlying tissues adjacent to a bony eminence. Patients who suffer from this disease may have difficulty accessing medical care. Recently, the COVID-19 pandemic has exacerbated this situation. Automatic diagnosis based on machine learning (ML) brings promising solutions. Traditional ML requires complicated preprocessing steps for feature extraction. Its clinical applications are thus limited to particular datasets. Deep learning (DL), which extracts features from convolution layers, can embrace larger datasets that might be deliberately excluded in traditional algorithms. However, DL requires large sets of domain specific labeled data for training. Labeling various tissues of pressure ulcers is a challenge even for experienced plastic surgeons. We propose a superpixel-assisted, region-based method of labeling images for tissue classification. The boundary-based method is applied to create a dataset for wound and re-epithelialization (re-ep) segmentation. Five popular DL models (U-Net, DeeplabV3, PsPNet, FPN, and Mask R-CNN) with encoder (ResNet-101) were trained on the two datasets. A total of 2836 images of pressure ulcers were labeled for tissue classification, while 2893 images were labeled for wound and re-ep segmentation. All five models had satisfactory results. DeeplabV3 had the best performance on both tasks with a precision of 0.9915, recall of 0.9915 and accuracy of 0.9957 on the tissue classification; and a precision of 0.9888, recall of 0.9887 and accuracy of 0.9925 on the wound and re-ep segmentation task. Combining segmentation results with clinical data, our algorithm can detect the signs of wound healing, monitor the progress of healing, estimate the wound size, and suggest the need for surgical debridement.
Asunto(s)
Algoritmos , COVID-19/epidemiología , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Redes Neurales de la Computación , Úlcera por Presión/diagnóstico , COVID-19/virología , Humanos , Úlcera por Presión/diagnóstico por imagen , SARS-CoV-2/aislamiento & purificación , Taiwán/epidemiologíaRESUMEN
Background: Diabetic foot and leg ulcers are a major cause of disability among patients with diabetes mellitus. A topical gel called ENERGI-F703, applied twice daily and with adenine as its active pharmaceutical ingredient, accelerated wound healing in diabetic mice. The current study evaluated the safety and efficacy of ENERGI-F703 for patients with diabetic foot and leg ulcers. Methods: This randomized, double-blind, multicenter, phase II trial recruited patients from eight medical centers in Taiwan. Patients with intractable diabetic foot and leg ulcers (Wagner Grade 1-3 without active osteomyelitis) were randomly assigned (2:1) to receive topical ENERGI-F703 gel or vehicle gel twice daily for 12 weeks or until complete ulcer closure. The investigator, enrolled patients and site personnel were masked to treatment allocation. Intention to treat (ITT) population and safety population were patient to primary analyses and safety analyses, respectively. Primary outcome was complete ulcer closure rate at the end of treatment. This trial is registered with ClinicalTrials.gov, number NCT02672436. Findings: Starting from March 15th, 2017 to December 26th, 2019, 141 patients were enrolled as safety population and randomized into ENERGI-F703 gel (n = 95) group or vehicle gel (n = 46) group. In ITT population, ENERGI-F703 (n = 90) and vehicle group showed ulcer closure rates of 36.7% (95% CI = 26.75% - 47.49%) and 26.2% (95% CI = 13.86% - 42.04%) with difference of 9.74 % (95 % CI = -6.74% - 26.23%) and 25% quartiles of the time to complete ulcer closure of 69 days and 84 days, respectively. There were 25 (26.3%) patients in ENERGI-F703 group and 11 (23.9%) patients in vehicle group experiencing serious adverse events and five deaths occurred during the study period, none of them related to the treatment. Interpretation: Our study suggests that ENERGI-F703 gel is a safe and well-tolerated treatment for chronic diabetic foot and leg ulcers. Further studies are needed to corroborate our findings in light of limitations. Funding: Energenesis Biomedical Co., Ltd.
RESUMEN
OBJECTIVE: To investigate the outcomes of a local healthcare system in managing a burn mass casualty incident (BMCI). METHODS: Thirty-three victims admitted to the National Taiwan University Hospital within 96h of the explosion were included in the study. Data were recorded on: patient demographics, Baux score, laboratory data, management response, treatment strategies, and outcomes. Case notes from June 27, 2015 to November 2015 were reviewed with a focus on fluid resuscitation, ventilation support, nutrition, infection control, sepsis treatment, and wound closure plan. RESULTS: Female predominance (mean age: 21.7 years) and lower extremity circumferential flame burns were the characteristics of the burn injury. The mean Baux score was 70±18. The mean burn area was 42% of the total body surface area (TBSA). A total of 79% patients arrived at the hospital within 24h of sustaining injuries. Intensive care unit (ICU) admission criteria were modified to accommodate patients with 40% TBSA of burns, facilities were expanded from 4 ICU beds to 18 beds, and new staff was recruited. A total of 36% patients (n=12/33, 62±13 TBSA of burns) required fluid resuscitation. The mean volume of Lactate Ringer administered in the first 24h of burns was 3.34±2.18ml/kg/%TBSA, while the mean volume of fresh frozen plasma administered was 0.60±0.63ml/kg/h. Forty-two percent patients were intubated on the day of admission, and 71% of the intubated patients had inhalation injuries that were confirmed by diagnostic bronchoscopy. The mean intubation period was 17±9 days. The incidence of pulmonary edema was 58% (n=7/12), possibly due to sub-optimal monitoring. Of these, 57% (n=4/7) patients progressed to adult respiratory distress syndrome, but were successfully treated with early strict fluid restriction, systemic antibiotics, ventilation support, and bronchial lavage. A total of 94% patients received grafting. The mean grafted area was 4432.3±3891cm2. Tube feeding was provided to patients with burns >40% TBSA. All patients tolerated gastric tube feeding without conversion to duodenal switch. On admission, all patients received prophylactic antibiotics. Septic shock was noted in 12 patients, but no mortality occurred. The mean hospital stay was 1.5 days per percent burn. CONCLUSIONS: This article highlights the value of precise triage, traffic control, and effective resource allocation in treating a BMCI. Effective supporting systems for facility expansion, staff recruitment, medical supplies and clear-cut treatment strategies for severely burned patients are contributory factors leading to zero mortalities in our series, in addition to young age and minimal inhalation injuries. The need for reevaluation of the safety of cornstarch powder in festival activities is clear.