Predictive model for 5.year mortality after breast cancer surgery in Taiwan residents

Background:Few studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years.This study aimed to validate the use of the artificial neural network(ANN)model to predict the 5?year mortality of breast cancer patients after surgery and compare predictive accuracy between the ANN model,multiple logistic regression(MLR)model,and Cox regression model.Methods:This study compared the MLR,Cox,and ANN models based on clinical data of 3632 breast cancer patients who underwent surgery between 1996 and 2010.An estimation dataset was used to train the model,and a validation dataset was used to evaluate model performance.The sensitivity analysis was also used to assess the relative signifi?cance of input variables in the prediction model.Results:The ANN model significantly outperformed the MLR and Cox models in predicting 5?year mortality,with higher overall performance indices.The results indicated that the 5?year postoperative mortality of breast cancer patients was significantly associated with age,Charlson comorbidity index(CCI),chemotherapy,radiotherapy,hormone therapy,and breast cancer surgery volumes of hospital and surgeon(all P<0.05).Breast cancer surgery volume of surgeon was the most influential(sensitive)variable affecting 5?year mortality,followed by breast cancer surgery volume of hospital,age,and CCI.Conclusions:Compared with the conventional MLR and Cox models,the ANN model was more accurate in predict?ing 5?year mortality of breast cancer patients who underwent surgery.The mortality predictors identified in this study can also be used to educate candidates for breast cancer surgery with respect to the course of recovery and health outcomes.

中国台湾省居民乳腺癌术后5年死亡率预测模型的研究

背景与目的目前少有采用2年以上的数据分析乳腺癌手术效果的研究。本文旨在研究人工神经网络(artificial neural network, ANN)模型在预测乳腺癌患者术后5年死亡率中的应用,比较ANN模型、多元逻辑回归(multiple logistic regression, MLR)模型和Cox回归模型的预测准确度。方法本研究根据1996–2010年接受手术治疗的3632例乳腺癌患者的临床资料,对MLR、Cox和ANN模型进行比较。应用估算数据集测试模型,应用验证数据集评估模型性能,应用灵敏度分析法对预测模型中输入变量的相对显著性进行评价。结果在预测5年死亡率方面ANN模型明显优于MLR和Cox模型,并且综合性能指标更高。研究结果显示,乳腺癌患者术后5年死亡率与年龄、Charlson并发症指数(Charlson comorbidity index, CCI)、化疗、放疗、激素治疗、医院和外科医生的乳腺癌手术量均显著相关(均为P <0.05)。外科医生的乳腺癌手术量是对5年死亡率影响最大(敏感)的变量,其次是医院的乳腺癌手术量、患者年龄和CCI。结论与传统的MLR和Cox模型相比,ANN模型在预测乳腺癌患者术后5年死亡率方面更为准确。本研究中确定的死亡率预测因子也可用于对乳腺癌手术患者进行康复和健康方面的教育。

Incidence trends and predictors for cost and average lengths of stay in colorectal cancer surgery

AIM:To evaluate the changing trends and outcomes of colorectal cancer(CRC)surgery performed at a large single institution in Taiwan.METHODS:This study retrospectively analyzed 778patients who received colorectal cancer surgery at E-Da Hospital in Taiwan from 2004 to 2009.These patients were from health examination,inpatient or emergency settings.The following attributes were analyzed in patients who had undergone CRC surgical procedures:gender,age,source,surgical type,tumor number,tumor size,number of lymph node metastasis,pathologic differentiation,chemotherapy,distant metastases,tumor site,tumor stage,average hospitalization cost and average lengths of stay(ALOS).The odds ratio and95%confidence intervals were calculated to assess the relative rate of change.Regression models were employed to predict average hospitalization cost and ALOS.RESULTS:The study sample included 458(58.87%)males and 320(41.13%)females with a mean age of64.53 years(standard deviation,12.33 years;range,28-86 years).The principal patient source came from inpatient and emergency room(96.02%).The principal tumor sites were noted at the sigmoid colon(35.73%)and rectum(30.46%).Most patients exhibited a tumor stage of 2(37.28%)or 3(34.19%).The number of new CRC surgeries performed per 100000 persons was12.21 in 2004 and gradually increased to 17.89 in 2009,representing a change of 46.52%.During the same period,the average hospitalization cost and ALOS decreased from$5303 to$4062 and from 19.7 to 14.4 d,respectively.The following factors were associated with considerably decreased hospital resource utilization:age,source,surgical type,tumor size,tumor site,and tumor stage.CONCLUSION:These results can be generalized to patient populations elsewhere in Taiwan and to other countries with similar patient profiles.

Medium-term surgical outcomes and health-related quality of life after laparoscopic vs open colorectal cancer resection: SF-36 health survey questionnaire

BACKGROUND Previous studies that compared the postoperative health-related quality of life(HRQoL)outcomes after receiving laparoscopic resection(LR)or open resection(OR)in patients with colorectal cancer(CRC)have different conclusions.AIM To explore the medium-term effect of postoperative HRQoL in such patients.METHODS This study randomized 567 patients undergoing non-metastatic CRC surgery managed by one surgeon to the LR or OR groups.HRQoL was assessed during the preoperative period and 3,6,and 12 mo postoperative using a modified version of the 36-Item Short Form(SF-36)Health Survey questionnaire,emphasizing eight specific items.RESULTS This cohort randomly assigned 541 patients to receive LR(n=296)or OR(n=245)surgical procedures.More episodes of postoperative urinary tract infection(P<0.001),wound infection(P<0.001),and pneumonia(P=0.048)were encountered in the OR group.The results demonstrated that the LR group subjectively gained mildly better general health(P=0.045),moderately better physical activity(P=0.006),and significantly better social function recovery(P=0.0001)3 mo postoperatively.Only the aspect of social function recovery was claimed at 6 mo,with a significant advantage in the LR group(P=0.001).No clinical difference was found in HRQoL during the 12 mo.CONCLUSION Our results demonstrated that LR resulted in better outcomes,including intra-operative blood loss,surgery-related complications,course of recovery,and especially some health domains of HRQoL at least within 6 mo postoperatively.Patients should undergo LR if there is no contraindication.

Potential and role of artificial intelligence in current medical healthcare

Artificial intelligence(AI)is defined as the digital computer or computer-controlled robot's ability to mimic intelligent conduct and crucial thinking commonly associated with intelligent beings.The application of AI technology and machine learning in medicine have allowed medical practitioners to provide patients with better quality of services;and current advancements have led to a dramatic change in the healthcare system.However,many efficient applications are still in their initial stages,which need further evaluations to improve and develop these applications.Clinicians must recognize and acclimate themselves with the developments in AI technology to improve their delivery of healthcare services;but for this to be possible,a significant revision of medical education is needed to provide future leaders with the required competencies.This article reviews the potential and limitations of AI in healthcare,as well as the current medical application trends including healthcare administration,clinical decision assistance,patient health monitoring,healthcare resource allocation,medical research,and public health policy development.Also,future possibilities for further clinical and scientific practice were also summarized.