Applying under-sampling techniques and cost-sensitive learning methods on risk assessment of breast cancer.

Breast cancer is one of the most common cause of cancer mortality. Early detection through mammography screening could significantly reduce mortality from breast cancer. However, most of screening methods may consume large amount of resources. We propose a computational model, which is solely based on personal health information, for breast cancer risk assessment. Our model can be served as a pre-screening program in the low-cost setting. In our study, the data set, consisting of 3976 records, is collected from Taipei City Hospital starting from 2008.1.1 to 2008.12.31. Based on the dataset, we first apply the sampling techniques and dimension reduction method to preprocess the testing data. Then, we construct various kinds of classifiers (including basic classifiers, ensemble methods, and cost-sensitive methods) to predict the risk. The cost-sensitive method with random forest classifier is able to achieve recall (or sensitivity) as 100 %. At the recall of 100 %, the precision (positive predictive value, PPV), and specificity of cost-sensitive method with random forest classifier was 2.9 % and 14.87 %, respectively. In our study, we build a breast cancer risk assessment model by using the data mining techniques. Our model has the potential to be served as an assisting tool in the breast cancer screening.

Routine depression screening and diagnosing strategy for cancer inpatients.

BACKGROUND: Clinical practice guidelines frequently recommend systematic screening for depression in cancer patients to improve recognition and prompt appropriate management. We aimed to screen major depressive disorder (MDD) in cancer inpatients using a structured tool and explore its applicability. METHODS: Cancer inpatients were routinely screened by nurses using the Taiwanese Depression Questionnaire (TDQ), and for those screened positive, this was followed by a non-mandated referral to a psychiatrist for clinical evaluation and diagnosis. Patients who completed this two-stage procedure comprised the analysis sample. RESULTS: Routine screening of 8800 patients in a period of 27 months yielded 1087 (26.9%) positive first-time screens. Of them, 298 (27.4%) completed the psychiatric consultation. Depressive disorders were diagnosed in 185 patients (62.1%), mainly adjustment disorder (23.8%) and MDD (21.5%). The estimated prevalence of MDD was 21.5%. Area under the curve was 0.72, a result produced by the receiver operating characteristic curve of the TDQ scores relative to the clinical psychiatric diagnoses of MDD. A TDQ cutoff score of ≧26 provided an optimal diagnostic accuracy for MDD. CONCLUSIONS: This two-stage depression screening and diagnosing strategy is practical for improving recognition of MDD and other depressive disorders in cancer patients and could be routinely applied, rather than selectively, in a comprehensive cancer care system.

Development and psychometric testing of the Suicide Caring Competence Scale (SCCS) for family caregivers in Taiwan.

Suicide caring competence is important for family caregivers to care their relatives with suicidal tendencies. The purpose of this study was to develop and test the psychometric properties of the Suicide Caring Competence Scale (SCCS) for family caregivers in Taiwan. A 20-item SCCS was tested on 165 family caregivers. Confirmatory factor analysis indicated that five subscales with 19 items best fit the data. The Cronbach's α and test-retest reliability of the SCCS was 0.90 and 0.81, respectively. The SCCS demonstrated acceptable construct validity and reliability. Nurses can use the SCCS to assess the suicide caring competence of family caregivers.

Randomized controlled trial comparing three methods of liver retraction in laparoscopic Roux-en-Y gastric bypass.

BACKGROUND: This study aimed to evaluate differences between three methods of liver retraction during laparoscopic Roux-en-Y Gastric bypass (LRYGB) and to compare novel liver retraction techniques with the traditional mechanical liver retractor in a randomized controlled trial. METHODS: In this study, 60 obese patients (26 males and 34 females) who underwent LRYGB between January and July 2010 were randomized to one of three groups (20 in each): group 1 (Nathanson liver retractor), group 2 (liver suspension tape), and group 3 (V-shaped liver suspension technique [V-LIST]). Data regarding demographics (age, sex, body mass index); liver function test (LFT) just before surgery; postoperative results immediately, then 18 h, 1 week, and 1 month after surgery; operative data, and visual analog scale (VAS) for pain on postoperative days (PODs) 1 and 2 were calculated and analyzed. RESULTS: The groups did not differ significantly in terms of preoperative LFT or operative data except that group 3 took significantly longer time for liver suspension than group 1 (p = 0.01) or group 2 (p = 0.03). The VAS score in group 2 was significantly lower on POD 1 than in group 1 (p = 0.04). Group 1 showed a significant rise in aspartate aminotransferase (AST) and alanine aminotransferase (ALT) at 18 h compared with group 2 (p < 0.01 and p = 0.02, respectively) and group 3 (p < 0.01 and p = 0.01), at 1 week compared with group 2 (p = 0.04 and 0.04), and in AST levels alone during the immediate postoperative compared with group 3 (p = 0.04). CONCLUSION: The Nathanson liver retractor causes more liver dysfunction than V-LIST or the liver suspension technique and causes more postoperative pain than the liver suspension technique. Both V-LIST and liver suspension tape have a short learning curve and implications for single-port surgery.

Psychiatric disorders of patients seeking obesity treatment.

BACKGROUND: Obese and overweight people have a higher risk of both chronic physical illness and mental illness. Obesity is reported to be positively associated with psychiatric disorders, especially in people who seek obesity treatment. At the same time, obesity treatment may be influenced by psychological factors or personality characteristics. This study aimed to understand the prevalence of mental disorders among ethnic Chinese who sought obesity treatment. METHODS: Subjects were retrospectively recruited from an obesity treatment center in Taiwan. The obesity treatments included bariatric surgery and non-surgery treatment. All subjects underwent a standardized clinical evaluation with two questionnaires and a psychiatric referral when needed. The psychiatric diagnosis was made thorough psychiatric clinic interviews using the SCID. A total of 841 patients were recruited. We compared the difference in psychiatric disorder prevalence between patients with surgical and non-surgical treatment. RESULTS: Of the 841 patients, 42% had at least one psychiatric disorder. Mood disorders, anxiety disorders and eating disorders were the most prevalent categories of psychiatric disorders. Females had more mood disorders and eating disorders than males. The surgical group had more binge-eating disorder, adjustment disorder, and sleep disorders than the non-surgical group. CONCLUSION: A high prevalence of psychiatric disorders was found among ethnic Chinese seeking obesity treatment. This is consistent with study results in the US and Europe.

Adherence to Psychiatric Follow-up Predicts 1-Year BMI Loss in Gastric Bypass Surgery Patients.

OBJECTIVE: The objective of this study was to investigate the effects of adherence to postoperative recommended psychiatric follow-up on weight loss in morbid obesity patients with psychiatric disorders 1 year after gastric bypass. METHODS: Three hundred eighteen morbidly obese patients were retrospectively reviewed. They were divided into four groups according to preoperative psychiatric evaluations and adherence to psychiatric follow-up 1 year after their bypass surgery. The first group included patients who did not meet the referral criteria (NMRC). The second group consisted of patients who did not meet the psychiatric diagnostic criteria (NMDC). The third group was patients who met criteria for a psychiatric disorder and were nonadherent (NA) to psychiatric follow-up. The fourth group consisted of patients who met criteria for a psychiatric disorder and were adherent (A) to psychiatric follow-up. RESULTS: The A group exhibited higher % change in BMI than the NA and NMRC groups at 1 year after bypass surgery. Regression analyses to examine the effects of the grouping variable on % change in BMI were performed by controlling the effects of age, gender, educational level, and preoperative BMI. The regression coefficient for the grouping variable was 0.175 (p = .003) at the 6-month and 0.133 (p = .027) at the 1-year % change in BMI. CONCLUSION: Our preliminary data suggest that adherence to postoperative psychiatric follow-up is associated with greater postoperative weight loss. However, evidence from studies with a longer follow-up is required to justify this therapeutic approach.

Laparoscopic adjustable gastric banded plication: evolution of procedure and 2-year results.

BACKGROUND: Laparoscopic adjustable gastric banded plication (LAGBP) is a new restrictive bariatric procedure combining adjustable banding and greater curvature plication of the stomach. This study aimed to report the evolution of this surgical technique and analyze the surgical results. METHODS: Eighty patients who underwent LAGBP were enrolled in this study. The band-first technique was used in 50 patients from May 2009 to June 2011 and was then changed to the plication-first technique from July 2011 to October 2011. Patients' demographics and pre- and postoperative data, including complications and weight loss, were collected and analyzed. RESULTS: Eighty patients (26 men and 54 women) with a mean age of 30.75 ± 8.68 years and a mean body mass index of 38.05 ± 4.73 kg/m2 were evaluated with a mean follow-up of 10.52 (1-24) months. The average operation duration and hospital stay were 92.85 ± 35.86 min and 1.73 ± 1.04 days, respectively. No intraoperative complications or surgical mortality was observed in this series. Four (8%) postoperative complications occurred with the band-first technique and one (3%) with the plication-first technique. Mean excess weight loss (percentage) at 6, 12, 18, and 24 months were 42.59 ± 13.67, 56.38 ± 19.89, 57.59 ± 19.88, and 65.84 ± 17.36%, respectively. The frequency of band adjustment was 2.44 ± 2.21 times in 2 years. CONCLUSIONS: In this present 2-year result, LAGBP using plication-first technique revealed fewer complications and good weight loss. Longer follow-up is still necessary to be accepted as a stand-alone bariatric procedure.

Effectiveness of intragastric balloon treatment for obese patients: one-year follow-up after balloon removal.

BACKGROUND: The Bioenterics Intragastric Balloon (BIB) is effective for weight loss. However, comparisons of its effectiveness between groups with different body mass index (BMI) are rare. This study compared the effectiveness of BIB treatment in patients with BMI <32 kg/m(2) and those with BMI ≥ 32 kg/m(2) at the time of BIB removal and at 1 year later. METHODS: Between April 2009 and June 2011, 28 obese patients who completed a full course of BIB treatment were enrolled. There are 16 patients with BMI <32 and 12 with BMI ≥ 32. Patients who lost more than 20 % of excess weight (% EWL) were categorized as responders. RESULTS: The BMI significantly fell from 32.4 ± 3.7 to 28.5 ± 3.7 kg/m(2) (P < 0.01) at the time of BIB removal. All biochemical measurements except for cholesterol level were significantly improved. The median value of %EWL of all patients at BIB removal was 40.1, and 20 patients (71.4 %) were responders. Adherence to dietitian counseling was significantly better in responders than in non-responders (85 vs. 25 %, respectively; P < 0.01). The percentage of responders at 1 year after BIB removal was significantly higher among patients with BMI <32 than those with ≥ 32 (62.5 vs. 16.7 %, respectively; P = 0.02). CONCLUSIONS: BIB placement can achieve significant weight loss and improvement of co-morbidities in obese patients. Better adherence to dietitian counseling is associated with better response. Patients with BMI <32 maintain better weight loss at 1 year after BIB removal.