[Changes of menstruation patterns and adverse effects during the treatment of LNG-IUS for symptomatic adenomyosis].

Objective: To investigate the changes of mestruation patterns and adverse effects during the treatment of levonorgestrel-releasing intrauterine system(LNG-IUS)for symptomatic adenomyosis in a prospective cohort study. Methods: From December, 2006 to December, 2014, patients of symptomatic adenomyosis diagnosed by transvaginal ultrasound in Peking Union Medical College Hospital were given LNG-IUS. Before and after placement of IUS, all patients' parameters were recorded, including carrying status of IUS, symptoms and scores of dysmenorrhea, menstruation scores, biochemical indicators, physical parameters, menstruation patterns and adverse effects. Risk factors for changes of menstruation patterns and adverse effects, and their impact on treatment effects were analyzed. Results: Totally 1 100 cases met inclusion criteria, with median age 36 years(range 20-44 years), median follow-up 35 months(range 1 -108 months). During follow-up changes of menstruation patterns increased significantly with amenorrhea and shortened-menstruation being the most common manifestations. On 3, 6, 12, 24, 36, 48 and 60 months after the placement of LNG-IUS, 0, 5.8%(43/744), 6.9%(47/682), 10.1%(60/595), 17.3%(87/502), 27.2%(104/383)and 29.6%(82/277)patients achieved amenorrhea respectively(P<0.01). Total and subclassification of adverse effects decreased significantly(P<0.01). Within 12 months and >12 months after placement, abdominal pain and body weight increasing ≥5 kg/year were the most common adverse effects. Changes of menstruation patterns, total and subclassifications of adverse effects were neither dependent on patient parameters, treatment modes and treatment effects, nor could predict future LNG-IUS carrying status(all P> 0.05). After taking out of LNG-IUS, most changes of menstruation and adverse effects disappeared. Conclusions: During the treatment of LNG-IUS for symptomatic adenomyosis, changes of menstruation patterns increase gradually with amenorrhea and shortened-menstruation being the most common manifestations, while adverse effects decrease significantly. Changes of menstruation patterns or adverse effects neither have any risk factor nor have impact on treatment effects.

[A prospective cohort study on the impact of placement timing of LNG-IUS for adenomyosis].

OBJECTIVE: To investigate the impact of placement in the procedures of gynecological laparoscopies or routine placement on the effects of levonorgestrel-releasing intrauterine system (LNG-IUS) for symptomatic adenomyosis in a prospective cohort study. METHODS: From December, 2006 to December, 2014, patients with adenomyosis diagnosed by transvaginal ultrasound in outpatient or inpatient clinics of Peking Union Medical College Hospital received the treatment of LNG-IUS.Before and after placement of LNG-IUS all the parameters were recorded including carrying status of IUS, symptoms and scores of dysmenorrhea, menstruation scores, biochemical indicators, physical parameters, menstruation patterns and adverse effects.Impact of placement timing (in the procedures of laparoscopies vesus routine placement) on the treatment effects, menstruation patterns and adverse effects of LNG-IUS were analyzed. RESULTS: 1 100 patients meet the inclusion criteria, with median age 36 years (20-44 years), median follow-up 35 months (1-108 months), of which 385 cases (35.0%) received LNG-IUS in the procedures of gynecological laparoscopies. Most common indications and pathology outcomes were endometriosis, major of which had deep infiltrating endometriosis. The accumulative carrying ratio of LNG-IUS were 73% and 63% on 60 months for operative patients and non-operative patients respectively (P<0.001), and accumulative take-out ratio were 7.8% and 10.3% (P=0.044). Placement timing of LNG-IUS was the only significant factor related with loss to follow-up (P<0.001) and take-out ratio (P<0.001). Operations and pathological outcome had no significant impact on patients' treatment effects, changes of menstruation patterns, adverse effects in total or in subclass. CONCLUSION: Placement of LNG-IUS in the procedures of gynecological laparoscopies for symptomatic adenomyosis increased carrying ratio and reduce take-out ratio at patients'request, but didn't influence treatment effects or adverse effects.

[A prospective study on the effects of levonorgestrel-releasing intrauterine system for adenomyosis with menorrhagia].

OBJECTIVE: To investigate treatment effects of levonorgestrel-releasing intrauterine system (LNG-IUS) for adenomyosis with menorrhea in a prospective study. METHODS: From December 2006 to December 2014, patients of symptomatic adenomyosis diagnosed by transvaginal ultrasound in outpatient or inpatient clinics of Peking Union Medical College Hospital were given the treatment of LNG-IUS. Before and after placement of LNG-IUS, all the patients' parameters were recorded prospectively, including scores of menstruation blood loss, carrying status of IUS, symptoms and scores of dysmenorrhea, biochemical indicators, physical parameters, menstruation patterns and adverse effects. Changes of pictorial chart scores of menstruation and distribution of anemia during follow-up were analyzed. RESULTS: Totally 1 100 women meets inclusion criteria, among which 618 cases (56.18%, 618/1 100) had severe menorrhea, with median follow-up period of 28 months (range 1- 60 months), and accumulative carrying rate of 66% at 60 months follow-up. After placement of LNG-IUS, compared with baselines, pictorial chart scores and ratio of menorrhea had decreased significantly (all P<0.01), the scroes of menstruation were 157±34, 94±35, 70±33, 67±18, 67±20, 65±19, 66±19, 65±21 at 0, 3, 6, 12, 24, 36, 48 and 60 months respectively. During 24 months after placement of LNG-IUS, pictorial chart scores and distribution of anemia had improved significantly compared with preceding period (all P<0.01). We found no dependent factors predicting improvement of pictorial chart scores of menorrhea, which was neither relevant with simultaneous changes of menstruation patterns nor adverse effects (all P>0.05). CONCLUSIONS: LNG-IUS is effective for adenomyosis of menorrhea. Improvement of menstruation blood loss is independent on patients characters, menstruation patterns or adverse effects.

[A prospective cohort study on effects of levonorgestrel-releasing intrauterine system for adenomyosis with severe dysmenorrhea].

OBJECTIVE: To investigate treatment effects of levonorgestrel-releasing intrauterine system (LNG-IUS) for adenomyosis with severe dysmenorrhea in a prospective cohort study. METHODS: From December 2006 to December 2014, patients of symptomatic adenomyosis diagnosed by transvaginal ultrasound in outpatient or inpatient clinics of Peking Union Medical College Hospital were given the treatment of LNG-IUS. Before and after placement of LNG-IUS, all the patients' parameters were recorded prospectively, including symptoms and scores of dysmenorrhea, menstruation scores, biochemical indicators, physical parameters, carrying status of LNG-IUS, menstruation patterns and adverse effects. Changes of scores and patterns of pain during follow-up were analyzed. RESULTS: Totally 1 100 women meets inclusion criteria, among which 640 cases (58.18%, 640/1 100) had severe dysmeorrhea, with median follow-up period of 35 months (range 1-60 months), and accumulative carrying rate of 65% at 60 months follow-up. After placement of LNG-IUS, scores of pain and ratio of severe dysmenorrhea had decreased significantly compared with baselines (all P<0.01), the scroes of visual analog scale (VAS) were 8.1±0.9, 5.5±2.4, 4.6±2.4, 3.3±2.2, 2.2±2.1, 2.2±1.8, 1.4±1.6 and 1.3±1.3 at 0, 3, 6, 12, 24, 36, 48 and 60 months respectively. During 36 months after placement of LNG-IUS, scores of pain had improved significantly compared with preceding period (all P<0.01). We found no universal dependent factors predicting improvement of pain, which was neither relevant with simultaneous changes of menstruation patterns nor adverse effects (all P>0.05). CONCLUSION: LNG-IUS is effective for adenomyosis of severe dysmenorrhea. Improvement of pain is independent on patients characters, menstruation patterns or adverse effects.

The cascade-correlation learning: a projection pursuit learning perspective.

Cascade-correlation (Cascor) is a popular supervised learning architecture that dynamically grows layers of hidden neurons of fixed nonlinear activations (e.g., sigmoids), so that the network topology (size, depth) can be efficiently determined. Similar to a cascade-correlation learning network (CCLN), a projection pursuit learning network (PPLN) also dynamically grows the hidden neurons. Unlike a CCLN where cascaded connections from the existing hidden units to the new candidate hidden unit are required to establish high-order nonlinearity in approximating the residual error, a PPLN approximates the high-order nonlinearity by using trainable parametric or semi-parametric nonlinear smooth activations based on minimum mean squared error criterion. An analysis is provided to show that the maximum correlation training criterion used in a CCLN tends to produce hidden units that saturate and thus makes it more suitable for classification tasks instead of regression tasks as evidenced in the simulation results. It is also observed that this critical weakness in CCLN can also potentially carry over to classification tasks, such as the two-spiral benchmark used in the original CCLN paper.