文本挖掘技术在药物研究中的应用

介绍生物医学文献中文本挖掘的过程,重点分析论述文本挖掘在药物研究中的应用,主要包括在药物命名识别、药物靶标发现、药物疗效评价和中医用药规律中的应用,最后指出文本挖掘在生物医学知识发现中需要解决的问题,并展望文本挖掘在药物研究领域的发展前景.     

新农合一卡通直补系统与HIS接口的设计与实现

针对SemRep不利于对所提取关系进行统计分析的问题,开发SemRep处理结果统计挖掘系统。介绍该系统各模块的设计情况,包括信息抽取、统计、查询、推导等。指出其功能能够达到最初设计目的。     

基于政策工具的我国省域层面3岁以下婴幼儿照护服务政策文本量化研究

目的 了解我国省级政府婴幼儿照护服务中的政策工具使用情况,分析相关政策的侧重点及问题,以期为未来调整和优化3岁以下婴幼儿照护服务政策提供参考。方法 选取2016年1月—2021年6月各省市政府颁布的30份3岁以下婴幼儿照护服务政策为研究对象,采用Rothwell政策工具对政策条款进行分类和频数统计分析。结果 676个编码文本单元中,环境型政策工具使用最多,占比68.2%（461/676）,其次为供给型政策工具,占比23.7%（160/676）,需求型政策工具使用最少,占比8.1%（55/676）。各类政策工具中,策略性措施使用最多,税收优惠使用最少。东部地区需求型政策工具使用数量明显高于中部和西部地区。结论 我国省级政府“3岁以下婴幼儿照护服务”政策工具使用不均衡,环境型工具使用过多,需求型工具使用不足,同时政策工具内部结构失衡。建议应结合区域社会经济水平和未来发展趋势,提升需求型政策工具的使用,加强政策工具间的均衡和互补,优化政策工具内部结构,充分发挥各类工具在促进婴幼儿照护服务发展中的作用。     

Enhancement of care through self-monitoring and tailored feedback via text messaging and their use in the treatment of childhood overweight

Objective

This paper first illustrates the general potential of the short message service (SMS) for symptom and behavior monitoring and the provision of tailored feedback. Second, an SMS-based maintenance treatment (SMSMT) is introduced aimed at enhancing the treatment of childhood overweight.

Methods

After a 12-week cognitive behavioral group treatment (CBGT), 40 children were assigned to the SMSMT for a period of 36 weeks. Children were asked to send weekly self-monitoring data on eating behavior, exercise behavior, and emotions and received tailored feedback. The adherence to SMSMT and changes in Body Mass Index Standard Deviation Scores (BMI-SDS) during the first and second treatment phase were analysed.

Results

Children (mean age = 10.05, SD = 1.28) submitted 67% of the weekly SMS that they were expected to send in. During CBGT a significant reduction by 0.20 BMI-SDS was observed. The reduction by 0.07 BMI-SDS during the SMSMT did not reach statistical significance.

Conclusion

The results support the feasibility of SMSMT in the treatment of childhood overweight. The efficacy of the intervention needs to be demonstrated in an RCT.

Practice implications

SMSMT is a promising intervention that may extend the reach of treatment centers for childhood overweight at reasonable cost and effort.     

Text Mining and Natural Language Processing Approaches for Automatic Categorization of Lay Requests to Web-Based Expert Forums

Background

Both healthy and sick people increasingly use electronic media to obtain medical information and advice. For example, Internet users may send requests to Web-based expert forums, or so-called “ask the doctor” services.

Objective

To automatically classify lay requests to an Internet medical expert forum using a combination of different text-mining strategies.

Methods

We first manually classified a sample of 988 requests directed to a involuntary childlessness forum on the German website “Rund ums Baby” (“Everything about Babies”) into one or more of 38 categories belonging to two dimensions (“subject matter” and “expectations”). After creating start and synonym lists, we calculated the average Cramer’s V statistic for the association of each word with each category. We also used principle component analysis and singular value decomposition as further text-mining strategies. With these measures we trained regression models and determined, on the basis of best regression models, for any request the probability of belonging to each of the 38 different categories, with a cutoff of 50%. Recall and precision of a test sample were calculated as a measure of quality for the automatic classification.

Results

According to the manual classification of 988 documents, 102 (10%) documents fell into the category “in vitro fertilization (IVF),” 81 (8%) into the category “ovulation,” 79 (8%) into “cycle,” and 57 (6%) into “semen analysis.” These were the four most frequent categories in the subject matter dimension (consisting of 32 categories). The expectation dimension comprised six categories; we classified 533 documents (54%) as “general information” and 351 (36%) as a wish for “treatment recommendations.” The generation of indicator variables based on the chi-square analysis and Cramer’s V proved to be the best approach for automatic classification in about half of the categories. In combination with the two other approaches, 100% precision and 100% recall were realized in 18 (47%) out of the 38 categories in the test sample. For 35 (92%) categories, precision and recall were better than 80%. For some categories, the input variables (ie, “words”) also included variables from other categories, most often with a negative sign. For example, absence of words predictive for “menstruation” was a strong indicator for the category “pregnancy test.”

Conclusions

Our approach suggests a way of automatically classifying and analyzing unstructured information in Internet expert forums. The technique can perform a preliminary categorization of new requests and help Internet medical experts to better handle the mass of information and to give professional feedback.     

A User-Informed,Theory-Based Pregnancy Prevention Intervention for Adolescents in the Emergency Department: A Prospective Cohort Study

PurposeFemale adolescents seeking emergency department (ED) care are at high risk of unintended pregnancy, primarily because of contraceptive nonuse; yet, few ED patients follow up for reproductive care when referred. The objective of this cohort study was to determine the feasibility, acceptability, adoption, fidelity, and potential efficacy of a personalized and interactive ED-based pregnancy prevention mobile health intervention (Emergency Room Interventions to improve the Care of Adolescents [Dr. Erica]).MethodsWe conducted a prospective cohort study with sexually active female ED patients aged 14–19 years who were not using highly effective contraceptives. Dr. Erica consists of a 10-week, automated, two-way texting intervention based on an evidence-based sexual health curriculum, the Social Cognitive Theory, and motivational interviewing techniques. At 12 weeks, we conducted follow-up via online survey and phone call to measure feasibility, acceptability, adoption, fidelity, and preliminary efficacy data (contraception initiation).ResultsWe screened 209 female ED patients to enroll 42. The average age was 17.5 years (standard deviation ± 1.4); the majority were Hispanic (n = 37, 88%) and had a primary provider (n = 40, 95%). One participant opted out (1/42, 2%), and a total of 35 participants (83%) completed follow-up. Although interactivity diminished with time, 83% of participants (35/42) replied to one or more text. Ninety-four percent of participants (29/31) liked the messages, and 83% (25/30) would recommend the program. Hormonal contraceptives were initiated by 46% of participants (16/35).ConclusionsDr. Erica was feasible and acceptable among female adolescent ED patients and demonstrated high fidelity and adoption. The intervention also showed potential to increase highly effective contraceptive use among high-risk females.     

Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals

Objective

To determine whether the automatic classification of documents can be useful in systematic reviews on medical topics, and specifically if the performance of the automatic classification can be enhanced by using the particular protocol of questions employed by the human reviewers to create multiple classifiers.

Methods and materials

The test collection is the data used in large-scale systematic review on the topic of the dissemination strategy of health care services for elderly people. From a group of 47,274 abstracts marked by human reviewers to be included in or excluded from further screening, we randomly selected 20,000 as a training set, with the remaining 27,274 becoming a separate test set. As a machine learning algorithm we used complement naïve Bayes. We tested both a global classification method, where a single classifier is trained on instances of abstracts and their classification (i.e., included or excluded), and a novel per-question classification method that trains multiple classifiers for each abstract, exploiting the specific protocol (questions) of the systematic review. For the per-question method we tested four ways of combining the results of the classifiers trained for the individual questions. As evaluation measures, we calculated precision and recall for several settings of the two methods. It is most important not to exclude any relevant documents (i.e., to attain high recall for the class of interest) but also desirable to exclude most of the non-relevant documents (i.e., to attain high precision on the class of interest) in order to reduce human workload.

Results

For the global method, the highest recall was 67.8% and the highest precision was 37.9%. For the per-question method, the highest recall was 99.2%, and the highest precision was 63%. The human-machine workflow proposed in this paper achieved a recall value of 99.6%, and a precision value of 17.8%.

Conclusion

The per-question method that combines classifiers following the specific protocol of the review leads to better results than the global method in terms of recall. Because neither method is efficient enough to classify abstracts reliably by itself, the technology should be applied in a semi-automatic way, with a human expert still involved. When the workflow includes one human expert and the trained automatic classifier, recall improves to an acceptable level, showing that automatic classification techniques can reduce the human workload in the process of building a systematic review.     

A preliminary randomized double-blind clinical trial on the efficacy of celecoxib as an adjunct in the treatment of obsessive-compulsive disorder

Obsessive-compulsive disorder is a common neuropsychiatric condition. Although a variety of pharmaceutical agents is available for its treatment, psychiatrists have found that many patients cannot tolerate the side effects, do not respond to treatment adequately, and may finally discontinue their treatment. However, augmentation strategies have been shown to have some benefits in the treatment of OCD. These include reducing both the overall cost of treatment and the side effects. The purpose of this study was to assess the efficacy of celecoxib as an adjuvant agent in the treatment of OCD in an 8-week, double-blind, placebo controlled trial. To this end, 25 patients were assigned to a study group and were given fluoxetine 20 mg/day plus celecoxib 400 mg/day (200 mg BID). The control group included 25 patients who were given fluoxetine 20 mg/day plus placebo. Both protocols significantly lowered scores on the Yale-Brown Obsessive-Compulsive Scale over the trial period. The combination of fluoxetine and celecoxib decreased the symptoms of obsessions and compulsions significantly more than fluoxetine plus placebo. The results of this study suggest that celecoxib can be an effective adjuvant agent in the management of patients with OCD; therefore, anti-inflammatory therapies should be further investigated.     

Aberrant emotional processing in posterior cortical midline structures in bipolar II depression

Bipolar II depression is a serious and disabling illness associated with significant impairment and high rates of suicide attempts. However, mechanisms underlying emotional dysregulation in this condition are poorly characterized. The goal of this work was to investigate one component of emotional processing in this disorder, brain activation associated with exposure to emotional faces. Functional MRI was used to study 16 unmedicated male subjects with bipolar II depression and 19 healthy male controls. The activation paradigm exposed subjects to happy, fearful and neutral faces. The two key findings of this study were as follows. First, bipolar subjects demonstrated significantly decreased activation in response to happy facial expression in the left posterior cortical midline structures (CMS) and frontal cortex. Second, depression severity was positively correlated with activation of the posterior CMS and other regions. Our results suggest that mechanisms involving CMS dysfunction may play a role in the neurobiology of bipolar II depression as has been demonstrated for unipolar illness. Further investigations of CMS function in bipolar spectrum disorders are warranted.