Large Scale Subject Category Classification of Scholarly Papers With Deep Attentive Neural Networks.

Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category classification is a prerequisite for bibliometric studies, organizing scientific publications for domain knowledge extraction, and facilitating faceted searches for digital library search engines. Unfortunately, many academic papers do not have such information as part of their metadata. Most existing methods for solving this task focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few or no citations cannot be classified using such methods. Here, we propose a deep attentive neural network (DANN) that classifies scholarly papers using only their abstracts. The network is trained using nine million abstracts from Web of Science (WoS). We also use the WoS schema that covers 104 subject categories. The proposed network consists of two bi-directional recurrent neural networks followed by an attention layer. We compare our model against baselines by varying the architecture and text representation. Our best model achieves micro- F 1 measure of 0.76 with F 1 of individual subject categories ranging from 0.50 to 0.95. The results showed the importance of retraining word embedding models to maximize the vocabulary overlap and the effectiveness of the attention mechanism. The combination of word vectors with TFIDF outperforms character and sentence level embedding models. We discuss imbalanced samples and overlapping categories and suggest possible strategies for mitigation. We also determine the subject category distribution in CiteSeerX by classifying a random sample of one million academic papers.

Kerure Clamp: A New Age Tool to Improve Extraction Technique in Follicular Unit Extraction.

BACKGROUND: Follicular unit extraction (FUE) has caused evolution in the management of pattern baldness. FUE methods is less traumatic with faster healing and minimal scarring. FUE is still evolving and many innovations are possible in the future. AIMS AND OBJECTIVES: To address the usefulness of Kerure clamp, an innovative tool for FUE method of hair transplantation. MATERIALS AND METHODS: The clamp was used on 20 consecutive patients undergoing FUE for male-pattern baldness. Part of the donor area was divided into test side where extraction was done with clamp in situ and the control where clamp was not used. Follicular transection rate (FTR) was calculated as a percentage for each side and subjected to statistical analysis. RESULT: We found an improvement in the FTR scores on the test side, and this difference was statistically significant (t = 9.63, P < 0.0001). CONCLUSION: A low-cost instrument has been devised by the authors which was shown to improve the the scoring of grafts and also aid in surgeon's efficacy and efficiency.

The story of a deformed leprous foot.

Eccrine syringofibroadenoma (ESFA) is a rare adnexal tumour of eccrine ductal proliferation. A 50 year old treated case of leprosy presented with a chronic non healing ulcer of 5 years duration on the deformity laden right foot. Multiple verrucous papules and plaques were seen surrounding the ulcer which showed histopathological findings consistent with ESFA. Although ESFA constitutes a rare association with leprosy, considering the load of treated cases in our country and elsewhere, it may represent an under-reported entity which requires more attention in the post elimination era.

Role of tetracycline in recalcitrant erythema nodosum.

Erythema nodosum is a type of septal panniculitis. We report a case of 40 year old male of chronic and recalcitrant erythema nodosum who responded to tetracycline. The possible mechanism of action of tetracycline is analyzed. Tetracycline should be considered as a logical option in recalcitrant erythema nodosum.