A 30 years, 4th Gravida with 3 abortions with history of 8 months amenorrhea was admitted to the hospital with chief complaints of leaking per vagina since 4 hours and was not associated with pain abdomen or bleeding per vaginum. Perceiving decreased fetal movements since 6 hours. She had 3 previous missed abortions followed by D and E. In the present pregnancy, gestational age was 32 weeks at the time of admission.Patient's general condition was stable, all other investigation were found to be normal her pulse was 100 beats/min, tachycardia present, BP -100/70mmHg. On obstetric examination, uterus was 30 weeks size, 1-2 contraction lasting for 15-20 seconds, Breech presentation, FHR was 124 per minute, regular, decreased liquor clinically. On vulvovaginal examination-Frank leaking per vagina present.Ultrasound showed single live intrauterine pregnancy of 29 weeks 3 days with breech presentation with oligohydramnios, Placenta was at fundal region, Biophysical profile was 6/8, FHR 124 bpm.After taking high risk consent in view of fetal prematurity, patient was posted for Emergency LSCS. And extracted a single live preterm female baby of weight of 1.45 kg by breech.During the cesarean section, on opening abdomen lower segment was found to be congested with torturous vessels. So we suspected missed diagnosis of placenta previa. After delivery of the baby, we found succenturiate lobe of the placenta occupying lower uterine segment with vessels running across the membrane.

No abstract

With a huge amount of information being stored as structured data, there is an increasing need for retrieving exact answers to questions from tables. Answering natural language questions on structured data usually involves semantic parsing of query to a machine understandable format which is then used to retrieve information from the database. Training semantic parsers for domain specific tasks is a tedious job and does not guarantee accurate results. In this paper, we used conversational analytics tool to create the user interface and to get the required entities and intents from the query thus avoiding the traditional semantic parsing approach. We then make use of Knowledge Graph for querying in structured data domain. Knowledge graphs can be easily leveraged for question answering systems, to use them as the database. We extract appropriate answers for different types of queries which have been illustrated in the Results section.

No abstract

No abstract