Relationship between anaemia, coagulation parameters during pregnancy and postpartum haemorrhage at childbirth: a prospective cohort study.

OBJECTIVES: To investigate the association between coagulation parameters and severity of anaemia (moderate anaemia: haemoglobin (Hb) 7-9.9 g/dL and severe anaemia: Hb <7 g/dL) during pregnancy and relate these to postpartum haemorrhage (PPH) at childbirth. DESIGN: A prospective cohort study of pregnant women recruited in the third trimester and followed-up after childbirth. SETTING: Ten hospitals across four states in India. PARTICIPANTS: 1342 pregnant women. INTERVENTION: Not applicable. METHODS: Hb and coagulation parameters: fibrinogen, D-dimer, D-dimer/fibrinogen ratio, platelets and international normalised ratio (INR) were measured at baseline. Participants were followed-up to measure blood loss within 2 hours after childbirth and PPH was defined based on blood loss and clinical assessment. Associations between coagulation parameters, Hb, anaemia and PPH were examined using multivariable logistic regression models. OUTCOMES MEASURES: Adjusted OR with 95% CI. RESULTS: In women with severe anaemia during the third trimester, the D-dimer was 27% higher, mean fibrinogen 117 mg/dL lower, D-dimer/fibrinogen ratio 69% higher and INR 12% higher compared with women with no/mild anaemia. Mean platelets in severe anaemia was 37.8×109/L lower compared with women with moderate anaemia. Similar relationships with smaller effect sizes were identified for women with moderate anaemia compared with women with no/mild anaemia. Low Hb and high INR at third trimester of pregnancy independently increased the odds of PPH at childbirth, but the other coagulation parameters were not found to be significantly associated with PPH. CONCLUSION: Altered blood coagulation profile in pregnant women with severe anaemia could be a risk factor for PPH and requires further evaluation.

A comprehensive study on the multi-class cervical cancer diagnostic prediction on pap smear images using a fusion-based decision from ensemble deep convolutional neural network.

The diagnosis of cervical dysplasia, carcinoma in situ and confirmed carcinoma cases is more easily perceived by commercially available and current research-based decision support systems when the scenario of pathologists to patient ratio is small. The treatment modalities for such diagnosis rely exclusively on precise identification of dysplasia stages as followed by The Bethesda System. The classification based on The Bethesda System is a multiclass problem, which is highly relevant and vital. Reliance on image interpretation, when done manually, introduces inter-observer variability and makes the microscope observation tedious and time-consuming. Taking this into account, a computer-assisted screening system built on deep learning can significantly assist pathologists to screen with correct predictions at a faster rate. The current study explores six different deep convolutional neural networks- Alexnet, Vggnet (vgg-16 and vgg-19), Resnet (resnet-50 and resnet-101) and Googlenet architectures for multi-class (four-class) diagnosis of cervical pre-cancerous as well as cancer lesions and incorporates their relative assessment. The study highlights the addition of an ensemble classifier with three of the best deep learning models for yielding a high accuracy multi-class classification. All six deep models including ensemble classifier were trained and validated on a hospital-based pap smear dataset collected through both conventional and liquid-based cytology methods along with the benchmark Herlev dataset.

Maternal and perinatal Health Research Collaboration, India (MaatHRI): methodology for establishing a hospital-based research platform in a low and middle income country setting.

Background: Maternal and perinatal Health Research collaboration, India (MaatHRI) is a research platform that aims to improve evidence-based pregnancy care and outcomes for mothers and babies in India, a country with the second highest burden of maternal and perinatal deaths. The objective of this paper is to describe the methods used to establish and standardise the platform and the results of the process. Methods: MaatHRI is a hospital-based collaborative research platform. It is adapted from the UK Obstetric Surveillance System (UKOSS) and built on a pilot model (IndOSS-Assam), which has been extensively standardised using the following methods: (i) establishing a network of hospitals; (ii) setting up a secure system for data collection, storage and transfer; (iii) developing a standardised laboratory infrastructure; and (iv) developing and implementing regulatory systems. Results: MaatHRI was established in September 2018. Fourteen hospitals participate across four states in India - Assam, Meghalaya, Uttar Pradesh and Maharashtra. The research team includes 20 nurses, a project manager, 16 obstetricians, two pathologists, a public health specialist, a general physician and a paediatrician. MaatHRI has advanced standardisation of data and laboratory parameters, real-time monitoring of data and participant safety, and secure transfer of data. Four observational epidemiological studies are presently being undertaken through the platform. MaatHRI has enabled bi-directional capacity building. It is overseen by a steering committee and a data safety and monitoring board, a process that is not normally used, but was found to be highly effective in ensuring data safety and equitable partnerships in the context of low and middle income countries (LMICs). Conclusion: MaatHRI is the first prototype of UKOSS and other similar platforms in a LMIC setting. The model is built on existing methods but applies new standardisation processes to develop a collaborative research platform that can be replicated in other LMICs.