Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry.

INTRODUCTION: The diagnosis of plasma cell neoplasms depends on the accurate quantification of plasma cells, traditionally done by immunohistochemical CD138 staining of bone marrow biopsies. Currently, there is no fully satisfactory reference method for this quantification. In our previous study, we compared the commonly used overview estimation method (method A) with a novel method for counting plasma cells in three representative areas (method B). Results showed comparable concordance parameters between the two methods. In this follow-up study, we compared the previously evaluated methods with a digital analysis method (method C) that uses artificial intelligence in open-source software, QuPath. METHODS: Archived CD138 immunohistochemically stained trephine sections of bone marrow samples used in our previous study were used (n = 33). Reviewers selected three representative areas on each sample by taking images with a light microscope and camera. Digital analysis was performed using the positive cell detection function in QuPath. The entire process was repeated by each reviewer to test intraobserver concordance (concordance correlation coefficient [CCC]) in addition to interobserver concordance (intraclass correlation coefficient [ICC]). RESULTS: Intraobserver concordance of method C showed strong agreement for all reviewers with the lowest CCC = 0.854. Interobserver concordance for method C using ICC was 0.909 and 0.949. This showed high interobserver agreement with significant differences between method C and previously assessed method A (ICC = 0.793 and 0.713) and method B (ICC = 0.657 and 0.658). CONCLUSION: We were able to successfully count CD138-positive plasma cells in bone marrow biopsies using artificial intelligence. This method is superior to both manual counting and overview estimation, regardless of tumour load.

Attitudes towards mental illness in Malawi: a cross-sectional survey.

BACKGROUND: Stigma and discrimination associated with mental illness are strongly linked to suffering, disability and poverty. In order to protect the rights of those with mental disorders and to sensitively develop services, it is vital to gain a more accurate understanding of the frequency and nature of stigma against people with mental illness. Little research about this issue has been conducted in Sub- Saharan Africa. Our study aimed to describe levels of stigma in Malawi. METHODS: A cross-sectional survey of patients and carers attending mental health and non-mental health related clinics in a general hospital in Blantyre, Malawi. Participants were interviewed using an adapted version of the questionnaire developed for the "World Psychiatric Association Program to Reduce Stigma and Discrimination Because of Schizophrenia". RESULTS: 210 participants participated in our study. Most attributed mental disorder to alcohol and illicit drug abuse (95.7%). This was closely followed by brain disease (92.8%), spirit possession (82.8%) and psychological trauma (76.1%). There were some associations found between demographic variables and single question responses, however no consistent trends were observed in stigmatising beliefs. These results should be interpreted with caution and in the context of existing research. Contrary to the international literature, having direct personal experience of mental illness seemed to have no positive effect on stigmatising beliefs in our sample. CONCLUSIONS: Our study contributes to an emerging picture that individuals in Sub-Saharan Africa most commonly attribute mental illness to alcohol/ illicit drug use and spirit possession. Our work adds weight to the argument that stigma towards mental illness is an important global health and human rights issue.

Meeting demand-Obstetric hemorrhage and blood availability in Malawi, a qualitative study.

BACKGROUND: Postpartum haemorrhage (PPH) is the leading cause of maternal mortality in Malawi. Despite the presence of a centralized institution supplying blood and blood products for hospitals across the country, a lack of timely blood transfusion has been identified as a critical barrier to successful PPH management. This study aims to understand the factors that affect the blood delivery pipeline and adequate access to blood products for postpartum haemorrhage patients. METHODS: Qualitative data were collected through in-depth interviews with key stakeholders across the blood delivery pipeline. Interviews were conducted from July 2020 to January 2021 at Queen Elizabeth Central Hospital and Mulanje District Hospital, a referral and district hospital respectively, as well as the Malawi Blood Transfusion Service. Line by line, open coding was used to perform a thematic analysis of the data using Nvivo and Atlas.ti software. RESULTS: Five key themes were identified: 1) Lack of blood availability due to an inadequate donor pool, 2) Transportation of blood products and PPH patients is impeded by distance to target sites and competing interests for blood delivery vehicles, 3) The Malawi Blood Transfusion Service has difficulty meeting demand for blood products due to inadequate funding and difficulty retaining blood donors, 4) Current PPH management protocols and practices lead to delays due to inconsistent guidelines on delivery and analysis of patient samples, and 5) Communication between health cadres is inconsistent and affected by a lack of adequate resources. CONCLUSIONS: Barriers to timely blood transfusion for PPH patients exist across the blood delivery pipeline. While an investment of infrastructure would alleviate many obstacles, several solutions identified in this study can be implemented without additional resources, such as establishing joint department meetings to improve communication between health cadres. Ultimately, given a resource limited setting, it may be worth considering de-centralizing the blood supply.