Detection of anemic condition in patients from clinical markers and explainable artificial intelligence.

BACKGROUND: Anaemia is a commonly known blood illness worldwide. Red blood cell (RBC) count or oxygen carrying capability being insufficient are two ways to describe anaemia. This disorder has an impact on the quality of life. If anaemia is detected in the initial stage, appropriate care can be taken to prevent further harm. OBJECTIVE: This study proposes a machine learning approach to identify anaemia from clinical markers, which will help further in clinical practice. METHODS: The models are designed with a dataset of 364 samples and 12 blood test attributes. The developed algorithm is expected to provide decision support to the clinicians based on blood markers. Each model is trained and validated on several performance metrics. RESULTS: The accuracy obtained by the random forest, K nearest neighbour, support vector machine, Naive Bayes, xgboost, and catboost are 97%, 98%, 95%, 95%, 98% and 97% respectively. Four explainers such as Shapley Additive Values (SHAP), QLattice, Eli5 and local interpretable model-agnostic explanations (LIME) are explored for interpreting the model predictions. CONCLUSION: The study provides insights into the potential of machine learning algorithms for classification and may help in the development of automated and accurate diagnostic tools for anaemia.

Evaluating patient blood management practices using PBM metrics in a tertiary care center.

BACKGROUND: PBM metrics play a crucial role in assessing and monitoring the effectiveness of PBM programs in healthcare settings. The present study aimed to assess the indicators to achieve effective enforcement of PBM at a tertiary care referral hospital. SUBJECTS AND METHOD: A prospective observational study was conducted on patients admitted for elective surgery at a tertiary care referral centre. PBM metrics were developed and assessed for various parameters, including documentation, patient evaluation, blood ordering schedule, and appropriateness. Experts in transfusion medicine and haematology checked content validity. Eleven different parameters were analysed, and a score was assigned based on the performance. The outcome was categorized as poor, satisfactory, or good. RESULTS: The study included 612 patients meeting the inclusion criteria and recruited from Orthopaedics, General Surgery, OBG, Urology, and ENT departments. All departments completed pre-operative anaemia tests, with General Surgery and Orthopaedics conducting the most red cell transfusions. During the study, all of the blood units were used, and there was no waste. The C/T ratio was greater in the Departments of General Surgery, Urology, and Otorhinolaryngology. Pre-operative anaemia was found in 44.12% of patients, 44 patients had red cell transfusions, with 65% getting single-unit PRBC transfusions. All departments received a PBM score between 17-19, showing adequate PBM but with room for improvement. CONCLUSION: The current study utilized Patient Blood Management (PBM) metrics to critically assess the existing practices and identify the key gaps and areas for improvement in a tertiary care centre.

Pediatric Non-Down Syndrome Acute Megakaryoblastic Leukemia With Unusual Immunophenotype.

Acute megakaryoblastic leukemia (AMKL) is a rare subtype of acute myeloid leukemia (AML) characterized by abnormal megakaryoblasts expressing platelet-specific surface antigens. 4%-16% of childhood AMLs are AMKL. Childhood AMKL is usually associated with Down syndrome (DS). It is 500 times more common in patients with DS when compared to the general population. In contrast, non-DS-AMKL is much rarer. We describe a case of de novo non-DS-AMKL in a teenage girl child who presented with a history of excessive tiredness, fever, abdominal pain for three months, and vomiting for four days. She had lost appetite, and weight. On examination she was pale; there was no clubbing, hepatosplenomegaly or lymphadenopathy. There were no dysmorphic features or neurocutaneous markers. Laboratory tests showed bicytopenia (Hb: 6.5g/dL, total WBC count: 700/µL, platelet count: 216,000/ µL, Reticulocyte %: 0.42) and 14% blasts on the peripheral blood smear. Platelet clumps and anisocytosis were also noted. Bone marrow aspirate showed a few hypocellular particles with dilute cell trails but showed 42% blasts. Mature megakaryocytes showed marked dyspoiesis. Flow cytometry on bone marrow aspirate showed myeloblasts and megakaryoblasts. Karyotyping showed 46 XX. Hence, a final diagnosis of non-DS-AMKL was established. She was treated symptomatically. However, she was discharged on request. Interestingly, the expression of erythroid markers such as CD36 and lymphoid markers like CD7 is usually seen in DS-AMKL and not in non-DS-AMKL. AMKL is treated with AML-directed chemotherapies. Although complete remission rates are similar to other AML subtypes, overall survival is only about 18-40 weeks.

Machine Learning-Based Detection of Dengue from Blood Smear Images Utilizing Platelet and Lymphocyte Characteristics.

Dengue fever, also known as break-bone fever, can be life-threatening. Caused by DENV, an RNA virus from the Flaviviridae family, dengue is currently a globally important public health problem. The clinical methods available for dengue diagnosis require skilled supervision. They are manual, time-consuming, labor-intensive, and not affordable to common people. This paper describes a method that can support clinicians during dengue diagnosis. It is proposed to automate the peripheral blood smear (PBS) examination using Artificial Intelligence (AI) to aid dengue diagnosis. Nowadays, AI, especially Machine Learning (ML), is increasingly being explored for successful analyses in the biomedical field. Digital pathology coupled with AI holds great potential in developing healthcare services. The automation system developed incorporates a blob detection method to detect platelets and thrombocytopenia from the PBS images. The results achieved are clinically acceptable. Moreover, an ML-based technique is proposed to detect dengue from the images of PBS based on the lymphocyte nucleus. Ten features are extracted, including six morphological and four Gray Level Spatial Dependance Matrix (GLSDM) features, out of the lymphocyte nucleus of normal and dengue cases. Features are then subjected to various popular supervised classifiers built using a ten-fold cross-validation policy for automated dengue detection. Among all the classifiers, the best performance was achieved by Support Vector Machine (SVM) and Decision Tree (DT), each with an accuracy of 93.62%. Furthermore, 1000 deep features extracted using pre-trained MobileNetV2 and 177 textural features extracted using Local binary pattern (LBP) from the lymphocyte nucleus are subjected to feature selection. The ReliefF selected 100 most significant features are then fed to the classifiers. The best performance was attained using an SVM classifier with 95.74% accuracy. With the obtained results, it is evident that this proposed approach can efficiently contribute as an adjuvant tool for diagnosing dengue from the digital microscopic images of PBS.

Bilateral massive nephromegaly-A rare presentation of t-cell acute lymphoblastic leukemia.

INTRODUCTION: Renal infiltration by leukemia causing massive bilateral nephromegaly is an extremely rare presentation of T-cell acute lymphoblastic leukemia(T-ALL). CASE REPORT: 18-month-old female toddler presented with fever and progressive abdominal distension of 4-6 weeks duration. Imaging revealed bilateral massively enlarged kidneys with normal excretion. Peripheral blood counts and smear examination was unremarkable and immunophenotypic evaluation of marrow was consistent with T-ALL. Chest imaging was unremarkable. She was started on modified Indian Childhood Collaborative Leukemia Group (ICiCLe) ALL protocol. Even with the best anti-tumor lysis syndrome (TLS) prophylaxis the child required two sessions of hemodialysis. An end-induction morphological remission & end-consolidation negative minimal residual disease (MRD) could be achieved. CONCLUSION: Bilateral massive nephromegaly is an extremely rare presentation of T-ALL. This case emphasizes the unusual presentation, need for prompt remediation of TLS, and most importantly the use of early intensification with four drug anthracycline & dexamethasone-based therapy for the treatment of T-ALL in children.

Impact of World Health Organization (WHO) Revised Criteria-2016 on the Diagnosis of Polycythemia Vera.

The diagnosis of polycythemia vera (PV) requires the integration of clinical and laboratory findings, bone marrow morphologic features, and JAK2 analysis. JAK2V617F (exon 14) mutation is found in 95% of PV cases. In PV, addition of characteristic bone marrow morphology as one of three major diagnostic criteria allowed reduced hemoglobin/hematocrit threshold for diagnosis to 16.5 g/dL/49% in men and 16 g/dL/48% in women. JAK2 mutation is still the third major diagnostic criterion in PV. Low serum erythropoietin level is now considered as minor criterion in PV and is used to detect cases, which are negative for JAK2 mutation. In this retrospective study, cases diagnosed as PV from January 2013 to December 2015 were reclassified using WHO 2016 criteria. Their clinical and laboratory parameters along with treatment and outcome were studied. Out of 26 patients of previously diagnosed PV, either definitively or provisionally, twenty-one were found to comply with the new 2016 revision of the WHO Criteria. Median age was 55.5 years, with a male preponderance. The median values of hemoglobin, hematocrit and platelets were 17.5 gm/dL, 56.7% and 493 × 109/L, respectively. JAK2V617F was mutated in 17 cases. Bone marrow showed hypercellularity, panmyelosis and marked megakaryocyte dyspoiesis in all patients. All patients had normal oxygen saturation, confirming the primary nature of the disease. Our study, first of its kind in India, underscores the importance of the 2016 revision of the WHO document in detecting cases of masked PV.

Blastoid Variant of Mantle Cell Lymphoma with Leukemic Presentation - A Rare Case Report.

Mantle Cell Lymphoma (MCL) is a type of Non-Hodgkin's lymphoma and has a wide spectrum of histopathological subtypes of which the blastoid or the blastic variant constitutes 10-15% of all cases. It is difficult to diagnose blastoid variant of MCL on the basis of morphology alone as it mimics lymphoblastic lymphoma and centroblastic large cell lymphoma, hence additional analysis like immunophenotyping and molecular studies aid in its diagnosis. We present a case of 45-year-old male who presented to medicine OPD with chief complaints of fever, fatigability and inguinal swelling. Complete blood count, peripheral smear and bone marrow examination was performed. Peripheral smear showed thrombocytopenia along with 53% abnormal cells. On bone marrow examination 43% abnormal lymphoid cells were seen. This case was diagnosed as blastoid variant of MCL on the basis of routine morphology and immunohistochemistry on bone marrow biopsy and flow cytometric immunophenotyping on peripheral blood.

Systemic mastocytosis: predominantly involving the bone, a case report.

Systemic mastocytosis (SM) is a rare clonal disorder of mast cells that can range from chronic smouldering type to aggressive mast cell leukaemia. It presents with non-specific symptoms like urticaria pigmentosa, unexplained flushing, hypotension and abdominal cramps, which may lead to a misdiagnosis, if there is no high index of clinical suspicion. This is a case report of a 52-year-old lady, with systemic mastocytosis, who presented with severe chronic back ache and no other clinical features. X - ray revealed lytic lesions in the lumbar vertebrae and bone marrow aspiration and a trephine biopsy examination showed infiltration by mast cells, with a positivity for Toluidine blue stain and CD 117. She was also noted to have peripheral eosinophilia, which is frequently encountered with this condition. She was diagnosed to have chronic indolent systemic mastocytosis which involved the bone predominantly.

Correlation of morphologic and cytochemical diagnosis with flowcytometric analysis in acute leukemia.

INTRODUCTION: The classification of acute leukemias has revolutionized over the years. Immunophenotyping of acute leukemia has gained popularity because of its influence on treatment and prognosis of the disease. The various antigens expressed by the leukemic cells can be assessed by flowcytometry (FCA) and can be used in rendering specific treatment and predicting the outcome of the different types of acute leukemia. AIMS: The main aim of this study was to compare the morphologic and cytochemical diagnoses with flowcytometric diagnoses in acute leukemia and to analyze the usefulness of FCA over morphology. RESULTS: In this study we analyzed 50 cases of acute leukemia and found concordance rate as high as 86% between morphologic/cytochemical diagnosis and flowcytometric diagnosis. Of these, complete concordance was seen in 58% of the cases and partial concordance was seen in 22% of the cases. Non-concordance was seen in only 4% of our cases. In remaining 16% of our cases FCA helped in sub classifying the acute leukemia where morphology and cytochemistry had failed to do so. CD19 and 20 were found to be consistent B-cell markers and CD3 was a very specific marker for T-cell leukemia. CD13 and 33 were important myeloid markers and were aided by other secondary panel of markers like CD14, CD117 and CD41. CONCLUSION: FCA not only helps in confirming morphologic diagnosis in acute leukemia but also helps in assigning specific lineage to the blasts, particularly in acute lymphoid leukemia. Immunophenotyping is of utmost importance in classifying acute leukemia as it greatly influences the treatment and the prognosis.

Chronic myeloid leukemia with hyperdiploidy: a case report with review of literature.

Chronic myeloid leukemia (CML) is a common marrow stem cell neoplasm characterized by the presence of the Philadelphia (Ph) chromosome in more than 90% of patients. Studies have shown that CML can be associated with various other cytogenetic abnormalities. 5-10% of these cases can show complex translocations involving other chromosomes in addition to Ph chromosome. Here, we report a Ph-positive CML patient with a hyperdiploid karyotype who presented clinically in chronic phase but progressed to blast crisis in spite of treatment with Imatinib. This case highlights the significance of cytogenetic abnormalities on the prognosis in CML.