Machine Learning Model for Classifying the Results of Fetal Cardiotocography Conducted in High-Risk Pregnancies.

PURPOSE: Fetal well-being is usually assessed via fetal heart rate (FHR) monitoring during the antepartum period. However, the interpretation of FHR is a complex and subjective process with low reliability. This study developed a machine learning model that can classify fetal cardiotocography results as normal or abnormal. MATERIALS AND METHODS: In total, 17492 fetal cardiotocography results were obtained from Ajou University Hospital and 100 fetal cardiotocography results from Czech Technical University and University Hospital in Brno. Board-certified physicians then reviewed the fetal cardiotocography results and labeled 1456 of them as gold-standard; these results were used to train and validate the model. The remaining results were used to validate the clinical effectiveness of the model with the actual outcome. RESULTS: In a test dataset, our model achieved an area under the receiver operating characteristic curve (AUROC) of 0.89 and area under the precision-recall curve (AUPRC) of 0.73 in an internal validation dataset. An average AUROC of 0.73 and average AUPRC of 0.40 were achieved in the external validation dataset. Fetus abnormality score, as calculated from the continuous fetal cardiotocography results, was significantly associated with actual clinical outcomes [intrauterine growth restriction: odds ratio, 3.626 (p=0.031); Apgar score 1 min: odds ratio, 9.523 (p<0.001), Apgar score 5 min: odds ratio, 11.49 (p=0.001), and fetal distress: odds ratio, 23.09 (p<0.001)]. CONCLUSION: The machine learning model developed in this study showed precision in classifying FHR signals. This suggests that the model can be applied to medical devices as a screening tool for monitoring fetal status.

Anti-N-methyl-D-aspartate receptor encephalitis associated with ovarian teratoma in Korea: three case reports.

Anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis is a severe autoimmune paraneoplastic syndrome associated with ovarian teratomas. Most patients develop neurologic symptoms, including psychosis, memory deficits, seizures, or abnormal movements, and experience abdominal pain related to ovarian neoplasm. We present a case report of three patients diagnosed with anti-NMDAR encephalitis accompanied by ovarian teratomas at Ajou University Hospital in Korea. The patients demonstrated a different clinical course of the disease. However, upon diagnosis, all patients underwent surgical removal of the ovarian teratoma followed by intensive immunotherapy. The symptoms progressively improved following treatment. This is a case report of a rare autoimmune anti-NMDAR encephalitis associated with ovarian neoplasms, including immature teratoma.

Rapid exacerbation of renal function after administration of hydroxyethyl starch in a dog.

Hydroxyethyl starches (HES) are commonly used synthetic colloidal solution in veterinary medicine. Despite of possible adverse effect to kidney injury in human, there is no report about nephrotoxic effects of HES in dogs. HES was administered to a Golden retriever (4-year-old, intact male) with ascites in order to increase plasma osmolality. Initially, the dog was mild azotemic, however, kidney function was rapidly deteriorated after several days of HES administration. Finally, histopathological examination revealed remarkable osmotic nephrosis. In the case reported herein, acute kidney injury was remarkably developed after HES administration. Clinical and histopathologic findings of acute kidney injury support nephrotoxic effects of HES to a dog.

Diagnosis of Lymphoid Malignancy by PCR for Analysis of Antigen Receptor Rearrangement after Blood Transfusion in a Dog with Acute Lymphocytic Leukemia.

Acute lymphocytic leukemia (ALL) is uncommon lymphoid malignancy in dogs, and its diagnosis is challenging. A 14-year-old spayed female mixed breed dog was transferred to a veterinary medical teaching hospital for an immediate blood transfusion. The dog showed lethargy, pale mucous membranes, and a weak femoral pulse. Complete blood count revealed non-regenerative anemia and severe leukopenia with thrombocytopenia. ALL was tentatively diagnosed based on the predominance of immature lymphoblasts on blood film examination. For confirmation of lymphoid malignancy, PCR for antigen receptor rearrangement (PARR) on a peripheral blood sample and flow cytometry analysis were performed after blood transfusion. Flow cytometry analysis revealed that lymphocyte subsets were of normal composition, but PARR detected a T-cell malignancy. The dog was diagnosed with ALL and survived 1 wk after diagnosis. In conclusion, after blood transfusion, flow cytometry was not a reliable diagnostic method for an ALL dog, whereas PARR could detect lymphoid malignancy. Our results suggest that PARR should be the first-line diagnostic tool to detect canine lymphoid malignancy after a blood transfusion.

High-level production of astaxanthin by Xanthophyllomyces dendrorhous mutant JH1 using statistical experimental designs.

Medium composition was optimized for high-level production of astaxanthin by Xanthophyllomyces dendrorhous mutant JH1 using statistical experimental designs. Glucose and yeast extract were the most important factors affecting astaxanthin production. Glucose 3.89%, yeast extract 0.29%, KH2PO4 0.25%, MgSO4 0.05%, MnSO4 0.02%, and CaCl2 0.01% were optimum for high-level production of astaxanthin. Under optimized conditions, the maximum concentration of astaxanthin obtained after 7 d of cultivation was 36.06 mg/l. The concentration of astaxanthin predicted by a polynomial model was 36.16 mg/l.