Applying Machine Learning to Pediatric Critical Care Data.

OBJECTIVES: To explore whether machine learning applied to pediatric critical care data could discover medically pertinent information, we analyzed clinically collected electronic medical record data, after data extraction and preparation, using k-means clustering. DESIGN: Retrospective analysis of electronic medical record ICU data. SETTING: Tertiary Children's Hospital PICU. PATIENTS: Anonymized electronic medical record data from PICU admissions over 10 years. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Data from 11,384 PICU episodes were cleaned, and specific features were generated. A k-means clustering algorithm was applied, and the stability and medical validity of the resulting 10 clusters were determined. The distribution of mortality, length of stay, use of ventilation and pressors, and diagnostic categories among resulting clusters was analyzed. Clusters had significant prognostic information (p < 0.0001). Cluster membership predicted mortality (area under the curve of the receiver operating characteristic = 0.77). Length of stay, the use of inotropes and intubation, and diagnostic categories were nonrandomly distributed among the clusters (p < 0.0001). CONCLUSIONS: A standard machine learning methodology was able to determine significant medically relevant information from PICU electronic medical record data which included prognosis, diagnosis, and therapy in an unsupervised approach. Further development and application of machine learning to critical care data may provide insights into how critical illness happens to children.

Efficacy and Safety of Oral Metronomic Chemotherapy in Recurrent Refractory Advanced Gynaecological Cancer: An Experience From the Regional Cancer Centre of Eastern India.

INTRODUCTION: The outcome of recurrent/metastatic gynaecological malignancy has drastically improved with the introduction of poly(ADP-ribose) polymerase inhibitors and immunotherapy, but the use of these drugs in routine practice is complicated due to access barriers and their high cost in developing countries. The purpose of this study is to present the clinical response, outcome and safety of oral metronomic chemotherapy (OMCT) in resource-limited, financially constrained populations. METHODS: This is a retrospective study on patients with advanced gynaecological cancer treated at Chittaranjan National Cancer Institute, Kolkata, India, from 2021 to 2023. The patients were treated with one of these two regimens: a split-dose course of cyclophosphamide (50 mg orally once daily for 21 days) and capecitabine (500 mg twice daily continuous) or a fixed-dose combination (capecitabine 1800 mg and cyclophosphamide 80 mg orally for 14 days in every 21 days) until disease progression or unacceptable toxicities occurred. All data was captured from the hospital's medical records until June 2023. Toxicity data was reported per the Common Terminology Criteria for Adverse Events (CTCAE) v5.1, and progression-free survival (PFS) was estimated using Kaplan-Meier methods. RESULTS: Among 34 screened patients, 10 were excluded due to noncompliance. This study analysed 24 patients with a median age at diagnosis of 56 years (IQ range 44-75). Sixteen (67%) patients were at stage IV disease with an Eastern Cooperative Oncology Group (ECOG) performance status of 3. Ovarian and cervical cancers were 80% and 20%, respectively; among them, 16 (67%) patients were platinum-refractory. Forty-two per cent of patients received three lines of chemotherapy before OMCT. A split course versus fixed dose was given to 67% versus 33% of the population; the best responses per the Response Evaluation Criteria in Solid Tumours v1.1 were complete response in 12%, partial response in 67% and stable disease in 21%. The most common toxicities were grade I anaemia (54%), grade I chemotherapy-induced nausea and vomiting (46%), grade I fatigue (42%) and grade I neutropenia (21%). Twenty-five per cent of patients were offered next-line systemic therapy after progression. The entire cohort had a median PFS of nine months (95%, CI: 5.2-12.7). Cox regression analysis identified a median PFS of 12 months (95%, CI: 6.2-17.7) among platinum-refractory groups. CONCLUSION: OMCT was a well-tolerated, affordable regimen with durable clinical response and survival outcome (median PFS of nine months) in recurrent, refractory advanced gynaecological cancer and can be offered to patients at resource-limited centres.

A Prospective Study Comparing Dosimetry between Computed Tomography (CT) based Radiation Planning and Positron Emission Computed Tomography (PET-CT) based Radiation Planning in Treatment of Non-Metastatic Non Small Cell Lung Carcinoma.

BACKGROUND: To evaluate dosimetry between CT based radiation planning and PET-CT based radiation planning. MATERIAL & METHODS: Histologically proven 40 cases of locally advanced non-small cell carcinoma of lung were accrued for the prospective study. Contrast enhanced planning CT images and PET images were acquired. Target volume delineation, organs of interest & radiation planning were performed in Eclipse V 14.5 followed by dosimetric comparison among GTV, PTV and OARs. A p-value of <0.05 was considered significant. RESULTS: The mean of GTV were 141.18 ± 119.76 cc in CT and 115.54 ± 91.02 cc in PET-CT based and the difference was statistically significant (p=0.03). The mean of CTV were 313.91 ± 180.87 cc in CT and 260.81 ± 148.83 cc in PET-CT based and the difference was statistically significant (p=0.03). The contralateral lung mean dose was statistically very significant (p<0.01) among both the 3D-CRT plans which were 8.49 Gy in CECT based planning and 9.53 Gy in PET CT based planning. The heart mean dose was also statistically significant (p=0.03) among the plans which were 17.90 Gy in CECT based planning and 17.06 Gy in PET CT based planning. Mann-Whitney U test showed the CT based PTV D90 was 58.20 Gy vs 57.58 Gy in PET CT based planning (p=0.02). PTV V95 were also comparable in both of the plans (p=0.02). CONCLUSIONS: GTV measured using PET-CT, may be greater or lesser than the CECT-based GTV. PET-CT-based contouring is more accurate for identifying tumour margins and new lymph node volumes.

Barriers and explanatory mechanisms in diagnostic delay in four cancers - A health-care disparity?

INTRODUCTION: Most cancer disparities research has traditionally focused on two key outcomes, access to appropriate treatment and survival, but they do not encompass important aspects of patient-centered care such as the timeliness of diagnosis and treatment. Prolonged time intervals between symptom onset and treatment initiation increase the risk of poorer clinical outcomes and are associated with worse patient experience of subsequent cancer care. This study aims to assess the delay from symptom onset to the start of definitive treatment and to identify the possible contributory factors and its impact on response in cancers of head and neck, breast, cervix, and lung. MATERIALS AND METHODS: This was a retrospective study of patients enrolled between 2015 and 2017. A questionnaire was filled in about socioeconomic aspects, patient history, tumor data, professionals who evaluated the patients, and the respective time delays. Statistical test included Mann-Whitney U test, univariate and multivariate test, and one-way ANOVA to evaluate the correlations. RESULTS: Stage migration was significant with patient delay (P < 0.01). In head and neck squamous cell carcinoma (HNSCC) and Carcinoma lung, a significant correlation was found between referral delay and residence (P < 0.01) and treatment delay and reason for referral (HNSCC only) (P = 0.04). Referral delay and treatment delay were correlated to response in breast and cervix, respectively (P < 0.01). CONCLUSION: Social awareness, regularly updating primary care physicians about alarming symptoms of cancer, developing guidelines to identify these symptoms, promoting continuity of care, and enabling access to specialist expertise through prompt referral should all help prevent delays in cancer diagnosis.

Virtual Neonatal Echocardiographic Training System (VNETS): An Echocardiographic Simulator for Training Basic Transthoracic Echocardiography Skills in Neonates and Infants.

There is a great need for training in pediatric echocardiography. In addition to physicians being trained in pediatric cardiology and echocardiography technologists, neonatologist, pediatric intensivists, and other health care professionals may be interested in such training. Since, there is limited opportunity of training on live patients, echocardiographic simulators may be of help. No simulator with complete range of echocardiographic modalities is available for neonates and infants. The aim of this project was to develop a mannequin-based echocardiographic simulator capable of simulating full range of pediatric 2D, color flow Doppler, spectral Doppler, and M-mode echocardiograms. A mannequin, a laptop computer, a magnetic tracking device, and a six-degree freedom (6DOF) sensor incorporated in a dummy transducer serve as the hardware platform of the simulator. We obtained six to seven 4D echocardiographic datasets in DICOM format through five acoustic windows from each infant along with a complete set of 2D video clips of color flow, Doppler, and M-mode. The 4D datasets are sliced into 3D slices using the visualization toolkit and are displayed as 2D echocardiograms through the information obtained by the 6DOF sensor. The coordinates from specific 3D slices triggers display of video clips of color flow, M-mode, and Doppler echocardiogram. Software written in C++ programming language controls the basic function of the program. The main simulator screen displays the full range of 2D echocardiograms including color flow Doppler, spectral Doppler, and M-mode from each acoustic window, whereas the side screen display the position and motion of the cutting planes through a 3D heart model. The system includes a software module to perform hemodynamic measurements from specific video clips images. Our hybrid, mannequin-based pediatric echocardiography simulator provides full range of pediatric echocardiography training experience. This simulator may help training in pediatric echocardiography for which there is a growing demand in clinical medicine.

Hepatoprotective activity of Macrothelypteris torresiana (Gaudich.) aerial parts against CCl4-induced hepatotoxicity in rodents and analysis of polyphenolic compounds by HPTLC.

Macrothelypteris torresiana is a fern species belonging to family Thelypteridaceae. The present study was conducted to evaluate hepatoprotective potential of ethanol extract from M. torresiana aerial parts (EEMTAP) and detect the polyphenolic compounds present in the extract using high performance thin layer chromatography (HPTLC). Hepatoprotective potential of EEMTAP were tested at doses of 300 and 600 mg/kg, per os (p.o.), on Wistar albino rats. The extract and silymarin treated animal groups showed significant decrease in activities of different biochemical parameters like serum glutamic oxaloacetic transaminase (SGOT), serum glutamate-pyruvate transaminase (SGPT), alkaline phosphatase (ALP), which were elevated by carbon tetrachloride (CCl4) intoxication. The levels of total bilirubin and total protein alongwith the liver weight were also restored to normalcy by EEMTAP and silymarin treatment. After CCl4 administration the level of hepatic antioxidant enzymes such as Glutathione (GSH) and Catalase (CAT) were decreased whereas the level of hepatic lipid peroxidation (LPO) was elevated. The level of these hepatic antioxidant enzymes were also brought to normalcy by EEMTAP and silymarin treatment. Histological studies supported the biochemical findings and treatment with EEMTAP at doses 300 and 600 mg/kg, p.o. was found to be effective in restoring CCl4-induced hepatotoxicity in rats. A simple HPTLC analysis was conducted for the detection of polyphenolic compounds in EEMTAP, and the result revealed the presence of caffeic acid as phenolic acid and quercetin as flavonoid. The proposed HPTLC method is simple, concise and provides a good resolution of caffeic acid and quercetin from other constituents present in EEMTAP.

A Complete Profile on Blind-your-eye Mangrove Excoecaria Agallocha L. (Euphorbiaceae): Ethnobotany, Phytochemistry, and Pharmacological Aspects.

Traditional system of medicine consists of large number of plants with various medicinal and pharmacological importances. This article provides a comprehensive review of the complete profile of an important mangrove plant Excoecaria agallocha L. (Euphorbiaceae) and elaborately describing the ethnobotany, phytochemistry, and pharmacological properties. It is used traditionally in the treatment of various diseases such as epilepsy, ulcers, leprosy, rheumatism, and paralysis. The latex obtained from the bark is poisonous in nature and may cause temporary blindness, thus it is also known as the blind-your-eye mangrove plant. Many phytoconstituents were isolated from the plant, which were mainly diterpenoids, triterpenoids, flavonoids, sterols, and few other compounds. The plant also showed many pharmacological activities such as antioxidant, antimicrobial, anti-inflammatory, analgesic, antiulcer, anticancer, antireverse transcriptase, antihistamine-release, antifilarial, DNA damage protective, antidiabetic, and antitumor protecting activities. Hence, this review could help guide researchers anticipating to undertake further investigations in these directions.

Hepatoprotective activity of Macrothelypteris torresiana (Gaudich.) aerial parts against CCl4-induced hepatotoxicity in rodents and analysis of polyphenolic compounds by HPTLC / 药物分析学报

Macrothelypteris torresiana is a fern species belonging to the family Thelypteridaceae. The present study was conducted to evaluate hepatoprotective potential of ethanol extract from M. torresiana aerial parts (EEMTAP) and detect the polyphenolic compounds present in the extract using high performance thin layerchromatography (HPTLC). Hepatoprotective potential of EEMTAP were tested at doses of 300 and 600 mg/kg, per os (p.o.), on Wistar albino rats. The extract and silymarin treated animal groups showed significant decrease in activities ofdifferent biochemical parameters like serum glutamic oxaloacetic transaminase(SGOT), serum glutamate-pyruvate transaminase (SGPT), and alkaline phosphatase (ALP), which were elevated by carbon tetrachloride (CCl4) intoxication. The levels of total bilirubin and total protein along with the liver weight were also restoredto normalcy by EEMTAP and silymarin treatment. After CCl4 administration, the levels of hepatic antioxidant enzymes such as glutathione (GSH) and catalase (CAT) were decreased whereas the level of hepatic lipid peroxidation (LPO) was elevated. The levels of these hepatic antioxidant enzymes were also brought to normalcy by EEMTAP and silymarin treatment. Histological studies supported the biochemical findings, and treatment with EEMTAP at doses of 300 and 600 mg/kg, p.o. was found to be effective in restoring CCl4-induced hepatotoxicity in rats. A simple HPTLC analysis was conducted for the detection of polyphenolic compounds in EEMTAP, and the result revealed the presence of caffeic acid as phenolic acid and quercetin as flavonoid. The proposed HPTLC method is simple and concise and provides a good resolution of caffeic acid and quercetin from other constituents present in EEMTAP.