Use of Machine Learning for Early Detection of Maternal Cardiovascular Conditions: Retrospective Study Using Electronic Health Record Data.

BACKGROUND: Cardiovascular conditions (eg, cardiac and coronary conditions, hypertensive disorders of pregnancy, and cardiomyopathies) were the leading cause of maternal mortality between 2017 and 2019. The United States has the highest maternal mortality rate of any high-income nation, disproportionately impacting those who identify as non-Hispanic Black or Hispanic. Novel clinical approaches to the detection and diagnosis of cardiovascular conditions are therefore imperative. Emerging research is demonstrating that machine learning (ML) is a promising tool for detecting patients at increased risk for hypertensive disorders during pregnancy. However, additional studies are required to determine how integrating ML and big data, such as electronic health records (EHRs), can improve the identification of obstetric patients at higher risk of cardiovascular conditions. OBJECTIVE: This study aimed to evaluate the capability and timing of a proprietary ML algorithm, Healthy Outcomes for all Pregnancy Experiences-Cardiovascular-Risk Assessment Technology (HOPE-CAT), to detect maternal-related cardiovascular conditions and outcomes. METHODS: Retrospective data from the EHRs of a large health care system were investigated by HOPE-CAT in a virtual server environment. Deidentification of EHR data and standardization enabled HOPE-CAT to analyze data without pre-existing biases. The ML algorithm assessed risk factors selected by clinical experts in cardio-obstetrics, and the algorithm was iteratively trained using relevant literature and current standards of risk identification. After refinement of the algorithm's learned risk factors, risk profiles were generated for every patient including a designation of standard versus high risk. The profiles were individually paired with clinical outcomes pertaining to cardiovascular pregnancy conditions and complications, wherein a delta was calculated between the date of the risk profile and the actual diagnosis or intervention in the EHR. RESULTS: In total, 604 pregnancies resulting in birth had records or diagnoses that could be compared against the risk profile; the majority of patients identified as Black (n=482, 79.8%) and aged between 21 and 34 years (n=509, 84.4%). Preeclampsia (n=547, 90.6%) was the most common condition, followed by thromboembolism (n=16, 2.7%) and acute kidney disease or failure (n=13, 2.2%). The average delta was 56.8 (SD 69.7) days between the identification of risk factors by HOPE-CAT and the first date of diagnosis or intervention of a related condition reported in the EHR. HOPE-CAT showed the strongest performance in early risk detection of myocardial infarction at a delta of 65.7 (SD 81.4) days. CONCLUSIONS: This study provides additional evidence to support ML in obstetrical patients to enhance the early detection of cardiovascular conditions during pregnancy. ML can synthesize multiday patient presentations to enhance provider decision-making and potentially reduce maternal health disparities.

Early Identification of Maternal Cardiovascular Risk Through Sourcing and Preparing Electronic Health Record Data: Machine Learning Study.

BACKGROUND: Health care data are fragmenting as patients seek care from diverse sources. Consequently, patient care is negatively impacted by disparate health records. Machine learning (ML) offers a disruptive force in its ability to inform and improve patient care and outcomes. However, the differences that exist in each individual's health records, combined with the lack of health data standards, in addition to systemic issues that render the data unreliable and that fail to create a single view of each patient, create challenges for ML. Although these problems exist throughout health care, they are especially prevalent within maternal health and exacerbate the maternal morbidity and mortality crisis in the United States. OBJECTIVE: This study aims to demonstrate that patient records extracted from the electronic health records (EHRs) of a large tertiary health care system can be made actionable for the goal of effectively using ML to identify maternal cardiovascular risk before evidence of diagnosis or intervention within the patient's record. Maternal patient records were extracted from the EHRs of a large tertiary health care system and made into patient-specific, complete data sets through a systematic method. METHODS: We outline the effort that was required to define the specifications of the computational systems, the data set, and access to relevant systems, while ensuring that data security, privacy laws, and policies were met. Data acquisition included the concatenation, anonymization, and normalization of health data across multiple EHRs in preparation for their use by a proprietary risk stratification algorithm designed to establish patient-specific baselines to identify and establish cardiovascular risk based on deviations from the patient's baselines to inform early interventions. RESULTS: Patient records can be made actionable for the goal of effectively using ML, specifically to identify cardiovascular risk in pregnant patients. CONCLUSIONS: Upon acquiring data, including their concatenation, anonymization, and normalization across multiple EHRs, the use of an ML-based tool can provide early identification of cardiovascular risk in pregnant patients.

Voice activated remote monitoring technology for heart failure patients: Study design, feasibility and observations from a pilot randomized control trial.

BACKGROUND: Heart failure (HF) is a serious health condition, associated with high health care costs, and poor outcomes. Patient empowerment and self-care are a key component of successful HF management. The emergence of telehealth may enable providers to remotely monitor patients' statuses, support adherence to medical guidelines, improve patient wellbeing, and promote daily awareness of overall patients' health. OBJECTIVE: To assess the feasibility of a voice activated technology for monitoring of HF patients, and its impact on HF clinical outcomes and health care utilization. METHODS: We conducted a randomized clinical trial; ambulatory HF patients were randomized to voice activated technology or standard of care (SOC) for 90 days. The system developed for this study monitored patient symptoms using a daily survey and alerted healthcare providers of pre-determined reported symptoms of worsening HF. We used summary statistics and descriptive visualizations to study the alerts generated by the technology and to healthcare utilization outcomes. RESULTS: The average age of patients was 54 years, the majority were Black and 45% were women. Almost all participants had an annual income below $50,000. Baseline characteristics were not statistically significantly different between the two arms. The technical infrastructure was successfully set up and two thirds of the invited study participants interacted with the technology. Patients reported favorable perception and high comfort level with the use of voice activated technology. The responses from the participants varied widely and higher perceived symptom burden was not associated with hospitalization on qualitative assessment of the data visualization plot. Among patients randomized to the voice activated technology arm, there was one HF emergency department (ED) visit and 2 HF hospitalizations; there were no events in the SOC arm. CONCLUSIONS: This study demonstrates the feasibility of remote symptom monitoring of HF patients using voice activated technology. The varying HF severity and the wide range of patient responses to the technology indicate that personalized technological approaches are needed to capture the full benefit of the technology. The differences in health care utilization between the two arms call for further study into the impact of remote monitoring on health care utilization and patients' wellbeing.

Bilateral Pulmonary Embolism in a Newly Diagnosed Case of Pulmonary Tuberculosis.

Pulmonary embolism in the cases of tuberculosis (TB) infection has incited physicians and researchers to derive a reasonable association in the past few years. However, despite the efforts, pulmonary embolism is often misdiagnosed in the context of active TB. Pulmonary embolism in TB is still considered a rare phenomenon, even though it seems to be a probable risk factor based on the emerging literature. We report a case of a young man who presented with recurrent respiratory symptoms. He had no risk factors except a former history of smoking. We believe that the symptoms he had on the initial visit were misinterpreted in the background of TB infection. We followed the case for two months after he was discharged on anticoagulants and anti-TB medication. In this case report, we would like to emphasize the need to consider this occult phenomenon in order to rule out TB in cases of pulmonary embolism and vice versa. We hope that the management of TB in the future might take into account the chances of concomitant pathology of pulmonary embolism in patients with active TB.

An Unusual Case of Klebsiella pneumoniae Endocarditis.

Klebsiella pneumoniae notoriously causes life-threatening community-acquired or hospital-acquired pneumonia. In the United States, community-acquired pneumonia is a relatively common diagnosis. However, community-acquired pneumonia due to Klebsiella pneumoniae is fairly uncommon. Delayed antibiotic administration can result in bacteremia, septicemia and other systemic complications. Infective endocarditis arising as a complication of community-acquired Klebsiella pneumoniae infection has rarely been reported. Our patient is an 88-year-old diabetic female, who was admitted to our intensive care unit due to a high-grade fever, worsening dyspnea and hypotension. Chest x-ray and blood culture were conclusive for pneumonia due to Klebsiella pneumoniae. Importantly, the species was only susceptible to colistin. Furthermore, an echocardiogram revealed mobile vegetations of the non-coronary cusp of the aortic valve. Treatment with colistin resulted in clinical improvement and an uneventful discharge from the hospital. Follow up echocardiography was scheduled upon discharge to monitor the resolution of cardiac vegetations.

A Case of Subclavian Artery Thrombosis.

Subclavian artery thrombosis is a rare cause of upper limb ischemia resulting from occlusion of the upper extremity blood supply. Symptomatic presentation is quite rare and therefore remains underdiagnosed by physicians. Possible catastrophic clinical consequences necessitate prompt rectification of the underlying disease and risk factors. Treatment modalities are often selected depending on the severity of clinical presentation. Herein, we present a case of a 52-year-old man who presented to the outpatient department with a one-month history of pain and blackish discoloration of the right-hand digits, palm, and wrist. His social history also revealed a chronic 30-year history of smoking. At the time of consultation, his past medical history was insignificant for chronic medical disease and hospitalizations. However, inpatient investigations diagnosed him with diabetes. Physical examination revealed a bad odor emanating from the devitalized affected right hand. Neurological examination was significant for the loss of pain sensation in the right hand. Furthermore, the right radial and brachial pulses were also absent (grade 0). Right upper extremity angiography revealed the occlusion of the right subclavian artery and right brachial artery. Above elbow amputation was advised and performed based on angiogram scans and physical examination findings. We report a case of subclavian artery thrombosis in an undiagnosed diabetic with a chronic history of smoking. Our report details the common etiology, clinical presentation, and management options feasible for this clinical entity. Furthermore, it reiterates the importance of counseling patients to attend annual healthcare doctor visits.

Successful Management of Coronary In-Stent Restenosis: A Case Report and Literature Review.

In-stent restenosis (ISR) arising in bare-metal stents and drug-eluting stents is difficult to manage. Herein, we report a case of ISR. Our patient had a history of percutaneous coronary intervention and presented with exaggerated angina symptoms despite being on antianginal medication. ISR was diagnosed with coronary angiography. In a clinical setting, it is treated with repeat revascularization of the blocked vessel with a re-stent placement or surgical approach.

Kawasaki Disease-Like Features in 10 Pediatric COVID-19 Cases: A Retrospective Study.

Children with coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2), usually present with symptoms of mild upper respiratory tract infection without developing any significant complications. However, this observation has been rendered incautious by hundreds of clinical cases from around the world that have depicted a less benign multisystem inflammatory illness mimicking Kawasaki disease in COVID-positive pediatric patients. Our study aimed at retrospectively reviewing the different features of Kawasaki disease-like illness in children suffering from COVID-19, including the complications, laboratory investigations, treatment strategies used during their hospital stay, and outcomes. We searched the electronic database of the two pediatric units of Mayo Hospital, Lahore, Pakistan, for children who had been admitted to the ward between April 2020 and July 2020 and were diagnosed with COVID-19. A total of 10 such pediatric cases were found, whose clinical details were then reviewed and the obtained data were presented in the form of tables and percentages. The median age was between 4 months to 11 years (mean: 6 years). Of the 10 patients, 8 (80%) were boys. Criteria for Kawasaki disease were met in all of them (100%), with a complete presentation in five (50%). Fever (100%), conjunctival and oral cavity changes (90%), and rash (80%) were the most common features. Seven (70%) patients required admission to a critical care unit, but no mortality occurred. This article can assist in understanding and dealing with Kawasaki disease-like manifestation of pediatric COVID-19 infection, especially in critical care settings, and its possible complications. It will help in a timely and appropriate decision-making regarding treatment and management of such cases.

Joubert Syndrome: A Rare Radiological Case.

Joubert syndrome is a rare autosomal recessive neurodevelopmental disease characterized by abnormal breathing patterns composed of episodic tachypnea/apnea, hypotonia, ataxia, developmental delay, intellectual impairment, ocular impairment, renal cysts, and hepatic fibrosis. We report the case of a 4-year-old boy who presented with global developmental delay, bilateral nystagmus, and gaze instability with difficulty walking and maintaining an upright posture. A detailed examination revealed facial dysmorphic features with a depressed nasal bridge and deepened orbital sockets. Neurological examination yielded positive results for hypotonia, gait ataxia, bilateral horizontal pendular nystagmus, and a grade 1 ptosis more prominent in the right eye. However, no abnormal breathing patterns were observed in our case. Magnetic resonance imaging revealed the characteristic molar tooth sign and a batwing appearance of the fourth ventricle.

Malignant Thyroid-type Papillary Neoplasm in Struma Ovarii: A Case Report.

Papillary thyroid carcinoma (PTC) arising in a coexistent struma ovarii (SO) is a rare malignancy. It manifests with abdominal symptoms such as palpable mass, pain, distension, and possibly ascites. It is usually diagnosed postoperatively, and its histopathological diagnostic criteria remain identical to that of papillary carcinoma of the thyroid gland. Due to the relative rarity of the disease, definitive guidelines for its overall management are still undefined. We present a case of a 51-year old female with suspicion of a left ovarian tumor due to her presenting symptoms: raised serum CA-125 levels and abnormal abdominopelvic CT scan findings. She underwent complete surgical debulking of the mass (total abdominal hysterectomy (TAH), bilateral salpingo-oophorectomy (BSO), omentectomy, appendectomy, and pelvic lymphadenectomy). The mass was postoperatively diagnosed by histopathology as PTC in SO (stage IA). Furthermore, our patient did not receive any adjuvant treatment. The patient has been disease-free for 24 months post-surgery and is scheduled for regular biannual follow-ups.