Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis.

BACKGROUND: Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Although evidence regarding its performance in VTE prediction is emerging, a comprehensive analysis of performance is lacking. AIMS: To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models. METHODS: A systematic literature search was performed using PubMed, MEDLINE, EMBASE, and Web of Science from inception to April 20, 2021. Search terms included "artificial intelligence" and "venous thromboembolism." Eligible criteria were original studies evaluating AI in the prediction of VTE in adults and reporting one of the following outcomes: sensitivity, specificity, positive predictive value, negative predictive value, or area under receiver operating curve (AUC). Risks of bias were assessed using the PROBAST tool. Unpaired t-test was performed to compare the mean AUC from AI versus conventional methods (RAMs or logistic regression models). RESULTS: A total of 20 studies were included. Number of participants ranged from 31 to 111 888. The AI-based models included artificial neural network (six studies), support vector machines (four studies), Bayesian methods (one study), super learner ensemble (one study), genetic programming (one study), unspecified machine learning models (two studies), and multiple machine learning models (five studies). Twelve studies (60%) had both training and testing cohorts. Among 14 studies (70%) where AUCs were reported, the mean AUC for AI versus conventional methods were 0.79 (95% CI: 0.74-0.85) versus 0.61 (95% CI: 0.54-0.68), respectively (p < .001). However, the good to excellent discriminative performance of AI methods is unlikely to be replicated when used in clinical practice, because most studies had high risk of bias due to missing data handling and outcome determination. CONCLUSION: The use of AI appears to improve the accuracy of diagnostic and prognostic prediction of VTE over conventional risk models; however, there was a high risk of bias observed across studies. Future studies should focus on transparent reporting, external validation, and clinical application of these models.

Spontaneous Tumor Lysis Syndrome Secondary to Metastatic Pancreatic Adenocarcinoma.

Spontaneous tumor lysis syndrome (STLS) secondary to metastatic pancreatic adenocarcinoma is a rare clinical phenomenon. An 86-year-old woman with a history of pancreatic cysts presented to the emergency department with progressive fatigue, transaminitis, elevated lactate dehydrogenase, and acute kidney injury of unclear etiology. Abdominal imaging and celiac lymph node biopsy were consistent with metastatic pancreatic adenocarcinoma. Her clinical status deteriorated requiring intensive care unit transfer, and her laboratory results were found to be consistent with STLS. Despite treatment, she entered multisystem organ failure and died shortly after. This case adds to the literature of STLS in pancreatic adenocarcinomas.

Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing.

OBJECTIVE: Leverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. MATERIALS AND METHODS: We trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment. RESULTS: The metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user. DISCUSSION: Our model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings. CONCLUSION: EHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting.

The potential use of artificial intelligence for venous thromboembolism prophylaxis and management: clinician and healthcare informatician perspectives.

Venous thromboembolism (VTE) is the leading cause of preventable death in hospitalized patients. Artificial intelligence (AI) and machine learning (ML) can support guidelines recommending an individualized approach to risk assessment and prophylaxis. We conducted electronic surveys asking clinician and healthcare informaticians about their perspectives on AI/ML for VTE prevention and management. Of 101 respondents to the informatician survey, most were 40 years or older, male, clinicians and data scientists, and had performed research on AI/ML. Of the 607 US-based respondents to the clinician survey, most were 40 years or younger, female, physicians, and had never used AI to inform clinical practice. Most informaticians agreed that AI/ML can be used to manage VTE (56.0%). Over one-third were concerned that clinicians would not use the technology (38.9%), but the majority of clinicians believed that AI/ML probably or definitely can help with VTE prevention (70.1%). The most common concern in both groups was a perceived lack of transparency (informaticians 54.4%; clinicians 25.4%). These two surveys revealed that key stakeholders are interested in AI/ML for VTE prevention and management, and identified potential barriers to address prior to implementation.

Machine learning natural language processing for identifying venous thromboembolism: systematic review and meta-analysis.

ABSTRACT: Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study's best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.

Updated COVID-19 clearance time among patients with cancer in the Delta and Omicron waves.

BACKGROUND: COVID-19 infection delays therapy and in-person evaluation for oncology patients, but clinic clearance criteria are not clearly defined. METHODS: We conducted a retrospective review of oncology patients with COVID-19 at a tertiary care center during the Delta and Omicron waves and compared clearance strategies. RESULTS: Median clearance by two consecutive negative tests was 32.0 days (Interquartile Range [IQR] 22.0-42.5, n = 153) and was prolonged in hematologic malignancy versus solid tumors (35.0 days for hematologic malignancy, 27.5 days for solid tumors, p = 0.01) and in patients receiving B-cell depletion versus other therapies. Median clearance by single negative test was reduced to 23.0 days (IQR 16.0-33.0), with recurrent positive rate 25.4% in hematologic malignancy versus 10.6% in solid tumors (p = 0.02). Clearance by a predefined waiting period required 41 days until an 80% negative rate. CONCLUSIONS: COVID-19 clearance remains prolonged in oncology patients. Single-negative test clearance can balance delays in care with risk of infection in patients with solid tumors.

Evaluating equitable care in the ICU: Creating a causal inference framework to assess the impact of life-sustaining interventions across racial and ethnic groups.

Background: Variability in the provision of intensive care unit (ICU)-interventions may lead to disparities between socially defined racial-ethnic groups. Research Question: We used causal inference to examine the use of invasive mechanical ventilation (IMV), renal replacement therapy (RRT), and vasopressor agents (VP) to identify disparities in outcomes across race-ethnicity in patients with sepsis. Study Design and Methods: Single-center, academic referral hospital in Boston, Massachusetts, USA. Retrospective analysis of treatment effect with a targeted trial design categorized by treatment assignment within the first 24 hours in the MIMIC-IV dataset (2008- 2019) using targeted maximum likelihood estimation. Of 76,943 ICU stays in MIMIC-IV, 32,971 adult stays fulfilling sepsis-3 criteria were included. The primary outcome was in-hospital mortality. Secondary outcomes were hospital-free days, and occurrence of nosocomial infection stratified by predicted mortality probability ranges and self-reported race-ethnicity. Average treatment effects by treatment type and race-ethnicity, Racial-ethnic group (REG) or White group (WG), were estimated. Results: Of 19,419 admissions that met inclusion criteria, median age was 68 years, 57.4% were women, 82% were White, and mortality was 18.2%. There was no difference in mortality benefit associated with the administration of IMV, RRT, or VP between the REG and the WG. There was also no difference in hospital-free days or nosocomial infections. These findings are unchanged with different eligibility periods. Interpretation: There were no differences in the treatment outcomes from three life-sustaining interventions in the ICU according to race-ethnicity. While there was no discernable harm from the treatments across mortality risk, there was also no measurable benefit. These findings highlight the need for research to understand better the risk-benefit of life-sustaining interventions in the ICU.

Venous thromboembolism prophylaxis for hospitalized adult patients: a survey of US health care providers on attitudes and practices.

Background: Venous thromboembolism (VTE) is a leading cause of preventable mortality among hospitalized patients, but appropriate risk assessment and thromboprophylaxis remain underutilized or misapplied. Objectives: We conducted an electronic survey of US health care providers to explore attitudes, practices, and barriers related to thromboprophylaxis in adult hospitalized patients and at discharge. Results: A total of 607 US respondents completed the survey: 63.1% reported working in an academic hospital, 70.7% identified as physicians, and hospital medicine was the most frequent specialty (52.1%). The majority of respondents agreed that VTE prophylaxis is important (98.8%; 95% CI: 97.6%-99.5%) and that current measures are safe (92.6%; 95% CI: 90.2%-94.5%) and effective (93.8%; 95% CI: 91.6%-95.6%), but only half (52.0%; 95% CI: 47.9%-56.0%) believed that hospitalized patients at their institution are on appropriate VTE prophylaxis almost all the time. One-third (35.4%) reported using a risk assessment model (RAM) to determine VTE prophylaxis need; 44.9% reported unfamiliarity with RAMs. The most common recommendation for improving rates of appropriate thromboprophylaxis was to leverage technology. A majority of respondents (84.5%) do not reassess a patient's need for VTE prophylaxis at discharge, and a minority educates patients about the risk (16.2%) or symptoms (18.9%) of VTE at discharge. Conclusion: Despite guideline recommendations to use RAMs, the majority of providers in our survey do not use them. A majority of respondents believed that technology could help improve VTE prophylaxis rates. A majority of respondents do not reassess the risk of VTE at discharge or educate patients about this risk of VTE at discharge.

A systematic review of federated learning applications for biomedical data.

OBJECTIVES: Federated learning (FL) allows multiple institutions to collaboratively develop a machine learning algorithm without sharing their data. Organizations instead share model parameters only, allowing them to benefit from a model built with a larger dataset while maintaining the privacy of their own data. We conducted a systematic review to evaluate the current state of FL in healthcare and discuss the limitations and promise of this technology. METHODS: We conducted a literature search using PRISMA guidelines. At least two reviewers assessed each study for eligibility and extracted a predetermined set of data. The quality of each study was determined using the TRIPOD guideline and PROBAST tool. RESULTS: 13 studies were included in the full systematic review. Most were in the field of oncology (6 of 13; 46.1%), followed by radiology (5 of 13; 38.5%). The majority evaluated imaging results, performed a binary classification prediction task via offline learning (n = 12; 92.3%), and used a centralized topology, aggregation server workflow (n = 10; 76.9%). Most studies were compliant with the major reporting requirements of the TRIPOD guidelines. In all, 6 of 13 (46.2%) of studies were judged at high risk of bias using the PROBAST tool and only 5 studies used publicly available data. CONCLUSION: Federated learning is a growing field in machine learning with many promising uses in healthcare. Few studies have been published to date. Our evaluation found that investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Speaking up about patient-perceived serious visit note errors: Patient and family experiences and recommendations.

BACKGROUND: Open notes invite patients and families to read ambulatory visit notes through the patient portal. Little is known about the extent to which they identify and speak up about perceived errors. Understanding the barriers to speaking up can inform quality improvements. OBJECTIVE: To describe patient and family attitudes, experiences, and barriers related to speaking up about perceived serious note errors. METHODS: Mixed method analysis of a 2016 electronic survey of patients and families at 2 northeast US academic medical centers. Participants had active patient portal accounts and at least 1 note available in the preceding 12 months. RESULTS: 6913 adult patients (response rate 28%) and 3672 pediatric families (response rate 17%) completed the survey. In total, 8724/9392 (93%) agreed that reporting mistakes improves patient safety. Among 8648 participants who read a note, 1434 (17%) perceived ≥1 mistake. 627/1434 (44%) reported the mistake was serious and 342/627 (56%) contacted their provider. Participants who self-identified as Black or African American, Asian, "other," or "multiple" race(s) (OR 0.50; 95% CI (0.26,0.97)) or those who reported poorer health (OR 0.58; 95% CI (0.37,0.90)) were each less likely to speak up than white or healthier respondents, respectively. The most common barriers to speaking up were not knowing how to report a mistake (61%) and avoiding perception as a "troublemaker" (34%). Qualitative analysis of 476 free-text suggestions revealed practical recommendations and proposed innovations for partnering with patients and families. CONCLUSIONS: About half of patients and families who perceived a serious mistake in their notes reported it. Identified barriers demonstrate modifiable issues such as establishing clear mechanisms for reporting and more challenging issues such as creating a supportive culture. Respondents offered new ideas for engaging patients and families in improving note accuracy.

Attitudes, experiences, and safety behaviours of adolescents and young adults who read visit notes: Opportunities to engage patients early in their care.

The Cures Act made access to electronic visit notes ('open notes') nearly universal across the USA, and efforts to share open notes with patients are underway worldwide. This landmark policy change provides an opportunity to engage adolescents and young adults (AYA) early in their care, yet little is known about their attitudes related to reading notes. We compared the responses of 332 AYA (13-25 years old) and 6,914 adults (>25 years old) in a 2016 survey at two USA academic adult and paediatric hospitals. Over 85% of AYA and adults with available notes reported reading at least one note in the prior year. AYA reported similar benefits from note-reading to adults in 15 outcomes related to engagement, relational effects and safety behaviours, supporting efforts to engage AYA as partners in their care using open notes.

A Retrospective Review of 193 Cases of Severe Eosinophilia in the Northeast United States.

BACKGROUND: This retrospective review evaluated the causes of severe eosinophilia (≥5000 eosinophils/L). Higher eosinophilia levels are more likely to cause tissue damage and may reflect disease severity. METHODS: We reviewed 193 cases of patients seen at Beth Israel Deaconess Medical Center in Boston, Massachusetts, and at the University of Vermont Medical Center in Burlington, Vermont, between January 2015 to May 2020 who had a peak absolute eosinophil count of at least 5000/µL. RESULTS: Thirty-nine percent of cases were attributable to a hematologic or oncologic cause. These cases had the highest mean peak absolute eosinophil count at 11,698/µL. Twenty percent of cases were secondary to drug reactions, of which 90% took place in an inpatient setting. Three percent of cases were from helminthic infection, the majority of which were in returning travelers. CONCLUSIONS: In our region of study, hematologic and oncologic cases are important causes of severe eosinophilia, drug reactions are a common etiology in the inpatient setting, and infections are a rare cause.

A Value-Added Health Systems Science Intervention Based on My Life, My Story for Patients Living with HIV and Medical Students: Translating Narrative Medicine from Classroom to Clinic.

In 2018-2019, at the Keck School of Medicine of the University of Southern California (KSOM), we developed and piloted a narrative-based health systems science intervention for patients living with HIV and medical students in which medical students co-wrote patients' life narratives for inclusion in the electronic health record. The pilot study aimed to assess the acceptability of the "life narrative protocol" (LNP) from multiple stakeholder positions and characterize participants' experiences of the clinical and pedagogical implications of the LNP. Students were recruited from KSOM. Patients and staff were recruited from the Maternal, Child, and Adolescent/Adult Center for Infectious Disease and Virology (MCA) at Los Angeles County+USC Medical Center. Ten patients, seventeen students, and ten MCA staff participated in the pilot study. Qualitative methods were used to gather data from students', patients', and staff's perspectives. Three themes emerged from the thematic analysis: (1) patients' life narratives conveyed their unique life experiences and voices; (2) the protocol could result in wide-ranging effects on HIV care; (3) the LNP enabled students to contribute value to patients' healthcare. Across groups, participants considered the LNP an acceptable intervention. The LNP, its limitations, and implications for HIV care, narrative medicine, and health information technology are presented.

Hematologic Abnormalities in Patients With Hidradenitis Suppurativa Receiving Adalimumab.

This post hoc analysis of PIONEER I and II randomized clinical trials assesses whether receiving adalimumab is associated with decreased hematologic abnormalities and increased clinical improvement in patients with hidradenitis suppurativa.

Management and outcome of antenatally diagnosed congenital cystic adenomatoid malformation of the lung.

OBJECTIVE: To review the management and outcome of babies with antenatally diagnosed congenital cystic adenomatoid malformation. DESIGN: Retrospective cohort review. SETTING: Tertiary neonatal care unit at Queen Mary Hospital and antenatal diagnostic centre at Tsan Yuk Hospital. PATIENTS: Consecutive patients with antenatally suspected congenital cystic adenomatoid malformation in their concepti among antenatal patients attending Tsan Yuk Hospital from 1994 to 2002. Twenty-four of 33 cases were referred to Queen Mary Hospital for postnatal management and for whom comprehensive records were available for analysis in 23. INTERVENTIONS: Postnatal interventions in their babies included investigational imaging for congenital cystic adenomatoid malformation and surgery. MAIN OUTCOME MEASURES: Antenatal and postnatal outcome, as well as pathology of the excised lesions. RESULTS: Antenatal outcome: termination of pregnancy in two cases and spontaneous abortion in one; in-utero regression was documented in nine cases and in one hydropic change was apparent. Postnatal outcome: only eight of 20 babies born alive had symptoms in neonatal period. Two developed serious infective complications in infancy, one with documented in-utero regression. Pulmonary parenchymal abnormalities were detected on computed tomography of the thorax in six of seven cases with normal or non-specific chest radiograph findings. Among nine cases with in-utero regression, congenital cystic adenomatoid malformation was confirmed by operative histology in five and abnormal computed tomography findings in three. Fifteen babies underwent surgical excision, one of whom died because of severe pre-existing pulmonary hypoplasia and nine endured minor postoperative complications. A favourable outcome was documented at a mean follow-up of 22 months (range, 2 months-7 years). CONCLUSIONS: In-utero regression of congenital cystic adenomatoid malformation on antenatal ultrasound may not represent genuine resolution. Computed tomographic thorax should be considered in all newborns with antenatally diagnosed congenital cystic adenomatoid malformation, and if confirmed early operation before first hospital discharge is recommended.

Randomized trial comparing two natural surfactants (Survanta vs. bLES) for treatment of neonatal respiratory distress syndrome.

Exogenous surfactants have been used as an effective treatment of neonatal respiratory distress syndrome (RDS). Different preparations of surfactant carry different biophysical and clinical properties. To study the response pattern and treatment outcome of two natural surfactants (bLES and Survanta) for the treatment of RDS, we conducted a randomized clinical trial at the neonatal unit of a university teaching hospital. Premature babies with birth weight between 500-1,800 g who developed RDS requiring mechanical ventilation with an oxygen requirement of more than 30% within 6 hr of life were randomized into two treatment groups. Oxygenation indices (OIs) within 12 hr of treatment were compared as primary outcomes, while neonatal complications were analyzed as secondary outcomes of the study. Sixty babies were recruited, with 29 in the bLES and 31 in the Survanta treatment group. Both groups had significant and sustained improvements in OI after surfactant replacement therapy (SRT), while the bLES group was associated with a significantly lower OI throughout the initial 12 hr after treatment compared with the Survanta group. There was no difference in secondary outcomes including mortality, ventilator days, and occurrence of chronic lung disease. We conclude that infants with RDS respond favorably to both types of surfactant replacement, and that bLES achieved a faster clinical response in terms of improvement in OI than Survanta.