Charting Single Cell Lineage Dynamics and Mutation Networks via Homing CRISPR.

Single cell lineage tracing, essential for unraveling cellular dynamics in disease evolution is critical for developing targeted therapies. CRISPR-Cas9, known for inducing permanent and cumulative mutations, is a cornerstone in lineage tracing. The novel homing guide RNA (hgRNA) technology enhances this by enabling dynamic retargeting and facilitating ongoing genetic modifications. Charting these mutations, especially through successive hgRNA edits, poses a significant challenge. Our solution, LINEMAP, is a computational framework designed to trace and map these mutations with precision. LINEMAP meticulously discerns mutation alleles at single-cell resolution and maps their complex interrelationships through a mutation evolution network. By utilizing a Markov Process model, we can predict mutation transition probabilities, revealing potential mutational routes and pathways. Our reconstruction algorithm, anchored in the Markov model's attributes, reconstructs cellular lineage pathways, shedding light on the cell's evolutionary journey to the minutiae of single-cell division. Our findings reveal an intricate network of mutation evolution paired with a predictive Markov model, advancing our capability to reconstruct single-cell lineage via hgRNA. This has substantial implications for advancing our understanding of biological mechanisms and propelling medical research forward.

A Deep Learning Decision Support Tool to Improve Risk Stratification and Reduce Unnecessary Biopsies in BI-RADS 4 Mammograms.

Purpose: To evaluate the performance of a biopsy decision support algorithmic model, the intelligent-augmented breast cancer risk calculator (iBRISK), on a multicenter patient dataset. Materials and Methods: iBRISK was previously developed by applying deep learning to clinical risk factors and mammographic descriptors from 9700 patient records at the primary institution and validated using another 1078 patients. All patients were seen from March 2006 to December 2016. In this multicenter study, iBRISK was further assessed on an independent, retrospective dataset (January 2015-June 2019) from three major health care institutions in Texas, with Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. Data were dichotomized and trichotomized to measure precision in risk stratification and probability of malignancy (POM) estimation. iBRISK score was also evaluated as a continuous predictor of malignancy, and cost savings analysis was performed. Results: The iBRISK model's accuracy was 89.5%, area under the receiver operating characteristic curve (AUC) was 0.93 (95% CI: 0.92, 0.95), sensitivity was 100%, and specificity was 81%. A total of 4209 women (median age, 56 years [IQR, 45-65 years]) were included in the multicenter dataset. Only two of 1228 patients (0.16%) in the "low" POM group had malignant lesions, while in the "high" POM group, the malignancy rate was 85.9%. iBRISK score as a continuous predictor of malignancy yielded an AUC of 0.97 (95% CI: 0.97, 0.98). Estimated potential cost savings were more than $420 million. Conclusion: iBRISK demonstrated high sensitivity in the malignancy prediction of BI-RADS 4 lesions. iBRISK may safely obviate biopsies in up to 50% of patients in low or moderate POM groups and reduce biopsy-associated costs.Keywords: Mammography, Breast, Oncology, Biopsy/Needle Aspiration, Radiomics, Precision Mammography, AI-augmented Biopsy Decision Support Tool, Breast Cancer Risk Calculator, BI-RADS 4 Mammography Risk Stratification, Overbiopsy Reduction, Probability of Malignancy (POM) Assessment, Biopsy-based Positive Predictive Value (PPV3) Supplemental material is available for this article. Published under a CC BY 4.0 license.See also the commentary by McDonald and Conant in this issue.

An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients.

Healthcare regulatory agencies have mandated a reduction in 30-day hospital readmission rates and have targeted COPD as a major contributor to 30-day readmissions. We aimed to develop and validate a simple tool deploying an artificial neural network (ANN) for early identification of COPD patients with high readmission risk. Using COPD patient data from eight hospitals within a large urban hospital system, four variables were identified, weighted and validated. These included the number of in-patient admissions in the previous 6 months, the number of medications administered on the first day, insurance status, and the Rothman Index on hospital day one. An ANN model was trained to provide a predictive algorithm and validated on an additional dataset from a separate time period. The model was implemented in a smartphone app (Re-Admit) incorporating four input risk factors, and a clinical care plan focused on high-risk readmission candidates was then implemented. Subsequent readmission data was analyzed to assess impact. The areas under the curve of receiver operating characteristics predicting readmission with ANN is 0.77, with sensitivity 0.75 and specificity 0.67 on the separate validation data. Readmission rates in the COPD high-risk subgroup after app and clinical intervention implementation saw a significant 48% decline. Our studies show the efficacy of ANN model on predicting readmission risks for COPD patients. The AI enabled Re-Admit smartphone app predicts readmission risk on day one of the patient's admission, allowing for early implementation of medical, hospital, and community resources to optimize and improve clinical care pathways.

Risk factors and machine learning model for predicting hospitalization outcomes in geriatric patients with dementia.

Introduction: Geriatric patients with dementia incur higher healthcare costs and longer hospital stays than other geriatric patients. We aimed to identify risk factors for hospitalization outcomes that could be mitigated early to improve outcomes and impact overall quality of life. Methods: We identified risk factors, that is, demographics, hospital complications, pre-admission, and post-admission risk factors including medical history and comorbidities, affecting hospitalization outcomes determined by hospital stays and discharge dispositions. Over 150 clinical and demographic factors of 15,678 encounters (8407 patients) were retrieved from our institution's data warehouse. We further narrowed them down to twenty factors through feature selection engineering by using analysis of variance (ANOVA) and Glmnet. We developed an explainable machine-learning model to predict hospitalization outcomes among geriatric patients with dementia. Results: Our model is based on stacking ensemble learning and achieved accuracy of 95.6% and area under the curve (AUC) of 0.757. It outperformed prevalent methods of risk assessment for encounters of patients with Alzheimer's disease dementia (ADD) (4993), vascular dementia (VD) (4173), Parkinson's disease with dementia (PDD) (3735), and other unspecified dementias (OUD) (2777). Top identified hospitalization outcome risk factors, mostly from medical history, include encephalopathy, number of medical problems at admission, pressure ulcers, urinary tract infections, falls, admission source, age, race, anemia, etc., with several overlaps in multi-dementia groups. Discussion: Our model identified several predictive factors that can be modified or intervened so that efforts can be made to prevent recurrence or mitigate their adverse effects. Knowledge of the modifiable risk factors would help guide early interventions for patients at high risk for poor hospitalization outcome as defined by hospital stays longer than seven days, undesirable discharge disposition, or both. The interventions include starting specific protocols on modifiable risk factors like encephalopathy, falls, and infections, where non-existent or not routine, to improve hospitalization outcomes of geriatric patients with dementia. Highlights: A total 15,678 encounters of Geriatrics with dementia with a final 20 risk factors.Developed a predictive model for hospitalization outcomes for multi-dementia types.Risk factors for each type were identified including those amenable to interventions.Top factors are encephalopathy, pressure ulcers, urinary tract infection (UTI), falls, and admission source.With accuracy of 95.6%, our ensemble predictive model outperforms other models.

A comparative efficacy study of diagnostic digital breast tomosynthesis and digital mammography in BI-RADS 4 breast cancer diagnosis.

PURPOSE: Probability of malignancy for BI-RADS 4-designated breast lesions ranges from 2% to 95%, contributing to high false-positive biopsy rates. We compare clinical performance of digital breast tomosynthesis (DBT) versus digital mammography (2D) among our BI-RADS 4 population without prior history of breast cancer. METHODS: We extracted retrospective data i.e., clinical, mammogram reports, and biopsy data, from electronic medical records across Houston Methodist's nine hospitals for patients who underwent diagnostic examinations using both modalities (02/01/2015 - 09/30/2020). 2D and DBT cohorts were not intra-individual matched, and there was no direct mammogram evaluation. Using Student's t test, Fisher's exact test, and Chi-squared test, we evaluated the data to determine statistical significance of differences between modalities in BI-RADS 4 cases. We calculated adjusted odds-ratio between modalities for cancer detection rate (CDR) and biopsy-derived positive predictive value (PPV3). RESULTS: There were 6,356 encounters (6,020 patients) in 2D and 5,896 encounters (5,637 patients) in DBT assessed as BI-RADS 4. Using Fisher's exact test, DBT mammography cases were significantly assessed as BI-RADS 4 5.66% more often than those undergoing 2D mammography, P = 0.0046 (1.0566 95% CI: 1.0169-1.0977). The CDRs were 112.65 (2D) and 120.76 (DBT), adjusted odds-ratio: 1.04 (0.93, 1.16)), P = 0.5029, while PPV3 were 14.41% (2D) and 15.99% (DBT), adjusted odds-ratio: 1.09 (0.97, 1.22), P = 0.1483; both logistic regression-adjusted for all other factors. CONCLUSION: DBT did not achieve better performance and sensitivity in assigning BI-RADS 4 cases compared with 2D, showed no significant advantage in CDR and PPV3, and does not reduce false-positive biopsies among BI-RADS 4-assessed patients.

An imageomics and multi-network based deep learning model for risk assessment of liver transplantation for hepatocellular cancer.

INTRODUCTION: Liver transplantation (LT) is an effective treatment for hepatocellular carcinoma (HCC), the most common type of primary liver cancer. Patients with small HCC (<5 cm) are given priority over others for transplantation due to clinical allocation policies based on tumor size. Attempting to shift from the prevalent paradigm that successful transplantation and longer disease-free survival can only be achieved in patients with small HCC to expanding the transplantation option to patients with HCC of the highest tumor burden (>5 cm), we developed a convergent artificial intelligence (AI) model that combines transient clinical data with quantitative histologic and radiomic features for more objective risk assessment of liver transplantation for HCC patients. METHODS: Patients who received a LT for HCC between 2008-2019 were eligible for inclusion in the analysis. All patients with post-LT recurrence were included, and those without recurrence were randomly selected for inclusion in the deep learning model. Pre- and post-transplant magnetic resonance imaging (MRI) scans and reports were compressed using CapsNet networks and natural language processing, respectively, as input for a multiple feature radial basis function network. We applied a histological image analysis algorithm to detect pathologic areas of interest from explant tissue of patients who recurred. The multilayer perceptron was designed as a feed-forward, supervised neural network topology, with the final assessment of recurrence risk. We used area under the curve (AUC) and F-1 score to assess the predictability of different network combinations. RESULTS: A total of 109 patients were included (87 in the training group, 22 in the testing group), of which 20 were positive for cancer recurrence. Seven models (AUC; F-1 score) were generated, including clinical features only (0.55; 0.52), magnetic resonance imaging (MRI) only (0.64; 0.61), pathological images only (0.64; 0.61), MRI plus pathology (0.68; 0.65), MRI plus clinical (0.78, 0.75), pathology plus clinical (0.77; 0.73), and a combination of clinical, MRI, and pathology features (0.87; 0.84). The final combined model showed 80 % recall and 89 % precision. The total accuracy of the implemented model was 82 %. CONCLUSION: We validated that the deep learning model combining clinical features and multi-scale histopathologic and radiomic image features can be used to discover risk factors for recurrence beyond tumor size and biomarker analysis. Such a predictive, convergent AI model has the potential to alter the LT allocation system for HCC patients and expand the transplantation treatment option to patients with HCC of the highest tumor burden.

Analysis of the Implementation of Telehealth Visits for Care of Patients With Cancer in Houston During the COVID-19 Pandemic.

PURPOSE: The purpose of this study was to evaluate the use of telemedicine amid the SARS-CoV-2 pandemic in patients with cancer and assess barriers to its implementation. PATIENTS AND METHODS: Telehealth video visits, using the Houston Methodist MyChart platform, were offered to patients with cancer as an alternative to in-person visits. Reasons given by patients who declined to use video visits were documented, and demographic information was collected from all patients. Surveys were used to assess the levels of satisfaction of treating physicians and patients who agreed to video visits. RESULTS: Of 1,762 patients with cancer who were offered telehealth video visits, 1,477 (83.8%) participated. The patients who declined participation were older (67.7 v 60.2 years; P < .0001), lived in significantly lower-income areas (P = .0021), and were less likely to have commercial insurance (P < .0001) than patients who participated. Most participating patients (92.6%) were satisfied with telehealth video visits. A majority of physicians (65.2%) were also satisfied with its use, and 74% indicated that they would likely use telemedicine in the future. Primary concerns that physicians had in using this technology were inadequate patient interactions and acquisition of medical data, increased potential for missing significant clinical findings, decreased quality of care, and potential medical liability. CONCLUSION: Oncology/hematology patients and their physicians expressed high levels of satisfaction with the use of telehealth video visits. Despite recent advances in technology, there are still opportunities to improve the equal implementation of telemedicine for the medical care of vulnerable older, low-income, and underinsured patient populations.

Sepsis outcomes in solid organ transplant recipients.

BACKGROUND: We present data on a cohort of patients diagnosed with sepsis over a 10-year period comparing outcomes in solid organ transplant (SOT) and non-solid organ transplant (non-SOT) recipients. METHODS: This is a retrospective single-center study of patients with diagnosis of sepsis from 1/1/06 to 6/30/16. Cases and controls were matched by year of sepsis diagnosis with propensity score matching. Conditional logistic regression and repeated measurement models were performed for binary outcomes. Trends over time for in-hospital mortality were determined using the Cochran-Armitage test. A gamma-distributed model was performed on the continuous variables. RESULTS: Overall, there were 18 632 admission encounters with a discharge diagnosis of sepsis in 14 780 unique patients. Of those admissions, 1689 were SOT recipients. After 1:1 matching by year, there were three thousand three hundred and forty patients (1670 cases; 1670 controls) diagnosed with sepsis. There was a decreasing trend for in-hospital mortality for sepsis over time in SOT patients and non-SOT patients (P < .05) due to early sepsis recognition and improved standard of care. Despite higher comorbidities in the SOT group, conditional logistic regression showed that in-hospital mortality for sepsis in SOT patients was similar compared with non-SOT patients (odds ratio [OR] =1.14 [95% confidence interval {CI}, 0.95-1.37], P = .161). However, heart and lung SOT subgroups had higher odds of dying compared with the non-SOT group (OR = 1.83 [95% CI, 1.30-2.57], P < .001 and OR = 1.77 [95% CI, 1.34-2.34], P < .001). On average, SOT patients had 2 days longer hospital length of stay compared with non-SOT admissions (17.00 ± 19.54 vs 15.23 ± 17.07, P < .05). Additionally, SOT patients had higher odds of hospital readmission within 30 days (OR = 1.25 [95% CI, 1.06-1.51], P = .020), and higher odds for DIC compared with non-SOT patients (OR = 1.76 [95% CI, 1.10-2.86], P = .021). CONCLUSION: Sepsis in solid organ transplants and non-solid organ transplant patients have similar mortality; however, the subset of heart and lung transplant recipients with sepsis has a higher rate of mortality compared with the non-solid organ transplant recipients. SOT with sepsis as a group has a higher hospital readmission rate compared with non-transplant sepsis patients.

Preventing inpatient falls with injuries using integrative machine learning prediction: a cohort study.

Patient falls during hospitalization can lead to severe injuries and remain one of the most vexing patient-safety problems facing hospitals. They lead to increased medical care costs, lengthened hospital stays, more litigation, and even death. Existing methods and technology to address this problem mostly focus on stratifying inpatients at risk, without predicting fall severity or injuries. Here, a retrospective cohort study was designed and performed to predict the severity of inpatient falls, based on a machine learning classifier integrating multi-view ensemble learning and model-based missing data imputation method. As input, over two thousand inpatient fall patients' demographic characteristics, diagnoses, procedural data, and bone density measurements were retrieved from the HMH clinical data warehouse from two separate time periods. The predictive classifier developed based on multi-view ensemble learning with missing values (MELMV) outperformed other three baseline models; achieved a cross-validated AUC of 0.713 (95% CI, 0.701-0.725), an AUC of 0.808 (95% CI, 0.740-0.876) on the separate testing set. Our studies show the efficacy of integrative machine-learning based classifier model in dealing with multi-source patient data, which in this case delivers robust predictive performance on the severity of patient falls. The severe fall index provided by the MELMV classifier is calculated to identify inpatients who are at risk of having severe injuries if they fall, thus triggering additional steps of intervention to prevent a harmful fall, beyond the standard-of-care procedure for all high-risk fall patients.

A Deep Learning-Based Decision Support Tool for Precision Risk Assessment of Breast Cancer.

PURPOSE: The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk. METHODS: BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores. RESULTS: For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93. CONCLUSION: BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.

A Behavior-Modification, Clinical-Grade Mobile Application to Improve Breast Cancer Survivors' Accountability and Health Outcomes.

PURPOSE: Only 34% of breast cancer survivors engage in the recommended level of physical activity because of a lack of accountability and motivation. Methodist Hospital Cancer Health Application (MOCHA) is a smartphone tool created specifically for self-reinforcement for patients with cancer through the daily accounting of activity and nutrition and direct interaction with clinical dietitians. We hypothesize that use of MOCHA will improve the accountability of breast cancer survivors and help them reach their personalized goals. PATIENTS AND METHODS: Women with stages I to III breast cancer who were at least 6 months post-active treatment with a body mass index (BMI) greater than 25 kg/m2 were enrolled in a 4-week feasibility trial. The primary objective was to demonstrate adherence during weeks 2 and 3 of the 4-week study period (14 days total). The secondary objective was to determine the usability of MOCHA according to the system usability scale. The exploratory objective was to determine weight loss and dietitian-participant interaction. RESULTS: We enrolled 33 breast cancer survivors who had an average BMI of 31.6 kg/m2. Twenty-five survivors completed the study, and the average number of daily uses was approximately 3.5 (range, 0 to 12) times/day; participants lost an average of 2 lbs (+4 lbs to -10.6 lbs). The average score of usability (the second objective) was 77.4, which was greater than the acceptable level. More than 90% of patients found MOCHA easy to navigate, and 84% were motivated to use MOCHA daily. CONCLUSION: This study emphasizes the importance of technology use to improve goal adherence for patients by providing real-time feedback and accountability with the health care team. MOCHA focuses on the engagement of the health care team and is integrated into clinical workflow. Future directions will use MOCHA in a long-term behavior modification study.