A proteome-scale map of the human interactome network.

Just as reference genome sequences revolutionized human genetics, reference maps of interactome networks will be critical to fully understand genotype-phenotype relationships. Here, we describe a systematic map of ?14,000 high-quality human binary protein-protein interactions. At equal quality, this map is ?30% larger than what is available from small-scale studies published in the literature in the last few decades. While currently available information is highly biased and only covers a relatively small portion of the proteome, our systematic map appears strikingly more homogeneous, revealing a "broader" human interactome network than currently appreciated. The map also uncovers significant interconnectivity between known and candidate cancer gene products, providing unbiased evidence for an expanded functional cancer landscape, while demonstrating how high-quality interactome models will help "connect the dots" of the genomic revolution.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis.

BACKGROUND: Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality. OBJECTIVE: This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data. METHODS: In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips. RESULTS: Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance. CONCLUSIONS: Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

Artificial Intelligence to Determine Fetal Sex.

OBJECTIVE: This proof-of-concept study assessed how confidently an artificial intelligence (AI) model can determine the sex of a fetus from an ultrasound image. STUDY DESIGN: Analysis was performed using 19,212 ultrasound image slices from a high-volume fetal sex determination practice. This dataset was split into a training set (11,769) and test set (7,443). A computer vision model was trained using a transfer learning approach with EfficientNetB4 architecture as base. The performance of the computer vision model was evaluated on the hold out test set. Accuracy, Cohen's Kappa and Multiclass Receiver Operating Characteristic area under the curve (AUC) were used to evaluate the performance of the model. RESULTS: The AI model achieved an Accuracy of 88.27% on the holdout test set and a Cohen's Kappa score 0.843. The ROC AUC score for Male was calculated to be 0.896, for Female a score of 0.897, for Unable to Assess a score of 0.916, and for Text Added a score of 0.981 was achieved. CONCLUSION: This novel AI model proved to have a high rate of fetal sex capture that could be of significant use in areas where ultrasound expertise is not readily available. KEY POINTS: · This is the first proof-of-concept AI model to determine fetal sex.. · This study adds to the growing research in ultrasound AI.. · Our findings demonstrate AI integration into obstetric care..

Accuracy of Parent-Reported Allergies and Medications in Pediatric Dentistry.

Purpose: To measure the accuracy of parent-reported allergies and medication usage by comparing parental reports during dental con- sultations to medical reports from their child's primary care physician. Methods: A retrospective chart review was performed for 862 eligible patients 17 years and younger seen in the Department of Pediatric Dentistry at Franciscan Children's, Boston, Mass., USA, and who were required to obtain medical clearance prior to initiating dental treatment with sedation or general anesthesia. Allergies were categorized into three groups: food, environmental, and drug allergies. Allergies in each category reported by the parents were compared to the physician-reported allergies to assess for accuracy. Medications reported by the parents were also compared to the total number of medications reported by the physician and categorized as a full, partial, or non-match. Results: The sensitivity of parental identification for drug, food, and environmental allergies was 50.9 percent, 48.1 percent, and 18.8 percent, respectively. Of the 245 patients taking prescription medications, 53.1 percent of parents were unable to identify any of their child's medications, 22.9 percent of parents were partially able to identify their child's medications, and only 24.1 percent of parents were able to identify their child's medications fully. Among parents of children who take one or more medications as reported by their physician, the average reporting accuracy was 34.7 percent. Conclusion: Utilizing interprofessional collaboration is warranted in identifying accurate reports of patient allergies and medication usage in the pediatric population to prevent adverse reactions and improve the overall quality of dental care.

Comparison of pulmonary congestion severity using artificial intelligence-assisted scoring versus clinical experts: A secondary analysis of BLUSHED-AHF.

AIM: Acute decompensated heart failure (ADHF) is the leading cause of cardiovascular hospitalizations in the United States. Detecting B-lines through lung ultrasound (LUS) can enhance clinicians' prognostic and diagnostic capabilities. Artificial intelligence/machine learning (AI/ML)-based automated guidance systems may allow novice users to apply LUS to clinical care. We investigated whether an AI/ML automated LUS congestion score correlates with expert's interpretations of B-line quantification from an external patient dataset. METHODS AND RESULTS: This was a secondary analysis from the BLUSHED-AHF study which investigated the effect of LUS-guided therapy on patients with ADHF. In BLUSHED-AHF, LUS was performed and B-lines were quantified by ultrasound operators. Two experts then separately quantified the number of B-lines per ultrasound video clip recorded. Here, an AI/ML-based lung congestion score (LCS) was calculated for all LUS clips from BLUSHED-AHF. Spearman correlation was computed between LCS and counts from each of the original three raters. A total of 3858 LUS clips were analysed on 130 patients. The LCS demonstrated good agreement with the two experts' B-line quantification score (r = 0.894, 0.882). Both experts' B-line quantification scores had significantly better agreement with the LCS than they did with the ultrasound operator's score (p < 0.005, p < 0.001). CONCLUSION: Artificial intelligence/machine learning-based LCS correlated with expert-level B-line quantification. Future studies are needed to determine whether automated tools may assist novice users in LUS interpretation.

Deep Learning for Detection and Localization of B-Lines in Lung Ultrasound.

Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish, BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel "single-point" approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F 1-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.

Accuracy of parent-reported health history in a dental setting.

BACKGROUND: Obtaining thorough documentation of a patient's medical history is important for dental care professionals, as oral health is connected intricately to systemic health. The purpose of this study was to assess the accuracy of parent-reported health history for pediatric patients in a dental setting. METHODS: A retrospective chart review was conducted on 863 patients 17 years and younger. Parent-reported health history was compared with subsequent physician-to-dentist consultations. The most common diagnoses were grouped on the basis of International Statistical Classification of Diseases and Related Health Problems, Tenth Revision, categories. RESULTS: The sensitivity of parent report of health conditions was highest for reporting mental and behavioral disorders (75.1%; 95% CI, 69.6% to 80.0%), followed by nervous system diseases (63.0%; 95% CI, 47.5% to 76.8%), respiratory conditions (47.9%; 95% CI, 37.6% to 58.4%), congenital conditions (46.3%; 95% CI, 30.7% to 62.6%), and cardiovascular conditions (25.0%; 95% CI, 11.4% to 43.4%) and was lowest for hematologic conditions (12.2%; 95% CI, 4.1% to 26.2%). Parents of children 6 years and older and those with private insurance had higher sensitivity for reporting mental and behavioral conditions than those with children younger than 6 years or having Medicaid (P < .0001). The specificity of parent-reported health conditions ranged from 96.0% for mental and behavioral disorders to 99.8% for hematologic conditions. CONCLUSIONS: Sensitivity varied widely, showing that parents may be unreliable in their report of children's health histories and that dentists cannot rely solely on parents when obtaining health history. PRACTICAL IMPLICATIONS: In advocating for patient safety, especially for those with special needs and complex medical conditions, this study supports the use of medical evaluation before dental treatment and for the integration of dental and electronic health records.

Programmable CRISPR-Cas Repression, Activation, and Computation with Sequence-Independent Targets and Triggers.

The programmability of CRISPR-derived Cas9 as a sequence-specific DNA-targeting protein has made it a powerful tool for genomic manipulation in biological research and translational applications. Cas9 activity can be programmably engineered to respond to nucleic acids, but these efforts have focused primarily on single-input control of Cas9, and until recently, they were limited by sequence dependence between parts of the guide RNA and the sequence to be detected. Here, we not only design and present DNA- and RNA-sensing conditional guide RNA (cgRNA) that have no such sequence constraints, but also demonstrate a complete set of logical computations using these designs on DNA and RNA sequence inputs, including AND, OR, NAND, and NOR. The development of sequence-independent nucleic acid-sensing CRISPR-Cas9 systems with multi-input logic computation capabilities could lead to improved genome engineering and regulation as well as the construction of synthetic circuits with broader functionality.

Enhanced lung tumor development in tobacco smoke-exposed p53 transgenic and Kras2 heterozygous deficient mice.

A/J mice bearing either a mutation in the p53 gene or a Kras2 heterozygous deficiency were investigated for their susceptibility to tobacco smoke-induced lung tumorigenesis. Transgenic mice and their wild-type littermates were exposed to mainstream tobacco smoke (MS) for 5 mo, followed by 4 mo of recovery in filtered air. In sham (filtered air) groups, p53 transgenic mice did not exhibit a higher tumor multiplicity but did exhibit larger tumors, with tumor load increased 3.6-fold, when compared with wild-type mice. With exposure to MS, tumor multiplicity was increased 60% but there was a strikingly increased tumor load (15.9-fold) in p53 transgenic mice. Increased tumor load (5.3-fold) but not tumor multiplicity was seen in MS-exposed Kras2 heterozygous deficient mice. Interestingly, MS exposure did not increase benzo[a]pyrene-induced lung tumorigenesis when MS exposure was initiated after BaP treatment. These results indicate that a p53 mutation or loss of a Kras2 allele increases susceptibility to MS-induced lung tumor development.

Using ALoFT to determine the impact of putative loss-of-function variants in protein-coding genes.

Variants predicted to result in the loss of function of human genes have attracted interest because of their clinical impact and surprising prevalence in healthy individuals. Here, we present ALoFT (annotation of loss-of-function transcripts), a method to annotate and predict the disease-causing potential of loss-of-function variants. Using data from Mendelian disease-gene discovery projects, we show that ALoFT can distinguish between loss-of-function variants that are deleterious as heterozygotes and those causing disease only in the homozygous state. Investigation of variants discovered in healthy populations suggests that each individual carries at least two heterozygous premature stop alleles that could potentially lead to disease if present as homozygotes. When applied to de novo putative loss-of-function variants in autism-affected families, ALoFT distinguishes between deleterious variants in patients and benign variants in unaffected siblings. Finally, analysis of somatic variants in >6500 cancer exomes shows that putative loss-of-function variants predicted to be deleterious by ALoFT are enriched in known driver genes.Variants causing loss of function (LoF) of human genes have clinical implications. Here, the authors present a method to predict disease-causing potential of LoF variants, ALoFT (annotation of Loss-of-Function Transcripts) and show its application to interpreting LoF variants in different contexts.

A systematic survey of loss-of-function variants in human protein-coding genes.

Genome-sequencing studies indicate that all humans carry many genetic variants predicted to cause loss of function (LoF) of protein-coding genes, suggesting unexpected redundancy in the human genome. Here we apply stringent filters to 2951 putative LoF variants obtained from 185 human genomes to determine their true prevalence and properties. We estimate that human genomes typically contain ~100 genuine LoF variants with ~20 genes completely inactivated. We identify rare and likely deleterious LoF alleles, including 26 known and 21 predicted severe disease-causing variants, as well as common LoF variants in nonessential genes. We describe functional and evolutionary differences between LoF-tolerant and recessive disease genes and a method for using these differences to prioritize candidate genes found in clinical sequencing studies.